Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- README.md +55 -0
- checkpoint-100/README.md +204 -0
- checkpoint-100/adapter_config.json +33 -0
- checkpoint-100/adapter_model.safetensors +3 -0
- checkpoint-100/optimizer.pt +3 -0
- checkpoint-100/pytorch_model.bin +3 -0
- checkpoint-100/rng_state.pth +3 -0
- checkpoint-100/scheduler.pt +3 -0
- checkpoint-100/special_tokens_map.json +29 -0
- checkpoint-100/tokenizer.json +0 -0
- checkpoint-100/tokenizer.model +3 -0
- checkpoint-100/tokenizer_config.json +50 -0
- checkpoint-100/trainer_state.json +629 -0
- checkpoint-100/training_args.bin +3 -0
- checkpoint-200/README.md +204 -0
- checkpoint-200/adapter_config.json +33 -0
- checkpoint-200/adapter_model.safetensors +3 -0
- checkpoint-200/optimizer.pt +3 -0
- checkpoint-200/pytorch_model.bin +3 -0
- checkpoint-200/rng_state.pth +3 -0
- checkpoint-200/scheduler.pt +3 -0
- checkpoint-200/special_tokens_map.json +29 -0
- checkpoint-200/tokenizer.json +0 -0
- checkpoint-200/tokenizer.model +3 -0
- checkpoint-200/tokenizer_config.json +50 -0
- checkpoint-200/trainer_state.json +1237 -0
- checkpoint-200/training_args.bin +3 -0
- checkpoint-300/README.md +204 -0
- checkpoint-300/adapter_config.json +33 -0
- checkpoint-300/adapter_model.safetensors +3 -0
- checkpoint-300/optimizer.pt +3 -0
- checkpoint-300/pytorch_model.bin +3 -0
- checkpoint-300/rng_state.pth +3 -0
- checkpoint-300/scheduler.pt +3 -0
- checkpoint-300/special_tokens_map.json +29 -0
- checkpoint-300/tokenizer.json +0 -0
- checkpoint-300/tokenizer.model +3 -0
- checkpoint-300/tokenizer_config.json +50 -0
- checkpoint-300/trainer_state.json +1845 -0
- checkpoint-300/training_args.bin +3 -0
- checkpoint-400/README.md +204 -0
- checkpoint-400/adapter_config.json +33 -0
- checkpoint-400/adapter_model.safetensors +3 -0
- checkpoint-400/optimizer.pt +3 -0
- checkpoint-400/pytorch_model.bin +3 -0
- checkpoint-400/rng_state.pth +3 -0
- checkpoint-400/scheduler.pt +3 -0
- checkpoint-400/special_tokens_map.json +29 -0
- checkpoint-400/tokenizer.json +0 -0
- checkpoint-400/tokenizer.model +3 -0
README.md
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- en
|
| 4 |
+
license: apache-2.0
|
| 5 |
+
tags:
|
| 6 |
+
- mistral
|
| 7 |
+
- Eclipse-7B
|
| 8 |
+
pipeline_tag: text-generation
|
| 9 |
+
---
|
| 10 |
+
# Model Card for Eclipse-7B
|
| 11 |
+
|
| 12 |
+
Mistral-7B-v0.1 model fine-tuned on the Ultrafeedback dataset using techinques shown in the paper [Self-Rewarding Language Models](https://arxiv.org/abs/2401.10020).
|
| 13 |
+
|
| 14 |
+
## Instruction format
|
| 15 |
+
|
| 16 |
+
In order to leverage instruction fine-tuning, your prompt should be surrounded by `[INST]` and `[/INST]` tokens. The very first instruction should begin with a begin of sentence id. The next instructions should not. The assistant generation will be ended by the end-of-sentence token id.
|
| 17 |
+
|
| 18 |
+
E.g.
|
| 19 |
+
```
|
| 20 |
+
text = "<s>[INST] What is your favourite condiment? [/INST]"
|
| 21 |
+
"Well, I'm quite partial to a good squeeze of fresh lemon juice. It adds just the right amount of zesty flavour to whatever I'm cooking up in the kitchen!</s> "
|
| 22 |
+
"[INST] Do you have mayonnaise recipes? [/INST]"
|
| 23 |
+
```
|
| 24 |
+
|
| 25 |
+
This format is available as a [chat template](https://huggingface.co/docs/transformers/main/chat_templating) via the `apply_chat_template()` method:
|
| 26 |
+
|
| 27 |
+
```python
|
| 28 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 29 |
+
|
| 30 |
+
device = "cuda" # the device to load the model onto
|
| 31 |
+
|
| 32 |
+
model = AutoModelForCausalLM.from_pretrained("Xenon1/Eclipse-7B")
|
| 33 |
+
tokenizer = AutoTokenizer.from_pretrained("Xenon1/Eclipse-7B")
|
| 34 |
+
|
| 35 |
+
messages = [
|
| 36 |
+
{"role": "user", "content": "What is your favourite condiment?"},
|
| 37 |
+
{"role": "assistant", "content": "Well, I'm quite partial to a good squeeze of fresh lemon juice. It adds just the right amount of zesty flavour to whatever I'm cooking up in the kitchen!"},
|
| 38 |
+
{"role": "user", "content": "Do you have mayonnaise recipes?"}
|
| 39 |
+
]
|
| 40 |
+
|
| 41 |
+
encodeds = tokenizer.apply_chat_template(messages, return_tensors="pt")
|
| 42 |
+
|
| 43 |
+
model_inputs = encodeds.to(device)
|
| 44 |
+
model.to(device)
|
| 45 |
+
|
| 46 |
+
generated_ids = model.generate(model_inputs, max_new_tokens=1000, do_sample=True)
|
| 47 |
+
decoded = tokenizer.batch_decode(generated_ids)
|
| 48 |
+
print(decoded[0])
|
| 49 |
+
```
|
| 50 |
+
|
| 51 |
+
## Model Architecture
|
| 52 |
+
This instruction model is based on Mistral-7B-v0.1, a transformer model with the following architecture choices:
|
| 53 |
+
- Grouped-Query Attention
|
| 54 |
+
- Sliding-Window Attention
|
| 55 |
+
- Byte-fallback BPE tokenizer
|
checkpoint-100/README.md
ADDED
|
@@ -0,0 +1,204 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: /lustre07/scratch/gagan30/arocr/meta-llama/models/FusionNet_7Bx2_MoE_14B
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
|
| 201 |
+
|
| 202 |
+
### Framework versions
|
| 203 |
+
|
| 204 |
+
- PEFT 0.7.2.dev0
|
checkpoint-100/adapter_config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "/lustre07/scratch/gagan30/arocr/meta-llama/models/FusionNet_7Bx2_MoE_14B",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layers_pattern": null,
|
| 10 |
+
"layers_to_transform": null,
|
| 11 |
+
"loftq_config": {},
|
| 12 |
+
"lora_alpha": 16,
|
| 13 |
+
"lora_dropout": 0.05,
|
| 14 |
+
"megatron_config": null,
|
| 15 |
+
"megatron_core": "megatron.core",
|
| 16 |
+
"modules_to_save": null,
|
| 17 |
+
"peft_type": "LORA",
|
| 18 |
+
"r": 16,
|
| 19 |
+
"rank_pattern": {},
|
| 20 |
+
"revision": null,
|
| 21 |
+
"target_modules": [
|
| 22 |
+
"q_proj",
|
| 23 |
+
"gate",
|
| 24 |
+
"o_proj",
|
| 25 |
+
"w1",
|
| 26 |
+
"w3",
|
| 27 |
+
"k_proj",
|
| 28 |
+
"v_proj",
|
| 29 |
+
"w2"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_rslora": false
|
| 33 |
+
}
|
checkpoint-100/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:48f339ed60a8b39a9ef374fc7c2b8e37f1731105e5a1304db6312e245f5f6d84
|
| 3 |
+
size 289512208
|
checkpoint-100/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:49cad7333bdfa78ba76748e7de058321adc760bd3edd9e43c9151ab6c121a599
|
| 3 |
+
size 579245842
|
checkpoint-100/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:049c26b844b79121ddd8379f7f69194e63f6fbf6aa007eeac0c66f17eebb8893
|
| 3 |
+
size 888
|
checkpoint-100/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1c60c4043ea0c138840ee4d7fdcaad9c23c046dc40edae567efa02aaa11f0c98
|
| 3 |
+
size 14244
|
checkpoint-100/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8bd67f4fe4158f58507b660bd584f6f3aa80a8710f0d5f5d18e04784a18dc00d
|
| 3 |
+
size 1064
|
checkpoint-100/special_tokens_map.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<unk>",
|
| 4 |
+
"<s>",
|
| 5 |
+
"</s>"
|
| 6 |
+
],
|
| 7 |
+
"bos_token": {
|
| 8 |
+
"content": "<s>",
|
| 9 |
+
"lstrip": false,
|
| 10 |
+
"normalized": false,
|
| 11 |
+
"rstrip": false,
|
| 12 |
+
"single_word": false
|
| 13 |
+
},
|
| 14 |
+
"eos_token": {
|
| 15 |
+
"content": "</s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false
|
| 20 |
+
},
|
| 21 |
+
"pad_token": "</s>",
|
| 22 |
+
"unk_token": {
|
| 23 |
+
"content": "<unk>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false
|
| 28 |
+
}
|
| 29 |
+
}
|
checkpoint-100/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-100/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
| 3 |
+
size 493443
|
checkpoint-100/tokenizer_config.json
ADDED
|
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": true,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"0": {
|
| 6 |
+
"content": "<unk>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"1": {
|
| 14 |
+
"content": "<s>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"2": {
|
| 22 |
+
"content": "</s>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
}
|
| 29 |
+
},
|
| 30 |
+
"additional_special_tokens": [
|
| 31 |
+
"<unk>",
|
| 32 |
+
"<s>",
|
| 33 |
+
"</s>"
|
| 34 |
+
],
|
| 35 |
+
"bos_token": "<s>",
|
| 36 |
+
"clean_up_tokenization_spaces": false,
|
| 37 |
+
"eos_token": "</s>",
|
| 38 |
+
"legacy": true,
|
| 39 |
+
"max_length": null,
|
| 40 |
+
"model_max_length": 255,
|
| 41 |
+
"pad_to_multiple_of": null,
|
| 42 |
+
"pad_token": "</s>",
|
| 43 |
+
"pad_token_type_id": 0,
|
| 44 |
+
"padding_side": "right",
|
| 45 |
+
"sp_model_kwargs": {},
|
| 46 |
+
"spaces_between_special_tokens": false,
|
| 47 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 48 |
+
"unk_token": "<unk>",
|
| 49 |
+
"use_default_system_prompt": true
|
| 50 |
+
}
|
checkpoint-100/trainer_state.json
ADDED
|
@@ -0,0 +1,629 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.16181229773462782,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 100,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0,
|
| 13 |
+
"learning_rate": 5e-05,
|
| 14 |
+
"loss": 1.9981,
|
| 15 |
+
"step": 1
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.0,
|
| 19 |
+
"learning_rate": 4.9999675930251536e-05,
|
| 20 |
+
"loss": 2.0613,
|
| 21 |
+
"step": 2
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.0,
|
| 25 |
+
"learning_rate": 4.99987037294078e-05,
|
| 26 |
+
"loss": 1.8228,
|
| 27 |
+
"step": 3
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.01,
|
| 31 |
+
"learning_rate": 4.99970834226737e-05,
|
| 32 |
+
"loss": 1.707,
|
| 33 |
+
"step": 4
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.01,
|
| 37 |
+
"learning_rate": 4.999481505205661e-05,
|
| 38 |
+
"loss": 1.5271,
|
| 39 |
+
"step": 5
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.01,
|
| 43 |
+
"learning_rate": 4.999189867636535e-05,
|
| 44 |
+
"loss": 1.4562,
|
| 45 |
+
"step": 6
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.01,
|
| 49 |
+
"learning_rate": 4.998833437120866e-05,
|
| 50 |
+
"loss": 1.3805,
|
| 51 |
+
"step": 7
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.01,
|
| 55 |
+
"learning_rate": 4.998412222899321e-05,
|
| 56 |
+
"loss": 1.2998,
|
| 57 |
+
"step": 8
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.01,
|
| 61 |
+
"learning_rate": 4.997926235892124e-05,
|
| 62 |
+
"loss": 1.4383,
|
| 63 |
+
"step": 9
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.02,
|
| 67 |
+
"learning_rate": 4.997375488698769e-05,
|
| 68 |
+
"loss": 1.2441,
|
| 69 |
+
"step": 10
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.02,
|
| 73 |
+
"learning_rate": 4.996759995597697e-05,
|
| 74 |
+
"loss": 1.2275,
|
| 75 |
+
"step": 11
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.02,
|
| 79 |
+
"learning_rate": 4.996079772545923e-05,
|
| 80 |
+
"loss": 1.2233,
|
| 81 |
+
"step": 12
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.02,
|
| 85 |
+
"learning_rate": 4.995334837178625e-05,
|
| 86 |
+
"loss": 1.1886,
|
| 87 |
+
"step": 13
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.02,
|
| 91 |
+
"learning_rate": 4.9945252088086825e-05,
|
| 92 |
+
"loss": 1.1779,
|
| 93 |
+
"step": 14
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.02,
|
| 97 |
+
"learning_rate": 4.993650908426182e-05,
|
| 98 |
+
"loss": 1.1122,
|
| 99 |
+
"step": 15
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.03,
|
| 103 |
+
"learning_rate": 4.992711958697868e-05,
|
| 104 |
+
"loss": 1.0766,
|
| 105 |
+
"step": 16
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.03,
|
| 109 |
+
"learning_rate": 4.991708383966556e-05,
|
| 110 |
+
"loss": 1.0836,
|
| 111 |
+
"step": 17
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.03,
|
| 115 |
+
"learning_rate": 4.9906402102505026e-05,
|
| 116 |
+
"loss": 0.9728,
|
| 117 |
+
"step": 18
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.03,
|
| 121 |
+
"learning_rate": 4.989507465242732e-05,
|
| 122 |
+
"loss": 0.9883,
|
| 123 |
+
"step": 19
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.03,
|
| 127 |
+
"learning_rate": 4.988310178310315e-05,
|
| 128 |
+
"loss": 1.0307,
|
| 129 |
+
"step": 20
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.03,
|
| 133 |
+
"learning_rate": 4.9870483804936084e-05,
|
| 134 |
+
"loss": 0.9613,
|
| 135 |
+
"step": 21
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.04,
|
| 139 |
+
"learning_rate": 4.9857221045054535e-05,
|
| 140 |
+
"loss": 1.1038,
|
| 141 |
+
"step": 22
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.04,
|
| 145 |
+
"learning_rate": 4.9843313847303246e-05,
|
| 146 |
+
"loss": 0.9206,
|
| 147 |
+
"step": 23
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.04,
|
| 151 |
+
"learning_rate": 4.9828762572234374e-05,
|
| 152 |
+
"loss": 0.9893,
|
| 153 |
+
"step": 24
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.04,
|
| 157 |
+
"learning_rate": 4.9813567597098166e-05,
|
| 158 |
+
"loss": 0.8328,
|
| 159 |
+
"step": 25
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.04,
|
| 163 |
+
"learning_rate": 4.979772931583317e-05,
|
| 164 |
+
"loss": 0.8712,
|
| 165 |
+
"step": 26
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.04,
|
| 169 |
+
"learning_rate": 4.978124813905599e-05,
|
| 170 |
+
"loss": 0.8031,
|
| 171 |
+
"step": 27
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.05,
|
| 175 |
+
"learning_rate": 4.976412449405072e-05,
|
| 176 |
+
"loss": 0.7675,
|
| 177 |
+
"step": 28
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.05,
|
| 181 |
+
"learning_rate": 4.974635882475778e-05,
|
| 182 |
+
"loss": 0.7851,
|
| 183 |
+
"step": 29
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.05,
|
| 187 |
+
"learning_rate": 4.972795159176243e-05,
|
| 188 |
+
"loss": 0.7447,
|
| 189 |
+
"step": 30
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.05,
|
| 193 |
+
"learning_rate": 4.9708903272282884e-05,
|
| 194 |
+
"loss": 0.7719,
|
| 195 |
+
"step": 31
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.05,
|
| 199 |
+
"learning_rate": 4.9689214360157844e-05,
|
| 200 |
+
"loss": 0.7142,
|
| 201 |
+
"step": 32
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.05,
|
| 205 |
+
"learning_rate": 4.9668885365833795e-05,
|
| 206 |
+
"loss": 0.8649,
|
| 207 |
+
"step": 33
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.06,
|
| 211 |
+
"learning_rate": 4.96479168163517e-05,
|
| 212 |
+
"loss": 0.7574,
|
| 213 |
+
"step": 34
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.06,
|
| 217 |
+
"learning_rate": 4.9626309255333346e-05,
|
| 218 |
+
"loss": 0.9205,
|
| 219 |
+
"step": 35
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.06,
|
| 223 |
+
"learning_rate": 4.9604063242967315e-05,
|
| 224 |
+
"loss": 0.7987,
|
| 225 |
+
"step": 36
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.06,
|
| 229 |
+
"learning_rate": 4.958117935599434e-05,
|
| 230 |
+
"loss": 0.7626,
|
| 231 |
+
"step": 37
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.06,
|
| 235 |
+
"learning_rate": 4.955765818769249e-05,
|
| 236 |
+
"loss": 0.8332,
|
| 237 |
+
"step": 38
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.06,
|
| 241 |
+
"learning_rate": 4.9533500347861675e-05,
|
| 242 |
+
"loss": 0.9178,
|
| 243 |
+
"step": 39
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.06,
|
| 247 |
+
"learning_rate": 4.950870646280791e-05,
|
| 248 |
+
"loss": 0.9919,
|
| 249 |
+
"step": 40
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.07,
|
| 253 |
+
"learning_rate": 4.948327717532705e-05,
|
| 254 |
+
"loss": 0.7098,
|
| 255 |
+
"step": 41
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.07,
|
| 259 |
+
"learning_rate": 4.9457213144688095e-05,
|
| 260 |
+
"loss": 0.7552,
|
| 261 |
+
"step": 42
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.07,
|
| 265 |
+
"learning_rate": 4.9430515046616175e-05,
|
| 266 |
+
"loss": 0.7496,
|
| 267 |
+
"step": 43
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.07,
|
| 271 |
+
"learning_rate": 4.940318357327495e-05,
|
| 272 |
+
"loss": 0.7667,
|
| 273 |
+
"step": 44
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.07,
|
| 277 |
+
"learning_rate": 4.937521943324873e-05,
|
| 278 |
+
"loss": 0.8685,
|
| 279 |
+
"step": 45
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.07,
|
| 283 |
+
"learning_rate": 4.934662335152405e-05,
|
| 284 |
+
"loss": 0.6715,
|
| 285 |
+
"step": 46
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.08,
|
| 289 |
+
"learning_rate": 4.931739606947091e-05,
|
| 290 |
+
"loss": 0.8149,
|
| 291 |
+
"step": 47
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.08,
|
| 295 |
+
"learning_rate": 4.9287538344823544e-05,
|
| 296 |
+
"loss": 0.7346,
|
| 297 |
+
"step": 48
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.08,
|
| 301 |
+
"learning_rate": 4.925705095166079e-05,
|
| 302 |
+
"loss": 0.7803,
|
| 303 |
+
"step": 49
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.08,
|
| 307 |
+
"learning_rate": 4.922593468038599e-05,
|
| 308 |
+
"loss": 0.7451,
|
| 309 |
+
"step": 50
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.08,
|
| 313 |
+
"learning_rate": 4.919419033770652e-05,
|
| 314 |
+
"loss": 0.8402,
|
| 315 |
+
"step": 51
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 0.08,
|
| 319 |
+
"learning_rate": 4.916181874661286e-05,
|
| 320 |
+
"loss": 0.7988,
|
| 321 |
+
"step": 52
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.09,
|
| 325 |
+
"learning_rate": 4.91288207463573e-05,
|
| 326 |
+
"loss": 0.7444,
|
| 327 |
+
"step": 53
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.09,
|
| 331 |
+
"learning_rate": 4.9095197192432105e-05,
|
| 332 |
+
"loss": 0.8545,
|
| 333 |
+
"step": 54
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.09,
|
| 337 |
+
"learning_rate": 4.906094895654744e-05,
|
| 338 |
+
"loss": 0.761,
|
| 339 |
+
"step": 55
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.09,
|
| 343 |
+
"learning_rate": 4.902607692660865e-05,
|
| 344 |
+
"loss": 0.6741,
|
| 345 |
+
"step": 56
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.09,
|
| 349 |
+
"learning_rate": 4.8990582006693365e-05,
|
| 350 |
+
"loss": 0.8457,
|
| 351 |
+
"step": 57
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.09,
|
| 355 |
+
"learning_rate": 4.895446511702793e-05,
|
| 356 |
+
"loss": 0.8096,
|
| 357 |
+
"step": 58
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 0.1,
|
| 361 |
+
"learning_rate": 4.891772719396369e-05,
|
| 362 |
+
"loss": 0.7989,
|
| 363 |
+
"step": 59
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.1,
|
| 367 |
+
"learning_rate": 4.888036918995258e-05,
|
| 368 |
+
"loss": 0.7683,
|
| 369 |
+
"step": 60
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.1,
|
| 373 |
+
"learning_rate": 4.884239207352252e-05,
|
| 374 |
+
"loss": 0.7912,
|
| 375 |
+
"step": 61
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.1,
|
| 379 |
+
"learning_rate": 4.880379682925228e-05,
|
| 380 |
+
"loss": 0.7417,
|
| 381 |
+
"step": 62
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.1,
|
| 385 |
+
"learning_rate": 4.876458445774594e-05,
|
| 386 |
+
"loss": 0.7511,
|
| 387 |
+
"step": 63
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.1,
|
| 391 |
+
"learning_rate": 4.872475597560699e-05,
|
| 392 |
+
"loss": 0.8021,
|
| 393 |
+
"step": 64
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.11,
|
| 397 |
+
"learning_rate": 4.8684312415411897e-05,
|
| 398 |
+
"loss": 0.8154,
|
| 399 |
+
"step": 65
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.11,
|
| 403 |
+
"learning_rate": 4.864325482568344e-05,
|
| 404 |
+
"loss": 0.7109,
|
| 405 |
+
"step": 66
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 0.11,
|
| 409 |
+
"learning_rate": 4.860158427086341e-05,
|
| 410 |
+
"loss": 0.7915,
|
| 411 |
+
"step": 67
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.11,
|
| 415 |
+
"learning_rate": 4.855930183128513e-05,
|
| 416 |
+
"loss": 0.6363,
|
| 417 |
+
"step": 68
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.11,
|
| 421 |
+
"learning_rate": 4.851640860314536e-05,
|
| 422 |
+
"loss": 0.6987,
|
| 423 |
+
"step": 69
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.11,
|
| 427 |
+
"learning_rate": 4.8472905698475906e-05,
|
| 428 |
+
"loss": 0.6498,
|
| 429 |
+
"step": 70
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.11,
|
| 433 |
+
"learning_rate": 4.84287942451148e-05,
|
| 434 |
+
"loss": 0.7768,
|
| 435 |
+
"step": 71
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.12,
|
| 439 |
+
"learning_rate": 4.8384075386677054e-05,
|
| 440 |
+
"loss": 0.7979,
|
| 441 |
+
"step": 72
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.12,
|
| 445 |
+
"learning_rate": 4.833875028252499e-05,
|
| 446 |
+
"loss": 0.7611,
|
| 447 |
+
"step": 73
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 0.12,
|
| 451 |
+
"learning_rate": 4.8292820107738235e-05,
|
| 452 |
+
"loss": 0.7889,
|
| 453 |
+
"step": 74
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.12,
|
| 457 |
+
"learning_rate": 4.824628605308319e-05,
|
| 458 |
+
"loss": 0.6706,
|
| 459 |
+
"step": 75
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.12,
|
| 463 |
+
"learning_rate": 4.819914932498222e-05,
|
| 464 |
+
"loss": 0.7762,
|
| 465 |
+
"step": 76
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.12,
|
| 469 |
+
"learning_rate": 4.815141114548232e-05,
|
| 470 |
+
"loss": 0.7517,
|
| 471 |
+
"step": 77
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.13,
|
| 475 |
+
"learning_rate": 4.8103072752223486e-05,
|
| 476 |
+
"loss": 0.7793,
|
| 477 |
+
"step": 78
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.13,
|
| 481 |
+
"learning_rate": 4.805413539840659e-05,
|
| 482 |
+
"loss": 0.7306,
|
| 483 |
+
"step": 79
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 0.13,
|
| 487 |
+
"learning_rate": 4.80046003527609e-05,
|
| 488 |
+
"loss": 0.834,
|
| 489 |
+
"step": 80
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.13,
|
| 493 |
+
"learning_rate": 4.7954468899511215e-05,
|
| 494 |
+
"loss": 0.8076,
|
| 495 |
+
"step": 81
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.13,
|
| 499 |
+
"learning_rate": 4.790374233834452e-05,
|
| 500 |
+
"loss": 0.8375,
|
| 501 |
+
"step": 82
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.13,
|
| 505 |
+
"learning_rate": 4.7852421984376324e-05,
|
| 506 |
+
"loss": 0.7839,
|
| 507 |
+
"step": 83
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.14,
|
| 511 |
+
"learning_rate": 4.780050916811658e-05,
|
| 512 |
+
"loss": 0.6221,
|
| 513 |
+
"step": 84
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.14,
|
| 517 |
+
"learning_rate": 4.7748005235435137e-05,
|
| 518 |
+
"loss": 0.7212,
|
| 519 |
+
"step": 85
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.14,
|
| 523 |
+
"learning_rate": 4.76949115475269e-05,
|
| 524 |
+
"loss": 0.6369,
|
| 525 |
+
"step": 86
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.14,
|
| 529 |
+
"learning_rate": 4.7641229480876515e-05,
|
| 530 |
+
"loss": 0.7167,
|
| 531 |
+
"step": 87
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 0.14,
|
| 535 |
+
"learning_rate": 4.758696042722269e-05,
|
| 536 |
+
"loss": 0.6908,
|
| 537 |
+
"step": 88
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.14,
|
| 541 |
+
"learning_rate": 4.753210579352211e-05,
|
| 542 |
+
"loss": 0.6681,
|
| 543 |
+
"step": 89
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.15,
|
| 547 |
+
"learning_rate": 4.747666700191297e-05,
|
| 548 |
+
"loss": 0.6566,
|
| 549 |
+
"step": 90
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.15,
|
| 553 |
+
"learning_rate": 4.7420645489678076e-05,
|
| 554 |
+
"loss": 0.6869,
|
| 555 |
+
"step": 91
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.15,
|
| 559 |
+
"learning_rate": 4.7364042709207626e-05,
|
| 560 |
+
"loss": 0.7106,
|
| 561 |
+
"step": 92
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 0.15,
|
| 565 |
+
"learning_rate": 4.730686012796153e-05,
|
| 566 |
+
"loss": 0.6782,
|
| 567 |
+
"step": 93
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 0.15,
|
| 571 |
+
"learning_rate": 4.724909922843136e-05,
|
| 572 |
+
"loss": 0.7148,
|
| 573 |
+
"step": 94
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 0.15,
|
| 577 |
+
"learning_rate": 4.719076150810193e-05,
|
| 578 |
+
"loss": 0.8887,
|
| 579 |
+
"step": 95
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 0.16,
|
| 583 |
+
"learning_rate": 4.7131848479412476e-05,
|
| 584 |
+
"loss": 0.7408,
|
| 585 |
+
"step": 96
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.16,
|
| 589 |
+
"learning_rate": 4.707236166971742e-05,
|
| 590 |
+
"loss": 0.7046,
|
| 591 |
+
"step": 97
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.16,
|
| 595 |
+
"learning_rate": 4.7012302621246804e-05,
|
| 596 |
+
"loss": 0.7657,
|
| 597 |
+
"step": 98
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.16,
|
| 601 |
+
"learning_rate": 4.695167289106629e-05,
|
| 602 |
+
"loss": 0.8138,
|
| 603 |
+
"step": 99
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 0.16,
|
| 607 |
+
"learning_rate": 4.689047405103678e-05,
|
| 608 |
+
"loss": 0.6964,
|
| 609 |
+
"step": 100
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 0.16,
|
| 613 |
+
"eval_loss": 0.796372652053833,
|
| 614 |
+
"eval_runtime": 5.3558,
|
| 615 |
+
"eval_samples_per_second": 1.867,
|
| 616 |
+
"eval_steps_per_second": 0.373,
|
| 617 |
+
"step": 100
|
| 618 |
+
}
|
| 619 |
+
],
|
| 620 |
+
"logging_steps": 1,
|
| 621 |
+
"max_steps": 618,
|
| 622 |
+
"num_input_tokens_seen": 0,
|
| 623 |
+
"num_train_epochs": 1,
|
| 624 |
+
"save_steps": 100,
|
| 625 |
+
"total_flos": 2.520597053571072e+17,
|
| 626 |
+
"train_batch_size": 4,
|
| 627 |
+
"trial_name": null,
|
| 628 |
+
"trial_params": null
|
| 629 |
+
}
|
checkpoint-100/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1669fbc766ffe69b2e1c5c6cf99065bb5af64e12a25e45ff208dd48072c391fc
|
| 3 |
+
size 4792
|
checkpoint-200/README.md
ADDED
|
@@ -0,0 +1,204 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: /lustre07/scratch/gagan30/arocr/meta-llama/models/FusionNet_7Bx2_MoE_14B
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
|
| 201 |
+
|
| 202 |
+
### Framework versions
|
| 203 |
+
|
| 204 |
+
- PEFT 0.7.2.dev0
|
checkpoint-200/adapter_config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "/lustre07/scratch/gagan30/arocr/meta-llama/models/FusionNet_7Bx2_MoE_14B",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layers_pattern": null,
|
| 10 |
+
"layers_to_transform": null,
|
| 11 |
+
"loftq_config": {},
|
| 12 |
+
"lora_alpha": 16,
|
| 13 |
+
"lora_dropout": 0.05,
|
| 14 |
+
"megatron_config": null,
|
| 15 |
+
"megatron_core": "megatron.core",
|
| 16 |
+
"modules_to_save": null,
|
| 17 |
+
"peft_type": "LORA",
|
| 18 |
+
"r": 16,
|
| 19 |
+
"rank_pattern": {},
|
| 20 |
+
"revision": null,
|
| 21 |
+
"target_modules": [
|
| 22 |
+
"q_proj",
|
| 23 |
+
"gate",
|
| 24 |
+
"o_proj",
|
| 25 |
+
"w1",
|
| 26 |
+
"w3",
|
| 27 |
+
"k_proj",
|
| 28 |
+
"v_proj",
|
| 29 |
+
"w2"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_rslora": false
|
| 33 |
+
}
|
checkpoint-200/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a8518cf3718b948b405c47e5c1fadee69f0503434377726a108a4c01c2a2a72c
|
| 3 |
+
size 289512208
|
checkpoint-200/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aac519c587e6d177d1f4119ef597d8ee84c925cf0f7f4eb5e873eeee41aaa88c
|
| 3 |
+
size 579245842
|
checkpoint-200/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:049c26b844b79121ddd8379f7f69194e63f6fbf6aa007eeac0c66f17eebb8893
|
| 3 |
+
size 888
|
checkpoint-200/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f1fec887c0727be4f93e419a47cc1fd96a7641b7e73a20d90a7012bb8ac44b1c
|
| 3 |
+
size 14244
|
checkpoint-200/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9512c47c6a35214e939ff6559c9df20c2dc67173a449007689dd9fef0c476eda
|
| 3 |
+
size 1064
|
checkpoint-200/special_tokens_map.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<unk>",
|
| 4 |
+
"<s>",
|
| 5 |
+
"</s>"
|
| 6 |
+
],
|
| 7 |
+
"bos_token": {
|
| 8 |
+
"content": "<s>",
|
| 9 |
+
"lstrip": false,
|
| 10 |
+
"normalized": false,
|
| 11 |
+
"rstrip": false,
|
| 12 |
+
"single_word": false
|
| 13 |
+
},
|
| 14 |
+
"eos_token": {
|
| 15 |
+
"content": "</s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false
|
| 20 |
+
},
|
| 21 |
+
"pad_token": "</s>",
|
| 22 |
+
"unk_token": {
|
| 23 |
+
"content": "<unk>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false
|
| 28 |
+
}
|
| 29 |
+
}
|
checkpoint-200/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-200/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
| 3 |
+
size 493443
|
checkpoint-200/tokenizer_config.json
ADDED
|
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": true,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"0": {
|
| 6 |
+
"content": "<unk>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"1": {
|
| 14 |
+
"content": "<s>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"2": {
|
| 22 |
+
"content": "</s>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
}
|
| 29 |
+
},
|
| 30 |
+
"additional_special_tokens": [
|
| 31 |
+
"<unk>",
|
| 32 |
+
"<s>",
|
| 33 |
+
"</s>"
|
| 34 |
+
],
|
| 35 |
+
"bos_token": "<s>",
|
| 36 |
+
"clean_up_tokenization_spaces": false,
|
| 37 |
+
"eos_token": "</s>",
|
| 38 |
+
"legacy": true,
|
| 39 |
+
"max_length": null,
|
| 40 |
+
"model_max_length": 255,
|
| 41 |
+
"pad_to_multiple_of": null,
|
| 42 |
+
"pad_token": "</s>",
|
| 43 |
+
"pad_token_type_id": 0,
|
| 44 |
+
"padding_side": "right",
|
| 45 |
+
"sp_model_kwargs": {},
|
| 46 |
+
"spaces_between_special_tokens": false,
|
| 47 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 48 |
+
"unk_token": "<unk>",
|
| 49 |
+
"use_default_system_prompt": true
|
| 50 |
+
}
|
checkpoint-200/trainer_state.json
ADDED
|
@@ -0,0 +1,1237 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.32362459546925565,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 200,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0,
|
| 13 |
+
"learning_rate": 5e-05,
|
| 14 |
+
"loss": 1.9981,
|
| 15 |
+
"step": 1
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.0,
|
| 19 |
+
"learning_rate": 4.9999675930251536e-05,
|
| 20 |
+
"loss": 2.0613,
|
| 21 |
+
"step": 2
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.0,
|
| 25 |
+
"learning_rate": 4.99987037294078e-05,
|
| 26 |
+
"loss": 1.8228,
|
| 27 |
+
"step": 3
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.01,
|
| 31 |
+
"learning_rate": 4.99970834226737e-05,
|
| 32 |
+
"loss": 1.707,
|
| 33 |
+
"step": 4
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.01,
|
| 37 |
+
"learning_rate": 4.999481505205661e-05,
|
| 38 |
+
"loss": 1.5271,
|
| 39 |
+
"step": 5
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.01,
|
| 43 |
+
"learning_rate": 4.999189867636535e-05,
|
| 44 |
+
"loss": 1.4562,
|
| 45 |
+
"step": 6
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.01,
|
| 49 |
+
"learning_rate": 4.998833437120866e-05,
|
| 50 |
+
"loss": 1.3805,
|
| 51 |
+
"step": 7
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.01,
|
| 55 |
+
"learning_rate": 4.998412222899321e-05,
|
| 56 |
+
"loss": 1.2998,
|
| 57 |
+
"step": 8
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.01,
|
| 61 |
+
"learning_rate": 4.997926235892124e-05,
|
| 62 |
+
"loss": 1.4383,
|
| 63 |
+
"step": 9
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.02,
|
| 67 |
+
"learning_rate": 4.997375488698769e-05,
|
| 68 |
+
"loss": 1.2441,
|
| 69 |
+
"step": 10
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.02,
|
| 73 |
+
"learning_rate": 4.996759995597697e-05,
|
| 74 |
+
"loss": 1.2275,
|
| 75 |
+
"step": 11
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.02,
|
| 79 |
+
"learning_rate": 4.996079772545923e-05,
|
| 80 |
+
"loss": 1.2233,
|
| 81 |
+
"step": 12
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.02,
|
| 85 |
+
"learning_rate": 4.995334837178625e-05,
|
| 86 |
+
"loss": 1.1886,
|
| 87 |
+
"step": 13
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.02,
|
| 91 |
+
"learning_rate": 4.9945252088086825e-05,
|
| 92 |
+
"loss": 1.1779,
|
| 93 |
+
"step": 14
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.02,
|
| 97 |
+
"learning_rate": 4.993650908426182e-05,
|
| 98 |
+
"loss": 1.1122,
|
| 99 |
+
"step": 15
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.03,
|
| 103 |
+
"learning_rate": 4.992711958697868e-05,
|
| 104 |
+
"loss": 1.0766,
|
| 105 |
+
"step": 16
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.03,
|
| 109 |
+
"learning_rate": 4.991708383966556e-05,
|
| 110 |
+
"loss": 1.0836,
|
| 111 |
+
"step": 17
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.03,
|
| 115 |
+
"learning_rate": 4.9906402102505026e-05,
|
| 116 |
+
"loss": 0.9728,
|
| 117 |
+
"step": 18
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.03,
|
| 121 |
+
"learning_rate": 4.989507465242732e-05,
|
| 122 |
+
"loss": 0.9883,
|
| 123 |
+
"step": 19
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.03,
|
| 127 |
+
"learning_rate": 4.988310178310315e-05,
|
| 128 |
+
"loss": 1.0307,
|
| 129 |
+
"step": 20
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.03,
|
| 133 |
+
"learning_rate": 4.9870483804936084e-05,
|
| 134 |
+
"loss": 0.9613,
|
| 135 |
+
"step": 21
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.04,
|
| 139 |
+
"learning_rate": 4.9857221045054535e-05,
|
| 140 |
+
"loss": 1.1038,
|
| 141 |
+
"step": 22
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.04,
|
| 145 |
+
"learning_rate": 4.9843313847303246e-05,
|
| 146 |
+
"loss": 0.9206,
|
| 147 |
+
"step": 23
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.04,
|
| 151 |
+
"learning_rate": 4.9828762572234374e-05,
|
| 152 |
+
"loss": 0.9893,
|
| 153 |
+
"step": 24
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.04,
|
| 157 |
+
"learning_rate": 4.9813567597098166e-05,
|
| 158 |
+
"loss": 0.8328,
|
| 159 |
+
"step": 25
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.04,
|
| 163 |
+
"learning_rate": 4.979772931583317e-05,
|
| 164 |
+
"loss": 0.8712,
|
| 165 |
+
"step": 26
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.04,
|
| 169 |
+
"learning_rate": 4.978124813905599e-05,
|
| 170 |
+
"loss": 0.8031,
|
| 171 |
+
"step": 27
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.05,
|
| 175 |
+
"learning_rate": 4.976412449405072e-05,
|
| 176 |
+
"loss": 0.7675,
|
| 177 |
+
"step": 28
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.05,
|
| 181 |
+
"learning_rate": 4.974635882475778e-05,
|
| 182 |
+
"loss": 0.7851,
|
| 183 |
+
"step": 29
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.05,
|
| 187 |
+
"learning_rate": 4.972795159176243e-05,
|
| 188 |
+
"loss": 0.7447,
|
| 189 |
+
"step": 30
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.05,
|
| 193 |
+
"learning_rate": 4.9708903272282884e-05,
|
| 194 |
+
"loss": 0.7719,
|
| 195 |
+
"step": 31
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.05,
|
| 199 |
+
"learning_rate": 4.9689214360157844e-05,
|
| 200 |
+
"loss": 0.7142,
|
| 201 |
+
"step": 32
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.05,
|
| 205 |
+
"learning_rate": 4.9668885365833795e-05,
|
| 206 |
+
"loss": 0.8649,
|
| 207 |
+
"step": 33
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.06,
|
| 211 |
+
"learning_rate": 4.96479168163517e-05,
|
| 212 |
+
"loss": 0.7574,
|
| 213 |
+
"step": 34
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.06,
|
| 217 |
+
"learning_rate": 4.9626309255333346e-05,
|
| 218 |
+
"loss": 0.9205,
|
| 219 |
+
"step": 35
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.06,
|
| 223 |
+
"learning_rate": 4.9604063242967315e-05,
|
| 224 |
+
"loss": 0.7987,
|
| 225 |
+
"step": 36
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.06,
|
| 229 |
+
"learning_rate": 4.958117935599434e-05,
|
| 230 |
+
"loss": 0.7626,
|
| 231 |
+
"step": 37
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.06,
|
| 235 |
+
"learning_rate": 4.955765818769249e-05,
|
| 236 |
+
"loss": 0.8332,
|
| 237 |
+
"step": 38
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.06,
|
| 241 |
+
"learning_rate": 4.9533500347861675e-05,
|
| 242 |
+
"loss": 0.9178,
|
| 243 |
+
"step": 39
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.06,
|
| 247 |
+
"learning_rate": 4.950870646280791e-05,
|
| 248 |
+
"loss": 0.9919,
|
| 249 |
+
"step": 40
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.07,
|
| 253 |
+
"learning_rate": 4.948327717532705e-05,
|
| 254 |
+
"loss": 0.7098,
|
| 255 |
+
"step": 41
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.07,
|
| 259 |
+
"learning_rate": 4.9457213144688095e-05,
|
| 260 |
+
"loss": 0.7552,
|
| 261 |
+
"step": 42
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.07,
|
| 265 |
+
"learning_rate": 4.9430515046616175e-05,
|
| 266 |
+
"loss": 0.7496,
|
| 267 |
+
"step": 43
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.07,
|
| 271 |
+
"learning_rate": 4.940318357327495e-05,
|
| 272 |
+
"loss": 0.7667,
|
| 273 |
+
"step": 44
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.07,
|
| 277 |
+
"learning_rate": 4.937521943324873e-05,
|
| 278 |
+
"loss": 0.8685,
|
| 279 |
+
"step": 45
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.07,
|
| 283 |
+
"learning_rate": 4.934662335152405e-05,
|
| 284 |
+
"loss": 0.6715,
|
| 285 |
+
"step": 46
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.08,
|
| 289 |
+
"learning_rate": 4.931739606947091e-05,
|
| 290 |
+
"loss": 0.8149,
|
| 291 |
+
"step": 47
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.08,
|
| 295 |
+
"learning_rate": 4.9287538344823544e-05,
|
| 296 |
+
"loss": 0.7346,
|
| 297 |
+
"step": 48
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.08,
|
| 301 |
+
"learning_rate": 4.925705095166079e-05,
|
| 302 |
+
"loss": 0.7803,
|
| 303 |
+
"step": 49
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.08,
|
| 307 |
+
"learning_rate": 4.922593468038599e-05,
|
| 308 |
+
"loss": 0.7451,
|
| 309 |
+
"step": 50
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.08,
|
| 313 |
+
"learning_rate": 4.919419033770652e-05,
|
| 314 |
+
"loss": 0.8402,
|
| 315 |
+
"step": 51
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 0.08,
|
| 319 |
+
"learning_rate": 4.916181874661286e-05,
|
| 320 |
+
"loss": 0.7988,
|
| 321 |
+
"step": 52
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.09,
|
| 325 |
+
"learning_rate": 4.91288207463573e-05,
|
| 326 |
+
"loss": 0.7444,
|
| 327 |
+
"step": 53
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.09,
|
| 331 |
+
"learning_rate": 4.9095197192432105e-05,
|
| 332 |
+
"loss": 0.8545,
|
| 333 |
+
"step": 54
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.09,
|
| 337 |
+
"learning_rate": 4.906094895654744e-05,
|
| 338 |
+
"loss": 0.761,
|
| 339 |
+
"step": 55
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.09,
|
| 343 |
+
"learning_rate": 4.902607692660865e-05,
|
| 344 |
+
"loss": 0.6741,
|
| 345 |
+
"step": 56
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.09,
|
| 349 |
+
"learning_rate": 4.8990582006693365e-05,
|
| 350 |
+
"loss": 0.8457,
|
| 351 |
+
"step": 57
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.09,
|
| 355 |
+
"learning_rate": 4.895446511702793e-05,
|
| 356 |
+
"loss": 0.8096,
|
| 357 |
+
"step": 58
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 0.1,
|
| 361 |
+
"learning_rate": 4.891772719396369e-05,
|
| 362 |
+
"loss": 0.7989,
|
| 363 |
+
"step": 59
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.1,
|
| 367 |
+
"learning_rate": 4.888036918995258e-05,
|
| 368 |
+
"loss": 0.7683,
|
| 369 |
+
"step": 60
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.1,
|
| 373 |
+
"learning_rate": 4.884239207352252e-05,
|
| 374 |
+
"loss": 0.7912,
|
| 375 |
+
"step": 61
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.1,
|
| 379 |
+
"learning_rate": 4.880379682925228e-05,
|
| 380 |
+
"loss": 0.7417,
|
| 381 |
+
"step": 62
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.1,
|
| 385 |
+
"learning_rate": 4.876458445774594e-05,
|
| 386 |
+
"loss": 0.7511,
|
| 387 |
+
"step": 63
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.1,
|
| 391 |
+
"learning_rate": 4.872475597560699e-05,
|
| 392 |
+
"loss": 0.8021,
|
| 393 |
+
"step": 64
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.11,
|
| 397 |
+
"learning_rate": 4.8684312415411897e-05,
|
| 398 |
+
"loss": 0.8154,
|
| 399 |
+
"step": 65
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.11,
|
| 403 |
+
"learning_rate": 4.864325482568344e-05,
|
| 404 |
+
"loss": 0.7109,
|
| 405 |
+
"step": 66
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 0.11,
|
| 409 |
+
"learning_rate": 4.860158427086341e-05,
|
| 410 |
+
"loss": 0.7915,
|
| 411 |
+
"step": 67
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.11,
|
| 415 |
+
"learning_rate": 4.855930183128513e-05,
|
| 416 |
+
"loss": 0.6363,
|
| 417 |
+
"step": 68
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.11,
|
| 421 |
+
"learning_rate": 4.851640860314536e-05,
|
| 422 |
+
"loss": 0.6987,
|
| 423 |
+
"step": 69
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.11,
|
| 427 |
+
"learning_rate": 4.8472905698475906e-05,
|
| 428 |
+
"loss": 0.6498,
|
| 429 |
+
"step": 70
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.11,
|
| 433 |
+
"learning_rate": 4.84287942451148e-05,
|
| 434 |
+
"loss": 0.7768,
|
| 435 |
+
"step": 71
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.12,
|
| 439 |
+
"learning_rate": 4.8384075386677054e-05,
|
| 440 |
+
"loss": 0.7979,
|
| 441 |
+
"step": 72
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.12,
|
| 445 |
+
"learning_rate": 4.833875028252499e-05,
|
| 446 |
+
"loss": 0.7611,
|
| 447 |
+
"step": 73
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 0.12,
|
| 451 |
+
"learning_rate": 4.8292820107738235e-05,
|
| 452 |
+
"loss": 0.7889,
|
| 453 |
+
"step": 74
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.12,
|
| 457 |
+
"learning_rate": 4.824628605308319e-05,
|
| 458 |
+
"loss": 0.6706,
|
| 459 |
+
"step": 75
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.12,
|
| 463 |
+
"learning_rate": 4.819914932498222e-05,
|
| 464 |
+
"loss": 0.7762,
|
| 465 |
+
"step": 76
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.12,
|
| 469 |
+
"learning_rate": 4.815141114548232e-05,
|
| 470 |
+
"loss": 0.7517,
|
| 471 |
+
"step": 77
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.13,
|
| 475 |
+
"learning_rate": 4.8103072752223486e-05,
|
| 476 |
+
"loss": 0.7793,
|
| 477 |
+
"step": 78
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.13,
|
| 481 |
+
"learning_rate": 4.805413539840659e-05,
|
| 482 |
+
"loss": 0.7306,
|
| 483 |
+
"step": 79
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 0.13,
|
| 487 |
+
"learning_rate": 4.80046003527609e-05,
|
| 488 |
+
"loss": 0.834,
|
| 489 |
+
"step": 80
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.13,
|
| 493 |
+
"learning_rate": 4.7954468899511215e-05,
|
| 494 |
+
"loss": 0.8076,
|
| 495 |
+
"step": 81
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.13,
|
| 499 |
+
"learning_rate": 4.790374233834452e-05,
|
| 500 |
+
"loss": 0.8375,
|
| 501 |
+
"step": 82
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.13,
|
| 505 |
+
"learning_rate": 4.7852421984376324e-05,
|
| 506 |
+
"loss": 0.7839,
|
| 507 |
+
"step": 83
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.14,
|
| 511 |
+
"learning_rate": 4.780050916811658e-05,
|
| 512 |
+
"loss": 0.6221,
|
| 513 |
+
"step": 84
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.14,
|
| 517 |
+
"learning_rate": 4.7748005235435137e-05,
|
| 518 |
+
"loss": 0.7212,
|
| 519 |
+
"step": 85
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.14,
|
| 523 |
+
"learning_rate": 4.76949115475269e-05,
|
| 524 |
+
"loss": 0.6369,
|
| 525 |
+
"step": 86
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.14,
|
| 529 |
+
"learning_rate": 4.7641229480876515e-05,
|
| 530 |
+
"loss": 0.7167,
|
| 531 |
+
"step": 87
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 0.14,
|
| 535 |
+
"learning_rate": 4.758696042722269e-05,
|
| 536 |
+
"loss": 0.6908,
|
| 537 |
+
"step": 88
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.14,
|
| 541 |
+
"learning_rate": 4.753210579352211e-05,
|
| 542 |
+
"loss": 0.6681,
|
| 543 |
+
"step": 89
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.15,
|
| 547 |
+
"learning_rate": 4.747666700191297e-05,
|
| 548 |
+
"loss": 0.6566,
|
| 549 |
+
"step": 90
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.15,
|
| 553 |
+
"learning_rate": 4.7420645489678076e-05,
|
| 554 |
+
"loss": 0.6869,
|
| 555 |
+
"step": 91
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.15,
|
| 559 |
+
"learning_rate": 4.7364042709207626e-05,
|
| 560 |
+
"loss": 0.7106,
|
| 561 |
+
"step": 92
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 0.15,
|
| 565 |
+
"learning_rate": 4.730686012796153e-05,
|
| 566 |
+
"loss": 0.6782,
|
| 567 |
+
"step": 93
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 0.15,
|
| 571 |
+
"learning_rate": 4.724909922843136e-05,
|
| 572 |
+
"loss": 0.7148,
|
| 573 |
+
"step": 94
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 0.15,
|
| 577 |
+
"learning_rate": 4.719076150810193e-05,
|
| 578 |
+
"loss": 0.8887,
|
| 579 |
+
"step": 95
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 0.16,
|
| 583 |
+
"learning_rate": 4.7131848479412476e-05,
|
| 584 |
+
"loss": 0.7408,
|
| 585 |
+
"step": 96
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.16,
|
| 589 |
+
"learning_rate": 4.707236166971742e-05,
|
| 590 |
+
"loss": 0.7046,
|
| 591 |
+
"step": 97
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.16,
|
| 595 |
+
"learning_rate": 4.7012302621246804e-05,
|
| 596 |
+
"loss": 0.7657,
|
| 597 |
+
"step": 98
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.16,
|
| 601 |
+
"learning_rate": 4.695167289106629e-05,
|
| 602 |
+
"loss": 0.8138,
|
| 603 |
+
"step": 99
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 0.16,
|
| 607 |
+
"learning_rate": 4.689047405103678e-05,
|
| 608 |
+
"loss": 0.6964,
|
| 609 |
+
"step": 100
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 0.16,
|
| 613 |
+
"eval_loss": 0.796372652053833,
|
| 614 |
+
"eval_runtime": 5.3558,
|
| 615 |
+
"eval_samples_per_second": 1.867,
|
| 616 |
+
"eval_steps_per_second": 0.373,
|
| 617 |
+
"step": 100
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 0.16,
|
| 621 |
+
"learning_rate": 4.68287076877737e-05,
|
| 622 |
+
"loss": 0.6541,
|
| 623 |
+
"step": 101
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 0.17,
|
| 627 |
+
"learning_rate": 4.6766375402605824e-05,
|
| 628 |
+
"loss": 0.714,
|
| 629 |
+
"step": 102
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 0.17,
|
| 633 |
+
"learning_rate": 4.6703478811533794e-05,
|
| 634 |
+
"loss": 0.6823,
|
| 635 |
+
"step": 103
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 0.17,
|
| 639 |
+
"learning_rate": 4.6640019545188216e-05,
|
| 640 |
+
"loss": 0.8283,
|
| 641 |
+
"step": 104
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.17,
|
| 645 |
+
"learning_rate": 4.657599924878736e-05,
|
| 646 |
+
"loss": 0.7126,
|
| 647 |
+
"step": 105
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.17,
|
| 651 |
+
"learning_rate": 4.651141958209453e-05,
|
| 652 |
+
"loss": 0.6612,
|
| 653 |
+
"step": 106
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.17,
|
| 657 |
+
"learning_rate": 4.644628221937504e-05,
|
| 658 |
+
"loss": 0.7339,
|
| 659 |
+
"step": 107
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 0.17,
|
| 663 |
+
"learning_rate": 4.638058884935279e-05,
|
| 664 |
+
"loss": 0.6852,
|
| 665 |
+
"step": 108
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 0.18,
|
| 669 |
+
"learning_rate": 4.6314341175166485e-05,
|
| 670 |
+
"loss": 0.6804,
|
| 671 |
+
"step": 109
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 0.18,
|
| 675 |
+
"learning_rate": 4.6247540914325504e-05,
|
| 676 |
+
"loss": 0.7904,
|
| 677 |
+
"step": 110
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 0.18,
|
| 681 |
+
"learning_rate": 4.618018979866534e-05,
|
| 682 |
+
"loss": 0.6545,
|
| 683 |
+
"step": 111
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.18,
|
| 687 |
+
"learning_rate": 4.611228957430272e-05,
|
| 688 |
+
"loss": 0.7545,
|
| 689 |
+
"step": 112
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.18,
|
| 693 |
+
"learning_rate": 4.6043842001590344e-05,
|
| 694 |
+
"loss": 0.7478,
|
| 695 |
+
"step": 113
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.18,
|
| 699 |
+
"learning_rate": 4.5974848855071206e-05,
|
| 700 |
+
"loss": 0.8083,
|
| 701 |
+
"step": 114
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"epoch": 0.19,
|
| 705 |
+
"learning_rate": 4.590531192343266e-05,
|
| 706 |
+
"loss": 0.7435,
|
| 707 |
+
"step": 115
|
| 708 |
+
},
|
| 709 |
+
{
|
| 710 |
+
"epoch": 0.19,
|
| 711 |
+
"learning_rate": 4.5835233009459964e-05,
|
| 712 |
+
"loss": 0.7647,
|
| 713 |
+
"step": 116
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 0.19,
|
| 717 |
+
"learning_rate": 4.576461392998961e-05,
|
| 718 |
+
"loss": 0.7631,
|
| 719 |
+
"step": 117
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 0.19,
|
| 723 |
+
"learning_rate": 4.569345651586218e-05,
|
| 724 |
+
"loss": 0.7674,
|
| 725 |
+
"step": 118
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 0.19,
|
| 729 |
+
"learning_rate": 4.5621762611874904e-05,
|
| 730 |
+
"loss": 0.6737,
|
| 731 |
+
"step": 119
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 0.19,
|
| 735 |
+
"learning_rate": 4.55495340767338e-05,
|
| 736 |
+
"loss": 0.6901,
|
| 737 |
+
"step": 120
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.2,
|
| 741 |
+
"learning_rate": 4.547677278300555e-05,
|
| 742 |
+
"loss": 0.709,
|
| 743 |
+
"step": 121
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 0.2,
|
| 747 |
+
"learning_rate": 4.540348061706886e-05,
|
| 748 |
+
"loss": 0.5995,
|
| 749 |
+
"step": 122
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 0.2,
|
| 753 |
+
"learning_rate": 4.5329659479065655e-05,
|
| 754 |
+
"loss": 0.6832,
|
| 755 |
+
"step": 123
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 0.2,
|
| 759 |
+
"learning_rate": 4.525531128285173e-05,
|
| 760 |
+
"loss": 0.7584,
|
| 761 |
+
"step": 124
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 0.2,
|
| 765 |
+
"learning_rate": 4.5180437955947195e-05,
|
| 766 |
+
"loss": 0.6998,
|
| 767 |
+
"step": 125
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 0.2,
|
| 771 |
+
"learning_rate": 4.510504143948646e-05,
|
| 772 |
+
"loss": 0.6477,
|
| 773 |
+
"step": 126
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.21,
|
| 777 |
+
"learning_rate": 4.502912368816794e-05,
|
| 778 |
+
"loss": 0.681,
|
| 779 |
+
"step": 127
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.21,
|
| 783 |
+
"learning_rate": 4.4952686670203357e-05,
|
| 784 |
+
"loss": 0.7638,
|
| 785 |
+
"step": 128
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 0.21,
|
| 789 |
+
"learning_rate": 4.487573236726673e-05,
|
| 790 |
+
"loss": 0.7086,
|
| 791 |
+
"step": 129
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 0.21,
|
| 795 |
+
"learning_rate": 4.4798262774442986e-05,
|
| 796 |
+
"loss": 0.6166,
|
| 797 |
+
"step": 130
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 0.21,
|
| 801 |
+
"learning_rate": 4.472027990017623e-05,
|
| 802 |
+
"loss": 0.5901,
|
| 803 |
+
"step": 131
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 0.21,
|
| 807 |
+
"learning_rate": 4.464178576621771e-05,
|
| 808 |
+
"loss": 0.8138,
|
| 809 |
+
"step": 132
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 0.22,
|
| 813 |
+
"learning_rate": 4.456278240757338e-05,
|
| 814 |
+
"loss": 0.6773,
|
| 815 |
+
"step": 133
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 0.22,
|
| 819 |
+
"learning_rate": 4.4483271872451094e-05,
|
| 820 |
+
"loss": 0.6576,
|
| 821 |
+
"step": 134
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.22,
|
| 825 |
+
"learning_rate": 4.44032562222076e-05,
|
| 826 |
+
"loss": 0.7106,
|
| 827 |
+
"step": 135
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 0.22,
|
| 831 |
+
"learning_rate": 4.432273753129502e-05,
|
| 832 |
+
"loss": 0.6479,
|
| 833 |
+
"step": 136
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 0.22,
|
| 837 |
+
"learning_rate": 4.4241717887207124e-05,
|
| 838 |
+
"loss": 0.7102,
|
| 839 |
+
"step": 137
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 0.22,
|
| 843 |
+
"learning_rate": 4.416019939042515e-05,
|
| 844 |
+
"loss": 0.7188,
|
| 845 |
+
"step": 138
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 0.22,
|
| 849 |
+
"learning_rate": 4.40781841543634e-05,
|
| 850 |
+
"loss": 0.6996,
|
| 851 |
+
"step": 139
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 0.23,
|
| 855 |
+
"learning_rate": 4.399567430531444e-05,
|
| 856 |
+
"loss": 0.7523,
|
| 857 |
+
"step": 140
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.23,
|
| 861 |
+
"learning_rate": 4.391267198239394e-05,
|
| 862 |
+
"loss": 0.6279,
|
| 863 |
+
"step": 141
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.23,
|
| 867 |
+
"learning_rate": 4.3829179337485254e-05,
|
| 868 |
+
"loss": 0.6718,
|
| 869 |
+
"step": 142
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 0.23,
|
| 873 |
+
"learning_rate": 4.374519853518362e-05,
|
| 874 |
+
"loss": 0.668,
|
| 875 |
+
"step": 143
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"epoch": 0.23,
|
| 879 |
+
"learning_rate": 4.366073175274004e-05,
|
| 880 |
+
"loss": 0.8341,
|
| 881 |
+
"step": 144
|
| 882 |
+
},
|
| 883 |
+
{
|
| 884 |
+
"epoch": 0.23,
|
| 885 |
+
"learning_rate": 4.357578118000482e-05,
|
| 886 |
+
"loss": 0.7262,
|
| 887 |
+
"step": 145
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 0.24,
|
| 891 |
+
"learning_rate": 4.3490349019370824e-05,
|
| 892 |
+
"loss": 0.7613,
|
| 893 |
+
"step": 146
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 0.24,
|
| 897 |
+
"learning_rate": 4.340443748571636e-05,
|
| 898 |
+
"loss": 0.6722,
|
| 899 |
+
"step": 147
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 0.24,
|
| 903 |
+
"learning_rate": 4.331804880634775e-05,
|
| 904 |
+
"loss": 0.7229,
|
| 905 |
+
"step": 148
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.24,
|
| 909 |
+
"learning_rate": 4.3231185220941605e-05,
|
| 910 |
+
"loss": 0.7265,
|
| 911 |
+
"step": 149
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 0.24,
|
| 915 |
+
"learning_rate": 4.3143848981486746e-05,
|
| 916 |
+
"loss": 0.7289,
|
| 917 |
+
"step": 150
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 0.24,
|
| 921 |
+
"learning_rate": 4.305604235222582e-05,
|
| 922 |
+
"loss": 0.6441,
|
| 923 |
+
"step": 151
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 0.25,
|
| 927 |
+
"learning_rate": 4.2967767609596624e-05,
|
| 928 |
+
"loss": 0.772,
|
| 929 |
+
"step": 152
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 0.25,
|
| 933 |
+
"learning_rate": 4.287902704217304e-05,
|
| 934 |
+
"loss": 0.705,
|
| 935 |
+
"step": 153
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"epoch": 0.25,
|
| 939 |
+
"learning_rate": 4.2789822950605725e-05,
|
| 940 |
+
"loss": 0.7711,
|
| 941 |
+
"step": 154
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 0.25,
|
| 945 |
+
"learning_rate": 4.2700157647562486e-05,
|
| 946 |
+
"loss": 0.7688,
|
| 947 |
+
"step": 155
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.25,
|
| 951 |
+
"learning_rate": 4.261003345766832e-05,
|
| 952 |
+
"loss": 0.6978,
|
| 953 |
+
"step": 156
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 0.25,
|
| 957 |
+
"learning_rate": 4.251945271744509e-05,
|
| 958 |
+
"loss": 0.7418,
|
| 959 |
+
"step": 157
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 0.26,
|
| 963 |
+
"learning_rate": 4.242841777525101e-05,
|
| 964 |
+
"loss": 0.6258,
|
| 965 |
+
"step": 158
|
| 966 |
+
},
|
| 967 |
+
{
|
| 968 |
+
"epoch": 0.26,
|
| 969 |
+
"learning_rate": 4.233693099121976e-05,
|
| 970 |
+
"loss": 0.7988,
|
| 971 |
+
"step": 159
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 0.26,
|
| 975 |
+
"learning_rate": 4.224499473719926e-05,
|
| 976 |
+
"loss": 0.6947,
|
| 977 |
+
"step": 160
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 0.26,
|
| 981 |
+
"learning_rate": 4.21526113966902e-05,
|
| 982 |
+
"loss": 0.6712,
|
| 983 |
+
"step": 161
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 0.26,
|
| 987 |
+
"learning_rate": 4.205978336478427e-05,
|
| 988 |
+
"loss": 0.6871,
|
| 989 |
+
"step": 162
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.26,
|
| 993 |
+
"learning_rate": 4.196651304810202e-05,
|
| 994 |
+
"loss": 0.6682,
|
| 995 |
+
"step": 163
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 0.27,
|
| 999 |
+
"learning_rate": 4.187280286473048e-05,
|
| 1000 |
+
"loss": 0.6139,
|
| 1001 |
+
"step": 164
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"epoch": 0.27,
|
| 1005 |
+
"learning_rate": 4.177865524416052e-05,
|
| 1006 |
+
"loss": 0.6259,
|
| 1007 |
+
"step": 165
|
| 1008 |
+
},
|
| 1009 |
+
{
|
| 1010 |
+
"epoch": 0.27,
|
| 1011 |
+
"learning_rate": 4.168407262722377e-05,
|
| 1012 |
+
"loss": 0.6894,
|
| 1013 |
+
"step": 166
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 0.27,
|
| 1017 |
+
"learning_rate": 4.1589057466029444e-05,
|
| 1018 |
+
"loss": 0.8107,
|
| 1019 |
+
"step": 167
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 0.27,
|
| 1023 |
+
"learning_rate": 4.149361222390068e-05,
|
| 1024 |
+
"loss": 0.728,
|
| 1025 |
+
"step": 168
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 0.27,
|
| 1029 |
+
"learning_rate": 4.1397739375310736e-05,
|
| 1030 |
+
"loss": 0.6987,
|
| 1031 |
+
"step": 169
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.28,
|
| 1035 |
+
"learning_rate": 4.1301441405818794e-05,
|
| 1036 |
+
"loss": 0.7855,
|
| 1037 |
+
"step": 170
|
| 1038 |
+
},
|
| 1039 |
+
{
|
| 1040 |
+
"epoch": 0.28,
|
| 1041 |
+
"learning_rate": 4.120472081200556e-05,
|
| 1042 |
+
"loss": 0.6786,
|
| 1043 |
+
"step": 171
|
| 1044 |
+
},
|
| 1045 |
+
{
|
| 1046 |
+
"epoch": 0.28,
|
| 1047 |
+
"learning_rate": 4.1107580101408524e-05,
|
| 1048 |
+
"loss": 0.805,
|
| 1049 |
+
"step": 172
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 0.28,
|
| 1053 |
+
"learning_rate": 4.101002179245693e-05,
|
| 1054 |
+
"loss": 0.7006,
|
| 1055 |
+
"step": 173
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 0.28,
|
| 1059 |
+
"learning_rate": 4.09120484144065e-05,
|
| 1060 |
+
"loss": 0.7023,
|
| 1061 |
+
"step": 174
|
| 1062 |
+
},
|
| 1063 |
+
{
|
| 1064 |
+
"epoch": 0.28,
|
| 1065 |
+
"learning_rate": 4.0813662507273885e-05,
|
| 1066 |
+
"loss": 0.7802,
|
| 1067 |
+
"step": 175
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 0.28,
|
| 1071 |
+
"learning_rate": 4.0714866621770775e-05,
|
| 1072 |
+
"loss": 0.6794,
|
| 1073 |
+
"step": 176
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.29,
|
| 1077 |
+
"learning_rate": 4.06156633192378e-05,
|
| 1078 |
+
"loss": 0.6833,
|
| 1079 |
+
"step": 177
|
| 1080 |
+
},
|
| 1081 |
+
{
|
| 1082 |
+
"epoch": 0.29,
|
| 1083 |
+
"learning_rate": 4.051605517157809e-05,
|
| 1084 |
+
"loss": 0.7591,
|
| 1085 |
+
"step": 178
|
| 1086 |
+
},
|
| 1087 |
+
{
|
| 1088 |
+
"epoch": 0.29,
|
| 1089 |
+
"learning_rate": 4.041604476119064e-05,
|
| 1090 |
+
"loss": 0.7059,
|
| 1091 |
+
"step": 179
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.29,
|
| 1095 |
+
"learning_rate": 4.0315634680903336e-05,
|
| 1096 |
+
"loss": 0.713,
|
| 1097 |
+
"step": 180
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 0.29,
|
| 1101 |
+
"learning_rate": 4.021482753390573e-05,
|
| 1102 |
+
"loss": 0.686,
|
| 1103 |
+
"step": 181
|
| 1104 |
+
},
|
| 1105 |
+
{
|
| 1106 |
+
"epoch": 0.29,
|
| 1107 |
+
"learning_rate": 4.011362593368156e-05,
|
| 1108 |
+
"loss": 0.718,
|
| 1109 |
+
"step": 182
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 0.3,
|
| 1113 |
+
"learning_rate": 4.001203250394101e-05,
|
| 1114 |
+
"loss": 0.8431,
|
| 1115 |
+
"step": 183
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.3,
|
| 1119 |
+
"learning_rate": 3.9910049878552646e-05,
|
| 1120 |
+
"loss": 0.7043,
|
| 1121 |
+
"step": 184
|
| 1122 |
+
},
|
| 1123 |
+
{
|
| 1124 |
+
"epoch": 0.3,
|
| 1125 |
+
"learning_rate": 3.9807680701475174e-05,
|
| 1126 |
+
"loss": 0.7591,
|
| 1127 |
+
"step": 185
|
| 1128 |
+
},
|
| 1129 |
+
{
|
| 1130 |
+
"epoch": 0.3,
|
| 1131 |
+
"learning_rate": 3.970492762668887e-05,
|
| 1132 |
+
"loss": 0.7677,
|
| 1133 |
+
"step": 186
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.3,
|
| 1137 |
+
"learning_rate": 3.9601793318126776e-05,
|
| 1138 |
+
"loss": 0.6897,
|
| 1139 |
+
"step": 187
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"epoch": 0.3,
|
| 1143 |
+
"learning_rate": 3.9498280449605664e-05,
|
| 1144 |
+
"loss": 0.753,
|
| 1145 |
+
"step": 188
|
| 1146 |
+
},
|
| 1147 |
+
{
|
| 1148 |
+
"epoch": 0.31,
|
| 1149 |
+
"learning_rate": 3.939439170475666e-05,
|
| 1150 |
+
"loss": 0.7049,
|
| 1151 |
+
"step": 189
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 0.31,
|
| 1155 |
+
"learning_rate": 3.929012977695572e-05,
|
| 1156 |
+
"loss": 0.6654,
|
| 1157 |
+
"step": 190
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.31,
|
| 1161 |
+
"learning_rate": 3.918549736925378e-05,
|
| 1162 |
+
"loss": 0.6969,
|
| 1163 |
+
"step": 191
|
| 1164 |
+
},
|
| 1165 |
+
{
|
| 1166 |
+
"epoch": 0.31,
|
| 1167 |
+
"learning_rate": 3.9080497194306686e-05,
|
| 1168 |
+
"loss": 0.6655,
|
| 1169 |
+
"step": 192
|
| 1170 |
+
},
|
| 1171 |
+
{
|
| 1172 |
+
"epoch": 0.31,
|
| 1173 |
+
"learning_rate": 3.897513197430486e-05,
|
| 1174 |
+
"loss": 0.7118,
|
| 1175 |
+
"step": 193
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.31,
|
| 1179 |
+
"learning_rate": 3.8869404440902735e-05,
|
| 1180 |
+
"loss": 0.5986,
|
| 1181 |
+
"step": 194
|
| 1182 |
+
},
|
| 1183 |
+
{
|
| 1184 |
+
"epoch": 0.32,
|
| 1185 |
+
"learning_rate": 3.876331733514792e-05,
|
| 1186 |
+
"loss": 0.7191,
|
| 1187 |
+
"step": 195
|
| 1188 |
+
},
|
| 1189 |
+
{
|
| 1190 |
+
"epoch": 0.32,
|
| 1191 |
+
"learning_rate": 3.865687340741014e-05,
|
| 1192 |
+
"loss": 0.6433,
|
| 1193 |
+
"step": 196
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 0.32,
|
| 1197 |
+
"learning_rate": 3.855007541730996e-05,
|
| 1198 |
+
"loss": 0.6386,
|
| 1199 |
+
"step": 197
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.32,
|
| 1203 |
+
"learning_rate": 3.844292613364719e-05,
|
| 1204 |
+
"loss": 0.8535,
|
| 1205 |
+
"step": 198
|
| 1206 |
+
},
|
| 1207 |
+
{
|
| 1208 |
+
"epoch": 0.32,
|
| 1209 |
+
"learning_rate": 3.833542833432916e-05,
|
| 1210 |
+
"loss": 0.7112,
|
| 1211 |
+
"step": 199
|
| 1212 |
+
},
|
| 1213 |
+
{
|
| 1214 |
+
"epoch": 0.32,
|
| 1215 |
+
"learning_rate": 3.822758480629864e-05,
|
| 1216 |
+
"loss": 0.7226,
|
| 1217 |
+
"step": 200
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.32,
|
| 1221 |
+
"eval_loss": 0.7749701738357544,
|
| 1222 |
+
"eval_runtime": 5.4698,
|
| 1223 |
+
"eval_samples_per_second": 1.828,
|
| 1224 |
+
"eval_steps_per_second": 0.366,
|
| 1225 |
+
"step": 200
|
| 1226 |
+
}
|
| 1227 |
+
],
|
| 1228 |
+
"logging_steps": 1,
|
| 1229 |
+
"max_steps": 618,
|
| 1230 |
+
"num_input_tokens_seen": 0,
|
| 1231 |
+
"num_train_epochs": 1,
|
| 1232 |
+
"save_steps": 100,
|
| 1233 |
+
"total_flos": 5.041194107142144e+17,
|
| 1234 |
+
"train_batch_size": 4,
|
| 1235 |
+
"trial_name": null,
|
| 1236 |
+
"trial_params": null
|
| 1237 |
+
}
|
checkpoint-200/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1669fbc766ffe69b2e1c5c6cf99065bb5af64e12a25e45ff208dd48072c391fc
|
| 3 |
+
size 4792
|
checkpoint-300/README.md
ADDED
|
@@ -0,0 +1,204 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: /lustre07/scratch/gagan30/arocr/meta-llama/models/FusionNet_7Bx2_MoE_14B
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
|
| 201 |
+
|
| 202 |
+
### Framework versions
|
| 203 |
+
|
| 204 |
+
- PEFT 0.7.2.dev0
|
checkpoint-300/adapter_config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "/lustre07/scratch/gagan30/arocr/meta-llama/models/FusionNet_7Bx2_MoE_14B",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layers_pattern": null,
|
| 10 |
+
"layers_to_transform": null,
|
| 11 |
+
"loftq_config": {},
|
| 12 |
+
"lora_alpha": 16,
|
| 13 |
+
"lora_dropout": 0.05,
|
| 14 |
+
"megatron_config": null,
|
| 15 |
+
"megatron_core": "megatron.core",
|
| 16 |
+
"modules_to_save": null,
|
| 17 |
+
"peft_type": "LORA",
|
| 18 |
+
"r": 16,
|
| 19 |
+
"rank_pattern": {},
|
| 20 |
+
"revision": null,
|
| 21 |
+
"target_modules": [
|
| 22 |
+
"q_proj",
|
| 23 |
+
"gate",
|
| 24 |
+
"o_proj",
|
| 25 |
+
"w1",
|
| 26 |
+
"w3",
|
| 27 |
+
"k_proj",
|
| 28 |
+
"v_proj",
|
| 29 |
+
"w2"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_rslora": false
|
| 33 |
+
}
|
checkpoint-300/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1caf05d4ee564afe0509443a20432e945ba57be20ad9511377952e9caa09a494
|
| 3 |
+
size 289512208
|
checkpoint-300/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8d5c8d7b4e6f1b9e73745b34c85ed03435e46f307101d64f389069dec62a3024
|
| 3 |
+
size 579246546
|
checkpoint-300/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:049c26b844b79121ddd8379f7f69194e63f6fbf6aa007eeac0c66f17eebb8893
|
| 3 |
+
size 888
|
checkpoint-300/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:38f8b8daff3129c5b0751c2f6ce50232436b879c0ae85f1e32205419dd899b6d
|
| 3 |
+
size 14244
|
checkpoint-300/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:14808eb35816406de817be13184fc0959b0b7a479676969bd5f06d8716aff1d5
|
| 3 |
+
size 1064
|
checkpoint-300/special_tokens_map.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<unk>",
|
| 4 |
+
"<s>",
|
| 5 |
+
"</s>"
|
| 6 |
+
],
|
| 7 |
+
"bos_token": {
|
| 8 |
+
"content": "<s>",
|
| 9 |
+
"lstrip": false,
|
| 10 |
+
"normalized": false,
|
| 11 |
+
"rstrip": false,
|
| 12 |
+
"single_word": false
|
| 13 |
+
},
|
| 14 |
+
"eos_token": {
|
| 15 |
+
"content": "</s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false
|
| 20 |
+
},
|
| 21 |
+
"pad_token": "</s>",
|
| 22 |
+
"unk_token": {
|
| 23 |
+
"content": "<unk>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false
|
| 28 |
+
}
|
| 29 |
+
}
|
checkpoint-300/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-300/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
| 3 |
+
size 493443
|
checkpoint-300/tokenizer_config.json
ADDED
|
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": true,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"0": {
|
| 6 |
+
"content": "<unk>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"1": {
|
| 14 |
+
"content": "<s>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"2": {
|
| 22 |
+
"content": "</s>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
}
|
| 29 |
+
},
|
| 30 |
+
"additional_special_tokens": [
|
| 31 |
+
"<unk>",
|
| 32 |
+
"<s>",
|
| 33 |
+
"</s>"
|
| 34 |
+
],
|
| 35 |
+
"bos_token": "<s>",
|
| 36 |
+
"clean_up_tokenization_spaces": false,
|
| 37 |
+
"eos_token": "</s>",
|
| 38 |
+
"legacy": true,
|
| 39 |
+
"max_length": null,
|
| 40 |
+
"model_max_length": 255,
|
| 41 |
+
"pad_to_multiple_of": null,
|
| 42 |
+
"pad_token": "</s>",
|
| 43 |
+
"pad_token_type_id": 0,
|
| 44 |
+
"padding_side": "right",
|
| 45 |
+
"sp_model_kwargs": {},
|
| 46 |
+
"spaces_between_special_tokens": false,
|
| 47 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 48 |
+
"unk_token": "<unk>",
|
| 49 |
+
"use_default_system_prompt": true
|
| 50 |
+
}
|
checkpoint-300/trainer_state.json
ADDED
|
@@ -0,0 +1,1845 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.4854368932038835,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 300,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0,
|
| 13 |
+
"learning_rate": 5e-05,
|
| 14 |
+
"loss": 1.9981,
|
| 15 |
+
"step": 1
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.0,
|
| 19 |
+
"learning_rate": 4.9999675930251536e-05,
|
| 20 |
+
"loss": 2.0613,
|
| 21 |
+
"step": 2
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.0,
|
| 25 |
+
"learning_rate": 4.99987037294078e-05,
|
| 26 |
+
"loss": 1.8228,
|
| 27 |
+
"step": 3
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.01,
|
| 31 |
+
"learning_rate": 4.99970834226737e-05,
|
| 32 |
+
"loss": 1.707,
|
| 33 |
+
"step": 4
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.01,
|
| 37 |
+
"learning_rate": 4.999481505205661e-05,
|
| 38 |
+
"loss": 1.5271,
|
| 39 |
+
"step": 5
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.01,
|
| 43 |
+
"learning_rate": 4.999189867636535e-05,
|
| 44 |
+
"loss": 1.4562,
|
| 45 |
+
"step": 6
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.01,
|
| 49 |
+
"learning_rate": 4.998833437120866e-05,
|
| 50 |
+
"loss": 1.3805,
|
| 51 |
+
"step": 7
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.01,
|
| 55 |
+
"learning_rate": 4.998412222899321e-05,
|
| 56 |
+
"loss": 1.2998,
|
| 57 |
+
"step": 8
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.01,
|
| 61 |
+
"learning_rate": 4.997926235892124e-05,
|
| 62 |
+
"loss": 1.4383,
|
| 63 |
+
"step": 9
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.02,
|
| 67 |
+
"learning_rate": 4.997375488698769e-05,
|
| 68 |
+
"loss": 1.2441,
|
| 69 |
+
"step": 10
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.02,
|
| 73 |
+
"learning_rate": 4.996759995597697e-05,
|
| 74 |
+
"loss": 1.2275,
|
| 75 |
+
"step": 11
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.02,
|
| 79 |
+
"learning_rate": 4.996079772545923e-05,
|
| 80 |
+
"loss": 1.2233,
|
| 81 |
+
"step": 12
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.02,
|
| 85 |
+
"learning_rate": 4.995334837178625e-05,
|
| 86 |
+
"loss": 1.1886,
|
| 87 |
+
"step": 13
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.02,
|
| 91 |
+
"learning_rate": 4.9945252088086825e-05,
|
| 92 |
+
"loss": 1.1779,
|
| 93 |
+
"step": 14
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.02,
|
| 97 |
+
"learning_rate": 4.993650908426182e-05,
|
| 98 |
+
"loss": 1.1122,
|
| 99 |
+
"step": 15
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.03,
|
| 103 |
+
"learning_rate": 4.992711958697868e-05,
|
| 104 |
+
"loss": 1.0766,
|
| 105 |
+
"step": 16
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.03,
|
| 109 |
+
"learning_rate": 4.991708383966556e-05,
|
| 110 |
+
"loss": 1.0836,
|
| 111 |
+
"step": 17
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.03,
|
| 115 |
+
"learning_rate": 4.9906402102505026e-05,
|
| 116 |
+
"loss": 0.9728,
|
| 117 |
+
"step": 18
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.03,
|
| 121 |
+
"learning_rate": 4.989507465242732e-05,
|
| 122 |
+
"loss": 0.9883,
|
| 123 |
+
"step": 19
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.03,
|
| 127 |
+
"learning_rate": 4.988310178310315e-05,
|
| 128 |
+
"loss": 1.0307,
|
| 129 |
+
"step": 20
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.03,
|
| 133 |
+
"learning_rate": 4.9870483804936084e-05,
|
| 134 |
+
"loss": 0.9613,
|
| 135 |
+
"step": 21
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.04,
|
| 139 |
+
"learning_rate": 4.9857221045054535e-05,
|
| 140 |
+
"loss": 1.1038,
|
| 141 |
+
"step": 22
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.04,
|
| 145 |
+
"learning_rate": 4.9843313847303246e-05,
|
| 146 |
+
"loss": 0.9206,
|
| 147 |
+
"step": 23
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.04,
|
| 151 |
+
"learning_rate": 4.9828762572234374e-05,
|
| 152 |
+
"loss": 0.9893,
|
| 153 |
+
"step": 24
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.04,
|
| 157 |
+
"learning_rate": 4.9813567597098166e-05,
|
| 158 |
+
"loss": 0.8328,
|
| 159 |
+
"step": 25
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.04,
|
| 163 |
+
"learning_rate": 4.979772931583317e-05,
|
| 164 |
+
"loss": 0.8712,
|
| 165 |
+
"step": 26
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.04,
|
| 169 |
+
"learning_rate": 4.978124813905599e-05,
|
| 170 |
+
"loss": 0.8031,
|
| 171 |
+
"step": 27
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.05,
|
| 175 |
+
"learning_rate": 4.976412449405072e-05,
|
| 176 |
+
"loss": 0.7675,
|
| 177 |
+
"step": 28
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.05,
|
| 181 |
+
"learning_rate": 4.974635882475778e-05,
|
| 182 |
+
"loss": 0.7851,
|
| 183 |
+
"step": 29
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.05,
|
| 187 |
+
"learning_rate": 4.972795159176243e-05,
|
| 188 |
+
"loss": 0.7447,
|
| 189 |
+
"step": 30
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.05,
|
| 193 |
+
"learning_rate": 4.9708903272282884e-05,
|
| 194 |
+
"loss": 0.7719,
|
| 195 |
+
"step": 31
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.05,
|
| 199 |
+
"learning_rate": 4.9689214360157844e-05,
|
| 200 |
+
"loss": 0.7142,
|
| 201 |
+
"step": 32
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.05,
|
| 205 |
+
"learning_rate": 4.9668885365833795e-05,
|
| 206 |
+
"loss": 0.8649,
|
| 207 |
+
"step": 33
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.06,
|
| 211 |
+
"learning_rate": 4.96479168163517e-05,
|
| 212 |
+
"loss": 0.7574,
|
| 213 |
+
"step": 34
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.06,
|
| 217 |
+
"learning_rate": 4.9626309255333346e-05,
|
| 218 |
+
"loss": 0.9205,
|
| 219 |
+
"step": 35
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.06,
|
| 223 |
+
"learning_rate": 4.9604063242967315e-05,
|
| 224 |
+
"loss": 0.7987,
|
| 225 |
+
"step": 36
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.06,
|
| 229 |
+
"learning_rate": 4.958117935599434e-05,
|
| 230 |
+
"loss": 0.7626,
|
| 231 |
+
"step": 37
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.06,
|
| 235 |
+
"learning_rate": 4.955765818769249e-05,
|
| 236 |
+
"loss": 0.8332,
|
| 237 |
+
"step": 38
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.06,
|
| 241 |
+
"learning_rate": 4.9533500347861675e-05,
|
| 242 |
+
"loss": 0.9178,
|
| 243 |
+
"step": 39
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.06,
|
| 247 |
+
"learning_rate": 4.950870646280791e-05,
|
| 248 |
+
"loss": 0.9919,
|
| 249 |
+
"step": 40
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.07,
|
| 253 |
+
"learning_rate": 4.948327717532705e-05,
|
| 254 |
+
"loss": 0.7098,
|
| 255 |
+
"step": 41
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.07,
|
| 259 |
+
"learning_rate": 4.9457213144688095e-05,
|
| 260 |
+
"loss": 0.7552,
|
| 261 |
+
"step": 42
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.07,
|
| 265 |
+
"learning_rate": 4.9430515046616175e-05,
|
| 266 |
+
"loss": 0.7496,
|
| 267 |
+
"step": 43
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.07,
|
| 271 |
+
"learning_rate": 4.940318357327495e-05,
|
| 272 |
+
"loss": 0.7667,
|
| 273 |
+
"step": 44
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.07,
|
| 277 |
+
"learning_rate": 4.937521943324873e-05,
|
| 278 |
+
"loss": 0.8685,
|
| 279 |
+
"step": 45
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.07,
|
| 283 |
+
"learning_rate": 4.934662335152405e-05,
|
| 284 |
+
"loss": 0.6715,
|
| 285 |
+
"step": 46
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.08,
|
| 289 |
+
"learning_rate": 4.931739606947091e-05,
|
| 290 |
+
"loss": 0.8149,
|
| 291 |
+
"step": 47
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.08,
|
| 295 |
+
"learning_rate": 4.9287538344823544e-05,
|
| 296 |
+
"loss": 0.7346,
|
| 297 |
+
"step": 48
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.08,
|
| 301 |
+
"learning_rate": 4.925705095166079e-05,
|
| 302 |
+
"loss": 0.7803,
|
| 303 |
+
"step": 49
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.08,
|
| 307 |
+
"learning_rate": 4.922593468038599e-05,
|
| 308 |
+
"loss": 0.7451,
|
| 309 |
+
"step": 50
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.08,
|
| 313 |
+
"learning_rate": 4.919419033770652e-05,
|
| 314 |
+
"loss": 0.8402,
|
| 315 |
+
"step": 51
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 0.08,
|
| 319 |
+
"learning_rate": 4.916181874661286e-05,
|
| 320 |
+
"loss": 0.7988,
|
| 321 |
+
"step": 52
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.09,
|
| 325 |
+
"learning_rate": 4.91288207463573e-05,
|
| 326 |
+
"loss": 0.7444,
|
| 327 |
+
"step": 53
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.09,
|
| 331 |
+
"learning_rate": 4.9095197192432105e-05,
|
| 332 |
+
"loss": 0.8545,
|
| 333 |
+
"step": 54
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.09,
|
| 337 |
+
"learning_rate": 4.906094895654744e-05,
|
| 338 |
+
"loss": 0.761,
|
| 339 |
+
"step": 55
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.09,
|
| 343 |
+
"learning_rate": 4.902607692660865e-05,
|
| 344 |
+
"loss": 0.6741,
|
| 345 |
+
"step": 56
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.09,
|
| 349 |
+
"learning_rate": 4.8990582006693365e-05,
|
| 350 |
+
"loss": 0.8457,
|
| 351 |
+
"step": 57
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.09,
|
| 355 |
+
"learning_rate": 4.895446511702793e-05,
|
| 356 |
+
"loss": 0.8096,
|
| 357 |
+
"step": 58
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 0.1,
|
| 361 |
+
"learning_rate": 4.891772719396369e-05,
|
| 362 |
+
"loss": 0.7989,
|
| 363 |
+
"step": 59
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.1,
|
| 367 |
+
"learning_rate": 4.888036918995258e-05,
|
| 368 |
+
"loss": 0.7683,
|
| 369 |
+
"step": 60
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.1,
|
| 373 |
+
"learning_rate": 4.884239207352252e-05,
|
| 374 |
+
"loss": 0.7912,
|
| 375 |
+
"step": 61
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.1,
|
| 379 |
+
"learning_rate": 4.880379682925228e-05,
|
| 380 |
+
"loss": 0.7417,
|
| 381 |
+
"step": 62
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.1,
|
| 385 |
+
"learning_rate": 4.876458445774594e-05,
|
| 386 |
+
"loss": 0.7511,
|
| 387 |
+
"step": 63
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.1,
|
| 391 |
+
"learning_rate": 4.872475597560699e-05,
|
| 392 |
+
"loss": 0.8021,
|
| 393 |
+
"step": 64
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.11,
|
| 397 |
+
"learning_rate": 4.8684312415411897e-05,
|
| 398 |
+
"loss": 0.8154,
|
| 399 |
+
"step": 65
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.11,
|
| 403 |
+
"learning_rate": 4.864325482568344e-05,
|
| 404 |
+
"loss": 0.7109,
|
| 405 |
+
"step": 66
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 0.11,
|
| 409 |
+
"learning_rate": 4.860158427086341e-05,
|
| 410 |
+
"loss": 0.7915,
|
| 411 |
+
"step": 67
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.11,
|
| 415 |
+
"learning_rate": 4.855930183128513e-05,
|
| 416 |
+
"loss": 0.6363,
|
| 417 |
+
"step": 68
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.11,
|
| 421 |
+
"learning_rate": 4.851640860314536e-05,
|
| 422 |
+
"loss": 0.6987,
|
| 423 |
+
"step": 69
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.11,
|
| 427 |
+
"learning_rate": 4.8472905698475906e-05,
|
| 428 |
+
"loss": 0.6498,
|
| 429 |
+
"step": 70
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.11,
|
| 433 |
+
"learning_rate": 4.84287942451148e-05,
|
| 434 |
+
"loss": 0.7768,
|
| 435 |
+
"step": 71
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.12,
|
| 439 |
+
"learning_rate": 4.8384075386677054e-05,
|
| 440 |
+
"loss": 0.7979,
|
| 441 |
+
"step": 72
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.12,
|
| 445 |
+
"learning_rate": 4.833875028252499e-05,
|
| 446 |
+
"loss": 0.7611,
|
| 447 |
+
"step": 73
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 0.12,
|
| 451 |
+
"learning_rate": 4.8292820107738235e-05,
|
| 452 |
+
"loss": 0.7889,
|
| 453 |
+
"step": 74
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.12,
|
| 457 |
+
"learning_rate": 4.824628605308319e-05,
|
| 458 |
+
"loss": 0.6706,
|
| 459 |
+
"step": 75
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.12,
|
| 463 |
+
"learning_rate": 4.819914932498222e-05,
|
| 464 |
+
"loss": 0.7762,
|
| 465 |
+
"step": 76
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.12,
|
| 469 |
+
"learning_rate": 4.815141114548232e-05,
|
| 470 |
+
"loss": 0.7517,
|
| 471 |
+
"step": 77
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.13,
|
| 475 |
+
"learning_rate": 4.8103072752223486e-05,
|
| 476 |
+
"loss": 0.7793,
|
| 477 |
+
"step": 78
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.13,
|
| 481 |
+
"learning_rate": 4.805413539840659e-05,
|
| 482 |
+
"loss": 0.7306,
|
| 483 |
+
"step": 79
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 0.13,
|
| 487 |
+
"learning_rate": 4.80046003527609e-05,
|
| 488 |
+
"loss": 0.834,
|
| 489 |
+
"step": 80
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.13,
|
| 493 |
+
"learning_rate": 4.7954468899511215e-05,
|
| 494 |
+
"loss": 0.8076,
|
| 495 |
+
"step": 81
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.13,
|
| 499 |
+
"learning_rate": 4.790374233834452e-05,
|
| 500 |
+
"loss": 0.8375,
|
| 501 |
+
"step": 82
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.13,
|
| 505 |
+
"learning_rate": 4.7852421984376324e-05,
|
| 506 |
+
"loss": 0.7839,
|
| 507 |
+
"step": 83
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.14,
|
| 511 |
+
"learning_rate": 4.780050916811658e-05,
|
| 512 |
+
"loss": 0.6221,
|
| 513 |
+
"step": 84
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.14,
|
| 517 |
+
"learning_rate": 4.7748005235435137e-05,
|
| 518 |
+
"loss": 0.7212,
|
| 519 |
+
"step": 85
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.14,
|
| 523 |
+
"learning_rate": 4.76949115475269e-05,
|
| 524 |
+
"loss": 0.6369,
|
| 525 |
+
"step": 86
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.14,
|
| 529 |
+
"learning_rate": 4.7641229480876515e-05,
|
| 530 |
+
"loss": 0.7167,
|
| 531 |
+
"step": 87
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 0.14,
|
| 535 |
+
"learning_rate": 4.758696042722269e-05,
|
| 536 |
+
"loss": 0.6908,
|
| 537 |
+
"step": 88
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.14,
|
| 541 |
+
"learning_rate": 4.753210579352211e-05,
|
| 542 |
+
"loss": 0.6681,
|
| 543 |
+
"step": 89
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.15,
|
| 547 |
+
"learning_rate": 4.747666700191297e-05,
|
| 548 |
+
"loss": 0.6566,
|
| 549 |
+
"step": 90
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.15,
|
| 553 |
+
"learning_rate": 4.7420645489678076e-05,
|
| 554 |
+
"loss": 0.6869,
|
| 555 |
+
"step": 91
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.15,
|
| 559 |
+
"learning_rate": 4.7364042709207626e-05,
|
| 560 |
+
"loss": 0.7106,
|
| 561 |
+
"step": 92
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 0.15,
|
| 565 |
+
"learning_rate": 4.730686012796153e-05,
|
| 566 |
+
"loss": 0.6782,
|
| 567 |
+
"step": 93
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 0.15,
|
| 571 |
+
"learning_rate": 4.724909922843136e-05,
|
| 572 |
+
"loss": 0.7148,
|
| 573 |
+
"step": 94
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 0.15,
|
| 577 |
+
"learning_rate": 4.719076150810193e-05,
|
| 578 |
+
"loss": 0.8887,
|
| 579 |
+
"step": 95
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 0.16,
|
| 583 |
+
"learning_rate": 4.7131848479412476e-05,
|
| 584 |
+
"loss": 0.7408,
|
| 585 |
+
"step": 96
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.16,
|
| 589 |
+
"learning_rate": 4.707236166971742e-05,
|
| 590 |
+
"loss": 0.7046,
|
| 591 |
+
"step": 97
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.16,
|
| 595 |
+
"learning_rate": 4.7012302621246804e-05,
|
| 596 |
+
"loss": 0.7657,
|
| 597 |
+
"step": 98
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.16,
|
| 601 |
+
"learning_rate": 4.695167289106629e-05,
|
| 602 |
+
"loss": 0.8138,
|
| 603 |
+
"step": 99
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 0.16,
|
| 607 |
+
"learning_rate": 4.689047405103678e-05,
|
| 608 |
+
"loss": 0.6964,
|
| 609 |
+
"step": 100
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 0.16,
|
| 613 |
+
"eval_loss": 0.796372652053833,
|
| 614 |
+
"eval_runtime": 5.3558,
|
| 615 |
+
"eval_samples_per_second": 1.867,
|
| 616 |
+
"eval_steps_per_second": 0.373,
|
| 617 |
+
"step": 100
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 0.16,
|
| 621 |
+
"learning_rate": 4.68287076877737e-05,
|
| 622 |
+
"loss": 0.6541,
|
| 623 |
+
"step": 101
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 0.17,
|
| 627 |
+
"learning_rate": 4.6766375402605824e-05,
|
| 628 |
+
"loss": 0.714,
|
| 629 |
+
"step": 102
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 0.17,
|
| 633 |
+
"learning_rate": 4.6703478811533794e-05,
|
| 634 |
+
"loss": 0.6823,
|
| 635 |
+
"step": 103
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 0.17,
|
| 639 |
+
"learning_rate": 4.6640019545188216e-05,
|
| 640 |
+
"loss": 0.8283,
|
| 641 |
+
"step": 104
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.17,
|
| 645 |
+
"learning_rate": 4.657599924878736e-05,
|
| 646 |
+
"loss": 0.7126,
|
| 647 |
+
"step": 105
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.17,
|
| 651 |
+
"learning_rate": 4.651141958209453e-05,
|
| 652 |
+
"loss": 0.6612,
|
| 653 |
+
"step": 106
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.17,
|
| 657 |
+
"learning_rate": 4.644628221937504e-05,
|
| 658 |
+
"loss": 0.7339,
|
| 659 |
+
"step": 107
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 0.17,
|
| 663 |
+
"learning_rate": 4.638058884935279e-05,
|
| 664 |
+
"loss": 0.6852,
|
| 665 |
+
"step": 108
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 0.18,
|
| 669 |
+
"learning_rate": 4.6314341175166485e-05,
|
| 670 |
+
"loss": 0.6804,
|
| 671 |
+
"step": 109
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 0.18,
|
| 675 |
+
"learning_rate": 4.6247540914325504e-05,
|
| 676 |
+
"loss": 0.7904,
|
| 677 |
+
"step": 110
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 0.18,
|
| 681 |
+
"learning_rate": 4.618018979866534e-05,
|
| 682 |
+
"loss": 0.6545,
|
| 683 |
+
"step": 111
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.18,
|
| 687 |
+
"learning_rate": 4.611228957430272e-05,
|
| 688 |
+
"loss": 0.7545,
|
| 689 |
+
"step": 112
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.18,
|
| 693 |
+
"learning_rate": 4.6043842001590344e-05,
|
| 694 |
+
"loss": 0.7478,
|
| 695 |
+
"step": 113
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.18,
|
| 699 |
+
"learning_rate": 4.5974848855071206e-05,
|
| 700 |
+
"loss": 0.8083,
|
| 701 |
+
"step": 114
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"epoch": 0.19,
|
| 705 |
+
"learning_rate": 4.590531192343266e-05,
|
| 706 |
+
"loss": 0.7435,
|
| 707 |
+
"step": 115
|
| 708 |
+
},
|
| 709 |
+
{
|
| 710 |
+
"epoch": 0.19,
|
| 711 |
+
"learning_rate": 4.5835233009459964e-05,
|
| 712 |
+
"loss": 0.7647,
|
| 713 |
+
"step": 116
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 0.19,
|
| 717 |
+
"learning_rate": 4.576461392998961e-05,
|
| 718 |
+
"loss": 0.7631,
|
| 719 |
+
"step": 117
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 0.19,
|
| 723 |
+
"learning_rate": 4.569345651586218e-05,
|
| 724 |
+
"loss": 0.7674,
|
| 725 |
+
"step": 118
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 0.19,
|
| 729 |
+
"learning_rate": 4.5621762611874904e-05,
|
| 730 |
+
"loss": 0.6737,
|
| 731 |
+
"step": 119
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 0.19,
|
| 735 |
+
"learning_rate": 4.55495340767338e-05,
|
| 736 |
+
"loss": 0.6901,
|
| 737 |
+
"step": 120
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.2,
|
| 741 |
+
"learning_rate": 4.547677278300555e-05,
|
| 742 |
+
"loss": 0.709,
|
| 743 |
+
"step": 121
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 0.2,
|
| 747 |
+
"learning_rate": 4.540348061706886e-05,
|
| 748 |
+
"loss": 0.5995,
|
| 749 |
+
"step": 122
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 0.2,
|
| 753 |
+
"learning_rate": 4.5329659479065655e-05,
|
| 754 |
+
"loss": 0.6832,
|
| 755 |
+
"step": 123
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 0.2,
|
| 759 |
+
"learning_rate": 4.525531128285173e-05,
|
| 760 |
+
"loss": 0.7584,
|
| 761 |
+
"step": 124
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 0.2,
|
| 765 |
+
"learning_rate": 4.5180437955947195e-05,
|
| 766 |
+
"loss": 0.6998,
|
| 767 |
+
"step": 125
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 0.2,
|
| 771 |
+
"learning_rate": 4.510504143948646e-05,
|
| 772 |
+
"loss": 0.6477,
|
| 773 |
+
"step": 126
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.21,
|
| 777 |
+
"learning_rate": 4.502912368816794e-05,
|
| 778 |
+
"loss": 0.681,
|
| 779 |
+
"step": 127
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.21,
|
| 783 |
+
"learning_rate": 4.4952686670203357e-05,
|
| 784 |
+
"loss": 0.7638,
|
| 785 |
+
"step": 128
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 0.21,
|
| 789 |
+
"learning_rate": 4.487573236726673e-05,
|
| 790 |
+
"loss": 0.7086,
|
| 791 |
+
"step": 129
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 0.21,
|
| 795 |
+
"learning_rate": 4.4798262774442986e-05,
|
| 796 |
+
"loss": 0.6166,
|
| 797 |
+
"step": 130
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 0.21,
|
| 801 |
+
"learning_rate": 4.472027990017623e-05,
|
| 802 |
+
"loss": 0.5901,
|
| 803 |
+
"step": 131
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 0.21,
|
| 807 |
+
"learning_rate": 4.464178576621771e-05,
|
| 808 |
+
"loss": 0.8138,
|
| 809 |
+
"step": 132
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 0.22,
|
| 813 |
+
"learning_rate": 4.456278240757338e-05,
|
| 814 |
+
"loss": 0.6773,
|
| 815 |
+
"step": 133
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 0.22,
|
| 819 |
+
"learning_rate": 4.4483271872451094e-05,
|
| 820 |
+
"loss": 0.6576,
|
| 821 |
+
"step": 134
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.22,
|
| 825 |
+
"learning_rate": 4.44032562222076e-05,
|
| 826 |
+
"loss": 0.7106,
|
| 827 |
+
"step": 135
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 0.22,
|
| 831 |
+
"learning_rate": 4.432273753129502e-05,
|
| 832 |
+
"loss": 0.6479,
|
| 833 |
+
"step": 136
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 0.22,
|
| 837 |
+
"learning_rate": 4.4241717887207124e-05,
|
| 838 |
+
"loss": 0.7102,
|
| 839 |
+
"step": 137
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 0.22,
|
| 843 |
+
"learning_rate": 4.416019939042515e-05,
|
| 844 |
+
"loss": 0.7188,
|
| 845 |
+
"step": 138
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 0.22,
|
| 849 |
+
"learning_rate": 4.40781841543634e-05,
|
| 850 |
+
"loss": 0.6996,
|
| 851 |
+
"step": 139
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 0.23,
|
| 855 |
+
"learning_rate": 4.399567430531444e-05,
|
| 856 |
+
"loss": 0.7523,
|
| 857 |
+
"step": 140
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.23,
|
| 861 |
+
"learning_rate": 4.391267198239394e-05,
|
| 862 |
+
"loss": 0.6279,
|
| 863 |
+
"step": 141
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.23,
|
| 867 |
+
"learning_rate": 4.3829179337485254e-05,
|
| 868 |
+
"loss": 0.6718,
|
| 869 |
+
"step": 142
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 0.23,
|
| 873 |
+
"learning_rate": 4.374519853518362e-05,
|
| 874 |
+
"loss": 0.668,
|
| 875 |
+
"step": 143
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"epoch": 0.23,
|
| 879 |
+
"learning_rate": 4.366073175274004e-05,
|
| 880 |
+
"loss": 0.8341,
|
| 881 |
+
"step": 144
|
| 882 |
+
},
|
| 883 |
+
{
|
| 884 |
+
"epoch": 0.23,
|
| 885 |
+
"learning_rate": 4.357578118000482e-05,
|
| 886 |
+
"loss": 0.7262,
|
| 887 |
+
"step": 145
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 0.24,
|
| 891 |
+
"learning_rate": 4.3490349019370824e-05,
|
| 892 |
+
"loss": 0.7613,
|
| 893 |
+
"step": 146
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 0.24,
|
| 897 |
+
"learning_rate": 4.340443748571636e-05,
|
| 898 |
+
"loss": 0.6722,
|
| 899 |
+
"step": 147
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 0.24,
|
| 903 |
+
"learning_rate": 4.331804880634775e-05,
|
| 904 |
+
"loss": 0.7229,
|
| 905 |
+
"step": 148
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.24,
|
| 909 |
+
"learning_rate": 4.3231185220941605e-05,
|
| 910 |
+
"loss": 0.7265,
|
| 911 |
+
"step": 149
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 0.24,
|
| 915 |
+
"learning_rate": 4.3143848981486746e-05,
|
| 916 |
+
"loss": 0.7289,
|
| 917 |
+
"step": 150
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 0.24,
|
| 921 |
+
"learning_rate": 4.305604235222582e-05,
|
| 922 |
+
"loss": 0.6441,
|
| 923 |
+
"step": 151
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 0.25,
|
| 927 |
+
"learning_rate": 4.2967767609596624e-05,
|
| 928 |
+
"loss": 0.772,
|
| 929 |
+
"step": 152
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 0.25,
|
| 933 |
+
"learning_rate": 4.287902704217304e-05,
|
| 934 |
+
"loss": 0.705,
|
| 935 |
+
"step": 153
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"epoch": 0.25,
|
| 939 |
+
"learning_rate": 4.2789822950605725e-05,
|
| 940 |
+
"loss": 0.7711,
|
| 941 |
+
"step": 154
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 0.25,
|
| 945 |
+
"learning_rate": 4.2700157647562486e-05,
|
| 946 |
+
"loss": 0.7688,
|
| 947 |
+
"step": 155
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.25,
|
| 951 |
+
"learning_rate": 4.261003345766832e-05,
|
| 952 |
+
"loss": 0.6978,
|
| 953 |
+
"step": 156
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 0.25,
|
| 957 |
+
"learning_rate": 4.251945271744509e-05,
|
| 958 |
+
"loss": 0.7418,
|
| 959 |
+
"step": 157
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 0.26,
|
| 963 |
+
"learning_rate": 4.242841777525101e-05,
|
| 964 |
+
"loss": 0.6258,
|
| 965 |
+
"step": 158
|
| 966 |
+
},
|
| 967 |
+
{
|
| 968 |
+
"epoch": 0.26,
|
| 969 |
+
"learning_rate": 4.233693099121976e-05,
|
| 970 |
+
"loss": 0.7988,
|
| 971 |
+
"step": 159
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 0.26,
|
| 975 |
+
"learning_rate": 4.224499473719926e-05,
|
| 976 |
+
"loss": 0.6947,
|
| 977 |
+
"step": 160
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 0.26,
|
| 981 |
+
"learning_rate": 4.21526113966902e-05,
|
| 982 |
+
"loss": 0.6712,
|
| 983 |
+
"step": 161
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 0.26,
|
| 987 |
+
"learning_rate": 4.205978336478427e-05,
|
| 988 |
+
"loss": 0.6871,
|
| 989 |
+
"step": 162
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.26,
|
| 993 |
+
"learning_rate": 4.196651304810202e-05,
|
| 994 |
+
"loss": 0.6682,
|
| 995 |
+
"step": 163
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 0.27,
|
| 999 |
+
"learning_rate": 4.187280286473048e-05,
|
| 1000 |
+
"loss": 0.6139,
|
| 1001 |
+
"step": 164
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"epoch": 0.27,
|
| 1005 |
+
"learning_rate": 4.177865524416052e-05,
|
| 1006 |
+
"loss": 0.6259,
|
| 1007 |
+
"step": 165
|
| 1008 |
+
},
|
| 1009 |
+
{
|
| 1010 |
+
"epoch": 0.27,
|
| 1011 |
+
"learning_rate": 4.168407262722377e-05,
|
| 1012 |
+
"loss": 0.6894,
|
| 1013 |
+
"step": 166
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 0.27,
|
| 1017 |
+
"learning_rate": 4.1589057466029444e-05,
|
| 1018 |
+
"loss": 0.8107,
|
| 1019 |
+
"step": 167
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 0.27,
|
| 1023 |
+
"learning_rate": 4.149361222390068e-05,
|
| 1024 |
+
"loss": 0.728,
|
| 1025 |
+
"step": 168
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 0.27,
|
| 1029 |
+
"learning_rate": 4.1397739375310736e-05,
|
| 1030 |
+
"loss": 0.6987,
|
| 1031 |
+
"step": 169
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.28,
|
| 1035 |
+
"learning_rate": 4.1301441405818794e-05,
|
| 1036 |
+
"loss": 0.7855,
|
| 1037 |
+
"step": 170
|
| 1038 |
+
},
|
| 1039 |
+
{
|
| 1040 |
+
"epoch": 0.28,
|
| 1041 |
+
"learning_rate": 4.120472081200556e-05,
|
| 1042 |
+
"loss": 0.6786,
|
| 1043 |
+
"step": 171
|
| 1044 |
+
},
|
| 1045 |
+
{
|
| 1046 |
+
"epoch": 0.28,
|
| 1047 |
+
"learning_rate": 4.1107580101408524e-05,
|
| 1048 |
+
"loss": 0.805,
|
| 1049 |
+
"step": 172
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 0.28,
|
| 1053 |
+
"learning_rate": 4.101002179245693e-05,
|
| 1054 |
+
"loss": 0.7006,
|
| 1055 |
+
"step": 173
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 0.28,
|
| 1059 |
+
"learning_rate": 4.09120484144065e-05,
|
| 1060 |
+
"loss": 0.7023,
|
| 1061 |
+
"step": 174
|
| 1062 |
+
},
|
| 1063 |
+
{
|
| 1064 |
+
"epoch": 0.28,
|
| 1065 |
+
"learning_rate": 4.0813662507273885e-05,
|
| 1066 |
+
"loss": 0.7802,
|
| 1067 |
+
"step": 175
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 0.28,
|
| 1071 |
+
"learning_rate": 4.0714866621770775e-05,
|
| 1072 |
+
"loss": 0.6794,
|
| 1073 |
+
"step": 176
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.29,
|
| 1077 |
+
"learning_rate": 4.06156633192378e-05,
|
| 1078 |
+
"loss": 0.6833,
|
| 1079 |
+
"step": 177
|
| 1080 |
+
},
|
| 1081 |
+
{
|
| 1082 |
+
"epoch": 0.29,
|
| 1083 |
+
"learning_rate": 4.051605517157809e-05,
|
| 1084 |
+
"loss": 0.7591,
|
| 1085 |
+
"step": 178
|
| 1086 |
+
},
|
| 1087 |
+
{
|
| 1088 |
+
"epoch": 0.29,
|
| 1089 |
+
"learning_rate": 4.041604476119064e-05,
|
| 1090 |
+
"loss": 0.7059,
|
| 1091 |
+
"step": 179
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.29,
|
| 1095 |
+
"learning_rate": 4.0315634680903336e-05,
|
| 1096 |
+
"loss": 0.713,
|
| 1097 |
+
"step": 180
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 0.29,
|
| 1101 |
+
"learning_rate": 4.021482753390573e-05,
|
| 1102 |
+
"loss": 0.686,
|
| 1103 |
+
"step": 181
|
| 1104 |
+
},
|
| 1105 |
+
{
|
| 1106 |
+
"epoch": 0.29,
|
| 1107 |
+
"learning_rate": 4.011362593368156e-05,
|
| 1108 |
+
"loss": 0.718,
|
| 1109 |
+
"step": 182
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 0.3,
|
| 1113 |
+
"learning_rate": 4.001203250394101e-05,
|
| 1114 |
+
"loss": 0.8431,
|
| 1115 |
+
"step": 183
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.3,
|
| 1119 |
+
"learning_rate": 3.9910049878552646e-05,
|
| 1120 |
+
"loss": 0.7043,
|
| 1121 |
+
"step": 184
|
| 1122 |
+
},
|
| 1123 |
+
{
|
| 1124 |
+
"epoch": 0.3,
|
| 1125 |
+
"learning_rate": 3.9807680701475174e-05,
|
| 1126 |
+
"loss": 0.7591,
|
| 1127 |
+
"step": 185
|
| 1128 |
+
},
|
| 1129 |
+
{
|
| 1130 |
+
"epoch": 0.3,
|
| 1131 |
+
"learning_rate": 3.970492762668887e-05,
|
| 1132 |
+
"loss": 0.7677,
|
| 1133 |
+
"step": 186
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.3,
|
| 1137 |
+
"learning_rate": 3.9601793318126776e-05,
|
| 1138 |
+
"loss": 0.6897,
|
| 1139 |
+
"step": 187
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"epoch": 0.3,
|
| 1143 |
+
"learning_rate": 3.9498280449605664e-05,
|
| 1144 |
+
"loss": 0.753,
|
| 1145 |
+
"step": 188
|
| 1146 |
+
},
|
| 1147 |
+
{
|
| 1148 |
+
"epoch": 0.31,
|
| 1149 |
+
"learning_rate": 3.939439170475666e-05,
|
| 1150 |
+
"loss": 0.7049,
|
| 1151 |
+
"step": 189
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 0.31,
|
| 1155 |
+
"learning_rate": 3.929012977695572e-05,
|
| 1156 |
+
"loss": 0.6654,
|
| 1157 |
+
"step": 190
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.31,
|
| 1161 |
+
"learning_rate": 3.918549736925378e-05,
|
| 1162 |
+
"loss": 0.6969,
|
| 1163 |
+
"step": 191
|
| 1164 |
+
},
|
| 1165 |
+
{
|
| 1166 |
+
"epoch": 0.31,
|
| 1167 |
+
"learning_rate": 3.9080497194306686e-05,
|
| 1168 |
+
"loss": 0.6655,
|
| 1169 |
+
"step": 192
|
| 1170 |
+
},
|
| 1171 |
+
{
|
| 1172 |
+
"epoch": 0.31,
|
| 1173 |
+
"learning_rate": 3.897513197430486e-05,
|
| 1174 |
+
"loss": 0.7118,
|
| 1175 |
+
"step": 193
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.31,
|
| 1179 |
+
"learning_rate": 3.8869404440902735e-05,
|
| 1180 |
+
"loss": 0.5986,
|
| 1181 |
+
"step": 194
|
| 1182 |
+
},
|
| 1183 |
+
{
|
| 1184 |
+
"epoch": 0.32,
|
| 1185 |
+
"learning_rate": 3.876331733514792e-05,
|
| 1186 |
+
"loss": 0.7191,
|
| 1187 |
+
"step": 195
|
| 1188 |
+
},
|
| 1189 |
+
{
|
| 1190 |
+
"epoch": 0.32,
|
| 1191 |
+
"learning_rate": 3.865687340741014e-05,
|
| 1192 |
+
"loss": 0.6433,
|
| 1193 |
+
"step": 196
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 0.32,
|
| 1197 |
+
"learning_rate": 3.855007541730996e-05,
|
| 1198 |
+
"loss": 0.6386,
|
| 1199 |
+
"step": 197
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.32,
|
| 1203 |
+
"learning_rate": 3.844292613364719e-05,
|
| 1204 |
+
"loss": 0.8535,
|
| 1205 |
+
"step": 198
|
| 1206 |
+
},
|
| 1207 |
+
{
|
| 1208 |
+
"epoch": 0.32,
|
| 1209 |
+
"learning_rate": 3.833542833432916e-05,
|
| 1210 |
+
"loss": 0.7112,
|
| 1211 |
+
"step": 199
|
| 1212 |
+
},
|
| 1213 |
+
{
|
| 1214 |
+
"epoch": 0.32,
|
| 1215 |
+
"learning_rate": 3.822758480629864e-05,
|
| 1216 |
+
"loss": 0.7226,
|
| 1217 |
+
"step": 200
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.32,
|
| 1221 |
+
"eval_loss": 0.7749701738357544,
|
| 1222 |
+
"eval_runtime": 5.4698,
|
| 1223 |
+
"eval_samples_per_second": 1.828,
|
| 1224 |
+
"eval_steps_per_second": 0.366,
|
| 1225 |
+
"step": 200
|
| 1226 |
+
},
|
| 1227 |
+
{
|
| 1228 |
+
"epoch": 0.33,
|
| 1229 |
+
"learning_rate": 3.811939834546163e-05,
|
| 1230 |
+
"loss": 0.6725,
|
| 1231 |
+
"step": 201
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.33,
|
| 1235 |
+
"learning_rate": 3.801087175661488e-05,
|
| 1236 |
+
"loss": 0.711,
|
| 1237 |
+
"step": 202
|
| 1238 |
+
},
|
| 1239 |
+
{
|
| 1240 |
+
"epoch": 0.33,
|
| 1241 |
+
"learning_rate": 3.790200785337311e-05,
|
| 1242 |
+
"loss": 0.6973,
|
| 1243 |
+
"step": 203
|
| 1244 |
+
},
|
| 1245 |
+
{
|
| 1246 |
+
"epoch": 0.33,
|
| 1247 |
+
"learning_rate": 3.7792809458096146e-05,
|
| 1248 |
+
"loss": 0.7107,
|
| 1249 |
+
"step": 204
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 0.33,
|
| 1253 |
+
"learning_rate": 3.768327940181572e-05,
|
| 1254 |
+
"loss": 0.6809,
|
| 1255 |
+
"step": 205
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.33,
|
| 1259 |
+
"learning_rate": 3.757342052416205e-05,
|
| 1260 |
+
"loss": 0.6272,
|
| 1261 |
+
"step": 206
|
| 1262 |
+
},
|
| 1263 |
+
{
|
| 1264 |
+
"epoch": 0.33,
|
| 1265 |
+
"learning_rate": 3.746323567329024e-05,
|
| 1266 |
+
"loss": 0.7267,
|
| 1267 |
+
"step": 207
|
| 1268 |
+
},
|
| 1269 |
+
{
|
| 1270 |
+
"epoch": 0.34,
|
| 1271 |
+
"learning_rate": 3.7352727705806446e-05,
|
| 1272 |
+
"loss": 0.764,
|
| 1273 |
+
"step": 208
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.34,
|
| 1277 |
+
"learning_rate": 3.724189948669381e-05,
|
| 1278 |
+
"loss": 0.7307,
|
| 1279 |
+
"step": 209
|
| 1280 |
+
},
|
| 1281 |
+
{
|
| 1282 |
+
"epoch": 0.34,
|
| 1283 |
+
"learning_rate": 3.7130753889238165e-05,
|
| 1284 |
+
"loss": 0.8486,
|
| 1285 |
+
"step": 210
|
| 1286 |
+
},
|
| 1287 |
+
{
|
| 1288 |
+
"epoch": 0.34,
|
| 1289 |
+
"learning_rate": 3.7019293794953595e-05,
|
| 1290 |
+
"loss": 0.7304,
|
| 1291 |
+
"step": 211
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 0.34,
|
| 1295 |
+
"learning_rate": 3.690752209350767e-05,
|
| 1296 |
+
"loss": 0.8079,
|
| 1297 |
+
"step": 212
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.34,
|
| 1301 |
+
"learning_rate": 3.679544168264656e-05,
|
| 1302 |
+
"loss": 0.6661,
|
| 1303 |
+
"step": 213
|
| 1304 |
+
},
|
| 1305 |
+
{
|
| 1306 |
+
"epoch": 0.35,
|
| 1307 |
+
"learning_rate": 3.668305546811991e-05,
|
| 1308 |
+
"loss": 0.7078,
|
| 1309 |
+
"step": 214
|
| 1310 |
+
},
|
| 1311 |
+
{
|
| 1312 |
+
"epoch": 0.35,
|
| 1313 |
+
"learning_rate": 3.65703663636055e-05,
|
| 1314 |
+
"loss": 0.6363,
|
| 1315 |
+
"step": 215
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.35,
|
| 1319 |
+
"learning_rate": 3.645737729063372e-05,
|
| 1320 |
+
"loss": 0.6479,
|
| 1321 |
+
"step": 216
|
| 1322 |
+
},
|
| 1323 |
+
{
|
| 1324 |
+
"epoch": 0.35,
|
| 1325 |
+
"learning_rate": 3.63440911785118e-05,
|
| 1326 |
+
"loss": 0.8032,
|
| 1327 |
+
"step": 217
|
| 1328 |
+
},
|
| 1329 |
+
{
|
| 1330 |
+
"epoch": 0.35,
|
| 1331 |
+
"learning_rate": 3.6230510964247886e-05,
|
| 1332 |
+
"loss": 0.7619,
|
| 1333 |
+
"step": 218
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 0.35,
|
| 1337 |
+
"learning_rate": 3.61166395924749e-05,
|
| 1338 |
+
"loss": 0.6744,
|
| 1339 |
+
"step": 219
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 0.36,
|
| 1343 |
+
"learning_rate": 3.600248001537418e-05,
|
| 1344 |
+
"loss": 0.5971,
|
| 1345 |
+
"step": 220
|
| 1346 |
+
},
|
| 1347 |
+
{
|
| 1348 |
+
"epoch": 0.36,
|
| 1349 |
+
"learning_rate": 3.588803519259898e-05,
|
| 1350 |
+
"loss": 0.7197,
|
| 1351 |
+
"step": 221
|
| 1352 |
+
},
|
| 1353 |
+
{
|
| 1354 |
+
"epoch": 0.36,
|
| 1355 |
+
"learning_rate": 3.577330809119768e-05,
|
| 1356 |
+
"loss": 0.7581,
|
| 1357 |
+
"step": 222
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.36,
|
| 1361 |
+
"learning_rate": 3.565830168553691e-05,
|
| 1362 |
+
"loss": 0.6288,
|
| 1363 |
+
"step": 223
|
| 1364 |
+
},
|
| 1365 |
+
{
|
| 1366 |
+
"epoch": 0.36,
|
| 1367 |
+
"learning_rate": 3.554301895722442e-05,
|
| 1368 |
+
"loss": 0.8863,
|
| 1369 |
+
"step": 224
|
| 1370 |
+
},
|
| 1371 |
+
{
|
| 1372 |
+
"epoch": 0.36,
|
| 1373 |
+
"learning_rate": 3.542746289503181e-05,
|
| 1374 |
+
"loss": 0.6523,
|
| 1375 |
+
"step": 225
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 0.37,
|
| 1379 |
+
"learning_rate": 3.5311636494816984e-05,
|
| 1380 |
+
"loss": 0.6503,
|
| 1381 |
+
"step": 226
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 0.37,
|
| 1385 |
+
"learning_rate": 3.519554275944655e-05,
|
| 1386 |
+
"loss": 0.7903,
|
| 1387 |
+
"step": 227
|
| 1388 |
+
},
|
| 1389 |
+
{
|
| 1390 |
+
"epoch": 0.37,
|
| 1391 |
+
"learning_rate": 3.50791846987179e-05,
|
| 1392 |
+
"loss": 0.7974,
|
| 1393 |
+
"step": 228
|
| 1394 |
+
},
|
| 1395 |
+
{
|
| 1396 |
+
"epoch": 0.37,
|
| 1397 |
+
"learning_rate": 3.496256532928125e-05,
|
| 1398 |
+
"loss": 0.712,
|
| 1399 |
+
"step": 229
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.37,
|
| 1403 |
+
"learning_rate": 3.484568767456135e-05,
|
| 1404 |
+
"loss": 0.6632,
|
| 1405 |
+
"step": 230
|
| 1406 |
+
},
|
| 1407 |
+
{
|
| 1408 |
+
"epoch": 0.37,
|
| 1409 |
+
"learning_rate": 3.47285547646792e-05,
|
| 1410 |
+
"loss": 0.7328,
|
| 1411 |
+
"step": 231
|
| 1412 |
+
},
|
| 1413 |
+
{
|
| 1414 |
+
"epoch": 0.38,
|
| 1415 |
+
"learning_rate": 3.46111696363734e-05,
|
| 1416 |
+
"loss": 0.6455,
|
| 1417 |
+
"step": 232
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 0.38,
|
| 1421 |
+
"learning_rate": 3.4493535332921475e-05,
|
| 1422 |
+
"loss": 0.6295,
|
| 1423 |
+
"step": 233
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 0.38,
|
| 1427 |
+
"learning_rate": 3.4375654904060956e-05,
|
| 1428 |
+
"loss": 0.6613,
|
| 1429 |
+
"step": 234
|
| 1430 |
+
},
|
| 1431 |
+
{
|
| 1432 |
+
"epoch": 0.38,
|
| 1433 |
+
"learning_rate": 3.425753140591031e-05,
|
| 1434 |
+
"loss": 0.6991,
|
| 1435 |
+
"step": 235
|
| 1436 |
+
},
|
| 1437 |
+
{
|
| 1438 |
+
"epoch": 0.38,
|
| 1439 |
+
"learning_rate": 3.413916790088973e-05,
|
| 1440 |
+
"loss": 0.6047,
|
| 1441 |
+
"step": 236
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.38,
|
| 1445 |
+
"learning_rate": 3.402056745764172e-05,
|
| 1446 |
+
"loss": 0.7401,
|
| 1447 |
+
"step": 237
|
| 1448 |
+
},
|
| 1449 |
+
{
|
| 1450 |
+
"epoch": 0.39,
|
| 1451 |
+
"learning_rate": 3.3901733150951535e-05,
|
| 1452 |
+
"loss": 0.6909,
|
| 1453 |
+
"step": 238
|
| 1454 |
+
},
|
| 1455 |
+
{
|
| 1456 |
+
"epoch": 0.39,
|
| 1457 |
+
"learning_rate": 3.37826680616675e-05,
|
| 1458 |
+
"loss": 0.6293,
|
| 1459 |
+
"step": 239
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 0.39,
|
| 1463 |
+
"learning_rate": 3.366337527662109e-05,
|
| 1464 |
+
"loss": 0.7261,
|
| 1465 |
+
"step": 240
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 0.39,
|
| 1469 |
+
"learning_rate": 3.354385788854694e-05,
|
| 1470 |
+
"loss": 0.8233,
|
| 1471 |
+
"step": 241
|
| 1472 |
+
},
|
| 1473 |
+
{
|
| 1474 |
+
"epoch": 0.39,
|
| 1475 |
+
"learning_rate": 3.3424118996002624e-05,
|
| 1476 |
+
"loss": 0.7349,
|
| 1477 |
+
"step": 242
|
| 1478 |
+
},
|
| 1479 |
+
{
|
| 1480 |
+
"epoch": 0.39,
|
| 1481 |
+
"learning_rate": 3.3304161703288385e-05,
|
| 1482 |
+
"loss": 0.6952,
|
| 1483 |
+
"step": 243
|
| 1484 |
+
},
|
| 1485 |
+
{
|
| 1486 |
+
"epoch": 0.39,
|
| 1487 |
+
"learning_rate": 3.318398912036658e-05,
|
| 1488 |
+
"loss": 0.6676,
|
| 1489 |
+
"step": 244
|
| 1490 |
+
},
|
| 1491 |
+
{
|
| 1492 |
+
"epoch": 0.4,
|
| 1493 |
+
"learning_rate": 3.3063604362781125e-05,
|
| 1494 |
+
"loss": 0.6929,
|
| 1495 |
+
"step": 245
|
| 1496 |
+
},
|
| 1497 |
+
{
|
| 1498 |
+
"epoch": 0.4,
|
| 1499 |
+
"learning_rate": 3.2943010551576654e-05,
|
| 1500 |
+
"loss": 0.7219,
|
| 1501 |
+
"step": 246
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 0.4,
|
| 1505 |
+
"learning_rate": 3.282221081321766e-05,
|
| 1506 |
+
"loss": 0.7747,
|
| 1507 |
+
"step": 247
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 0.4,
|
| 1511 |
+
"learning_rate": 3.27012082795074e-05,
|
| 1512 |
+
"loss": 0.6931,
|
| 1513 |
+
"step": 248
|
| 1514 |
+
},
|
| 1515 |
+
{
|
| 1516 |
+
"epoch": 0.4,
|
| 1517 |
+
"learning_rate": 3.258000608750674e-05,
|
| 1518 |
+
"loss": 0.6869,
|
| 1519 |
+
"step": 249
|
| 1520 |
+
},
|
| 1521 |
+
{
|
| 1522 |
+
"epoch": 0.4,
|
| 1523 |
+
"learning_rate": 3.245860737945278e-05,
|
| 1524 |
+
"loss": 0.6864,
|
| 1525 |
+
"step": 250
|
| 1526 |
+
},
|
| 1527 |
+
{
|
| 1528 |
+
"epoch": 0.41,
|
| 1529 |
+
"learning_rate": 3.233701530267743e-05,
|
| 1530 |
+
"loss": 0.7052,
|
| 1531 |
+
"step": 251
|
| 1532 |
+
},
|
| 1533 |
+
{
|
| 1534 |
+
"epoch": 0.41,
|
| 1535 |
+
"learning_rate": 3.2215233009525786e-05,
|
| 1536 |
+
"loss": 0.7917,
|
| 1537 |
+
"step": 252
|
| 1538 |
+
},
|
| 1539 |
+
{
|
| 1540 |
+
"epoch": 0.41,
|
| 1541 |
+
"learning_rate": 3.209326365727441e-05,
|
| 1542 |
+
"loss": 0.7137,
|
| 1543 |
+
"step": 253
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 0.41,
|
| 1547 |
+
"learning_rate": 3.19711104080495e-05,
|
| 1548 |
+
"loss": 0.7149,
|
| 1549 |
+
"step": 254
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 0.41,
|
| 1553 |
+
"learning_rate": 3.184877642874486e-05,
|
| 1554 |
+
"loss": 0.694,
|
| 1555 |
+
"step": 255
|
| 1556 |
+
},
|
| 1557 |
+
{
|
| 1558 |
+
"epoch": 0.41,
|
| 1559 |
+
"learning_rate": 3.172626489093986e-05,
|
| 1560 |
+
"loss": 0.6155,
|
| 1561 |
+
"step": 256
|
| 1562 |
+
},
|
| 1563 |
+
{
|
| 1564 |
+
"epoch": 0.42,
|
| 1565 |
+
"learning_rate": 3.1603578970817146e-05,
|
| 1566 |
+
"loss": 0.743,
|
| 1567 |
+
"step": 257
|
| 1568 |
+
},
|
| 1569 |
+
{
|
| 1570 |
+
"epoch": 0.42,
|
| 1571 |
+
"learning_rate": 3.1480721849080344e-05,
|
| 1572 |
+
"loss": 0.6893,
|
| 1573 |
+
"step": 258
|
| 1574 |
+
},
|
| 1575 |
+
{
|
| 1576 |
+
"epoch": 0.42,
|
| 1577 |
+
"learning_rate": 3.1357696710871576e-05,
|
| 1578 |
+
"loss": 0.6215,
|
| 1579 |
+
"step": 259
|
| 1580 |
+
},
|
| 1581 |
+
{
|
| 1582 |
+
"epoch": 0.42,
|
| 1583 |
+
"learning_rate": 3.123450674568889e-05,
|
| 1584 |
+
"loss": 0.6225,
|
| 1585 |
+
"step": 260
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 0.42,
|
| 1589 |
+
"learning_rate": 3.1111155147303574e-05,
|
| 1590 |
+
"loss": 0.795,
|
| 1591 |
+
"step": 261
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 0.42,
|
| 1595 |
+
"learning_rate": 3.0987645113677335e-05,
|
| 1596 |
+
"loss": 0.84,
|
| 1597 |
+
"step": 262
|
| 1598 |
+
},
|
| 1599 |
+
{
|
| 1600 |
+
"epoch": 0.43,
|
| 1601 |
+
"learning_rate": 3.086397984687943e-05,
|
| 1602 |
+
"loss": 0.6852,
|
| 1603 |
+
"step": 263
|
| 1604 |
+
},
|
| 1605 |
+
{
|
| 1606 |
+
"epoch": 0.43,
|
| 1607 |
+
"learning_rate": 3.074016255300359e-05,
|
| 1608 |
+
"loss": 0.7301,
|
| 1609 |
+
"step": 264
|
| 1610 |
+
},
|
| 1611 |
+
{
|
| 1612 |
+
"epoch": 0.43,
|
| 1613 |
+
"learning_rate": 3.061619644208498e-05,
|
| 1614 |
+
"loss": 0.7638,
|
| 1615 |
+
"step": 265
|
| 1616 |
+
},
|
| 1617 |
+
{
|
| 1618 |
+
"epoch": 0.43,
|
| 1619 |
+
"learning_rate": 3.0492084728016902e-05,
|
| 1620 |
+
"loss": 0.7403,
|
| 1621 |
+
"step": 266
|
| 1622 |
+
},
|
| 1623 |
+
{
|
| 1624 |
+
"epoch": 0.43,
|
| 1625 |
+
"learning_rate": 3.036783062846751e-05,
|
| 1626 |
+
"loss": 0.8257,
|
| 1627 |
+
"step": 267
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 0.43,
|
| 1631 |
+
"learning_rate": 3.0243437364796386e-05,
|
| 1632 |
+
"loss": 0.6582,
|
| 1633 |
+
"step": 268
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 0.44,
|
| 1637 |
+
"learning_rate": 3.0118908161971025e-05,
|
| 1638 |
+
"loss": 0.6031,
|
| 1639 |
+
"step": 269
|
| 1640 |
+
},
|
| 1641 |
+
{
|
| 1642 |
+
"epoch": 0.44,
|
| 1643 |
+
"learning_rate": 2.9994246248483228e-05,
|
| 1644 |
+
"loss": 0.6981,
|
| 1645 |
+
"step": 270
|
| 1646 |
+
},
|
| 1647 |
+
{
|
| 1648 |
+
"epoch": 0.44,
|
| 1649 |
+
"learning_rate": 2.9869454856265376e-05,
|
| 1650 |
+
"loss": 0.6632,
|
| 1651 |
+
"step": 271
|
| 1652 |
+
},
|
| 1653 |
+
{
|
| 1654 |
+
"epoch": 0.44,
|
| 1655 |
+
"learning_rate": 2.9744537220606693e-05,
|
| 1656 |
+
"loss": 0.7312,
|
| 1657 |
+
"step": 272
|
| 1658 |
+
},
|
| 1659 |
+
{
|
| 1660 |
+
"epoch": 0.44,
|
| 1661 |
+
"learning_rate": 2.9619496580069317e-05,
|
| 1662 |
+
"loss": 0.6421,
|
| 1663 |
+
"step": 273
|
| 1664 |
+
},
|
| 1665 |
+
{
|
| 1666 |
+
"epoch": 0.44,
|
| 1667 |
+
"learning_rate": 2.9494336176404357e-05,
|
| 1668 |
+
"loss": 0.6031,
|
| 1669 |
+
"step": 274
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 0.44,
|
| 1673 |
+
"learning_rate": 2.9369059254467858e-05,
|
| 1674 |
+
"loss": 0.77,
|
| 1675 |
+
"step": 275
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 0.45,
|
| 1679 |
+
"learning_rate": 2.9243669062136664e-05,
|
| 1680 |
+
"loss": 0.7053,
|
| 1681 |
+
"step": 276
|
| 1682 |
+
},
|
| 1683 |
+
{
|
| 1684 |
+
"epoch": 0.45,
|
| 1685 |
+
"learning_rate": 2.9118168850224226e-05,
|
| 1686 |
+
"loss": 0.7678,
|
| 1687 |
+
"step": 277
|
| 1688 |
+
},
|
| 1689 |
+
{
|
| 1690 |
+
"epoch": 0.45,
|
| 1691 |
+
"learning_rate": 2.8992561872396313e-05,
|
| 1692 |
+
"loss": 0.5997,
|
| 1693 |
+
"step": 278
|
| 1694 |
+
},
|
| 1695 |
+
{
|
| 1696 |
+
"epoch": 0.45,
|
| 1697 |
+
"learning_rate": 2.8866851385086652e-05,
|
| 1698 |
+
"loss": 0.772,
|
| 1699 |
+
"step": 279
|
| 1700 |
+
},
|
| 1701 |
+
{
|
| 1702 |
+
"epoch": 0.45,
|
| 1703 |
+
"learning_rate": 2.8741040647412538e-05,
|
| 1704 |
+
"loss": 0.6521,
|
| 1705 |
+
"step": 280
|
| 1706 |
+
},
|
| 1707 |
+
{
|
| 1708 |
+
"epoch": 0.45,
|
| 1709 |
+
"learning_rate": 2.8615132921090292e-05,
|
| 1710 |
+
"loss": 0.6677,
|
| 1711 |
+
"step": 281
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 0.46,
|
| 1715 |
+
"learning_rate": 2.8489131470350727e-05,
|
| 1716 |
+
"loss": 0.6277,
|
| 1717 |
+
"step": 282
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 0.46,
|
| 1721 |
+
"learning_rate": 2.836303956185453e-05,
|
| 1722 |
+
"loss": 0.7005,
|
| 1723 |
+
"step": 283
|
| 1724 |
+
},
|
| 1725 |
+
{
|
| 1726 |
+
"epoch": 0.46,
|
| 1727 |
+
"learning_rate": 2.8236860464607534e-05,
|
| 1728 |
+
"loss": 0.8361,
|
| 1729 |
+
"step": 284
|
| 1730 |
+
},
|
| 1731 |
+
{
|
| 1732 |
+
"epoch": 0.46,
|
| 1733 |
+
"learning_rate": 2.8110597449876014e-05,
|
| 1734 |
+
"loss": 0.6893,
|
| 1735 |
+
"step": 285
|
| 1736 |
+
},
|
| 1737 |
+
{
|
| 1738 |
+
"epoch": 0.46,
|
| 1739 |
+
"learning_rate": 2.7984253791101834e-05,
|
| 1740 |
+
"loss": 0.7185,
|
| 1741 |
+
"step": 286
|
| 1742 |
+
},
|
| 1743 |
+
{
|
| 1744 |
+
"epoch": 0.46,
|
| 1745 |
+
"learning_rate": 2.7857832763817622e-05,
|
| 1746 |
+
"loss": 0.703,
|
| 1747 |
+
"step": 287
|
| 1748 |
+
},
|
| 1749 |
+
{
|
| 1750 |
+
"epoch": 0.47,
|
| 1751 |
+
"learning_rate": 2.773133764556181e-05,
|
| 1752 |
+
"loss": 0.6402,
|
| 1753 |
+
"step": 288
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 0.47,
|
| 1757 |
+
"learning_rate": 2.7604771715793697e-05,
|
| 1758 |
+
"loss": 0.6384,
|
| 1759 |
+
"step": 289
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 0.47,
|
| 1763 |
+
"learning_rate": 2.74781382558084e-05,
|
| 1764 |
+
"loss": 0.8262,
|
| 1765 |
+
"step": 290
|
| 1766 |
+
},
|
| 1767 |
+
{
|
| 1768 |
+
"epoch": 0.47,
|
| 1769 |
+
"learning_rate": 2.735144054865181e-05,
|
| 1770 |
+
"loss": 0.7639,
|
| 1771 |
+
"step": 291
|
| 1772 |
+
},
|
| 1773 |
+
{
|
| 1774 |
+
"epoch": 0.47,
|
| 1775 |
+
"learning_rate": 2.722468187903544e-05,
|
| 1776 |
+
"loss": 0.7043,
|
| 1777 |
+
"step": 292
|
| 1778 |
+
},
|
| 1779 |
+
{
|
| 1780 |
+
"epoch": 0.47,
|
| 1781 |
+
"learning_rate": 2.7097865533251314e-05,
|
| 1782 |
+
"loss": 0.5832,
|
| 1783 |
+
"step": 293
|
| 1784 |
+
},
|
| 1785 |
+
{
|
| 1786 |
+
"epoch": 0.48,
|
| 1787 |
+
"learning_rate": 2.6970994799086735e-05,
|
| 1788 |
+
"loss": 0.681,
|
| 1789 |
+
"step": 294
|
| 1790 |
+
},
|
| 1791 |
+
{
|
| 1792 |
+
"epoch": 0.48,
|
| 1793 |
+
"learning_rate": 2.6844072965739054e-05,
|
| 1794 |
+
"loss": 0.658,
|
| 1795 |
+
"step": 295
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 0.48,
|
| 1799 |
+
"learning_rate": 2.6717103323730396e-05,
|
| 1800 |
+
"loss": 0.6749,
|
| 1801 |
+
"step": 296
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 0.48,
|
| 1805 |
+
"learning_rate": 2.6590089164822364e-05,
|
| 1806 |
+
"loss": 0.6759,
|
| 1807 |
+
"step": 297
|
| 1808 |
+
},
|
| 1809 |
+
{
|
| 1810 |
+
"epoch": 0.48,
|
| 1811 |
+
"learning_rate": 2.6463033781930673e-05,
|
| 1812 |
+
"loss": 0.5983,
|
| 1813 |
+
"step": 298
|
| 1814 |
+
},
|
| 1815 |
+
{
|
| 1816 |
+
"epoch": 0.48,
|
| 1817 |
+
"learning_rate": 2.633594046903981e-05,
|
| 1818 |
+
"loss": 0.7378,
|
| 1819 |
+
"step": 299
|
| 1820 |
+
},
|
| 1821 |
+
{
|
| 1822 |
+
"epoch": 0.49,
|
| 1823 |
+
"learning_rate": 2.62088125211176e-05,
|
| 1824 |
+
"loss": 0.7041,
|
| 1825 |
+
"step": 300
|
| 1826 |
+
},
|
| 1827 |
+
{
|
| 1828 |
+
"epoch": 0.49,
|
| 1829 |
+
"eval_loss": 0.7667814493179321,
|
| 1830 |
+
"eval_runtime": 5.4254,
|
| 1831 |
+
"eval_samples_per_second": 1.843,
|
| 1832 |
+
"eval_steps_per_second": 0.369,
|
| 1833 |
+
"step": 300
|
| 1834 |
+
}
|
| 1835 |
+
],
|
| 1836 |
+
"logging_steps": 1,
|
| 1837 |
+
"max_steps": 618,
|
| 1838 |
+
"num_input_tokens_seen": 0,
|
| 1839 |
+
"num_train_epochs": 1,
|
| 1840 |
+
"save_steps": 100,
|
| 1841 |
+
"total_flos": 7.561791160713216e+17,
|
| 1842 |
+
"train_batch_size": 4,
|
| 1843 |
+
"trial_name": null,
|
| 1844 |
+
"trial_params": null
|
| 1845 |
+
}
|
checkpoint-300/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1669fbc766ffe69b2e1c5c6cf99065bb5af64e12a25e45ff208dd48072c391fc
|
| 3 |
+
size 4792
|
checkpoint-400/README.md
ADDED
|
@@ -0,0 +1,204 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: /lustre07/scratch/gagan30/arocr/meta-llama/models/FusionNet_7Bx2_MoE_14B
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
|
| 201 |
+
|
| 202 |
+
### Framework versions
|
| 203 |
+
|
| 204 |
+
- PEFT 0.7.2.dev0
|
checkpoint-400/adapter_config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "/lustre07/scratch/gagan30/arocr/meta-llama/models/FusionNet_7Bx2_MoE_14B",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layers_pattern": null,
|
| 10 |
+
"layers_to_transform": null,
|
| 11 |
+
"loftq_config": {},
|
| 12 |
+
"lora_alpha": 16,
|
| 13 |
+
"lora_dropout": 0.05,
|
| 14 |
+
"megatron_config": null,
|
| 15 |
+
"megatron_core": "megatron.core",
|
| 16 |
+
"modules_to_save": null,
|
| 17 |
+
"peft_type": "LORA",
|
| 18 |
+
"r": 16,
|
| 19 |
+
"rank_pattern": {},
|
| 20 |
+
"revision": null,
|
| 21 |
+
"target_modules": [
|
| 22 |
+
"q_proj",
|
| 23 |
+
"gate",
|
| 24 |
+
"o_proj",
|
| 25 |
+
"w1",
|
| 26 |
+
"w3",
|
| 27 |
+
"k_proj",
|
| 28 |
+
"v_proj",
|
| 29 |
+
"w2"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_rslora": false
|
| 33 |
+
}
|
checkpoint-400/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:64a17b3fa9574e66855740e7ab7b92c151db96622ffabfdcb62e4a7ad7e764ff
|
| 3 |
+
size 289512208
|
checkpoint-400/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7bd7491af4b7fb0dfc9d2075f0c5365810d4e359b4320a34a78813c33c31f248
|
| 3 |
+
size 579246546
|
checkpoint-400/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:049c26b844b79121ddd8379f7f69194e63f6fbf6aa007eeac0c66f17eebb8893
|
| 3 |
+
size 888
|
checkpoint-400/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:28e870b1698005b4198dd417c453350c8acd5e6367b862bef489f2fa92b5aad5
|
| 3 |
+
size 14244
|
checkpoint-400/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:18a7cbdaff115ebbdbd626b08af973e9ad734f85d66a3354d40000428b39c458
|
| 3 |
+
size 1064
|
checkpoint-400/special_tokens_map.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<unk>",
|
| 4 |
+
"<s>",
|
| 5 |
+
"</s>"
|
| 6 |
+
],
|
| 7 |
+
"bos_token": {
|
| 8 |
+
"content": "<s>",
|
| 9 |
+
"lstrip": false,
|
| 10 |
+
"normalized": false,
|
| 11 |
+
"rstrip": false,
|
| 12 |
+
"single_word": false
|
| 13 |
+
},
|
| 14 |
+
"eos_token": {
|
| 15 |
+
"content": "</s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false
|
| 20 |
+
},
|
| 21 |
+
"pad_token": "</s>",
|
| 22 |
+
"unk_token": {
|
| 23 |
+
"content": "<unk>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false
|
| 28 |
+
}
|
| 29 |
+
}
|
checkpoint-400/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-400/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
| 3 |
+
size 493443
|