Task: SequenceClassification

README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: facebook/opt-6.7b
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- 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. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+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).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.11.1

adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "facebook/opt-6.7b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "score",
+    "classifier",
+    "score"
+  ],
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "fc1",
+    "out_proj",
+    "q_proj",
+    "fc2",
+    "k_proj"
+  ],
+  "task_type": "SEQ_CLS",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4b4bbd06a5769350db16a9e57c1313a6cdeb6d17251aae8a40ec9642c271b8f
+size 37818360

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "add_bos_token": true,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "</s>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "errors": "replace",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "</s>"
+}

trainer_state-opt-fp16-QLORA-super_glue-axg-sequence_classification.json

@@ -0,0 +1,682 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 8.88888888888889,
+  "eval_steps": 1,
+  "global_step": 40,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 2.578125,
+      "learning_rate": 2.5e-05,
+      "loss": 0.663,
+      "step": 1
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "eval_accuracy": 0.6388888888888888,
+      "eval_loss": 0.6485392451286316,
+      "eval_runtime": 0.6135,
+      "eval_samples_per_second": 117.366,
+      "eval_steps_per_second": 8.15,
+      "step": 1
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 8.875,
+      "learning_rate": 5e-05,
+      "loss": 0.756,
+      "step": 2
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "eval_accuracy": 0.6111111111111112,
+      "eval_loss": 0.6574299931526184,
+      "eval_runtime": 0.6097,
+      "eval_samples_per_second": 118.09,
+      "eval_steps_per_second": 8.201,
+      "step": 2
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 4.46875,
+      "learning_rate": 4.868421052631579e-05,
+      "loss": 0.7238,
+      "step": 3
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "eval_accuracy": 0.5277777777777778,
+      "eval_loss": 0.7034233808517456,
+      "eval_runtime": 0.608,
+      "eval_samples_per_second": 118.427,
+      "eval_steps_per_second": 8.224,
+      "step": 3
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 13.25,
+      "learning_rate": 4.736842105263158e-05,
+      "loss": 0.7122,
+      "step": 4
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "eval_accuracy": 0.5,
+      "eval_loss": 0.7725694179534912,
+      "eval_runtime": 0.6086,
+      "eval_samples_per_second": 118.309,
+      "eval_steps_per_second": 8.216,
+      "step": 4
+    },
+    {
+      "epoch": 1.1111111111111112,
+      "grad_norm": 9.0,
+      "learning_rate": 4.605263157894737e-05,
+      "loss": 0.7642,
+      "step": 5
+    },
+    {
+      "epoch": 1.1111111111111112,
+      "eval_accuracy": 0.4583333333333333,
+      "eval_loss": 0.8437364101409912,
+      "eval_runtime": 0.6086,
+      "eval_samples_per_second": 118.308,
+      "eval_steps_per_second": 8.216,
+      "step": 5
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 11.5,
+      "learning_rate": 4.473684210526316e-05,
+      "loss": 0.7398,
+      "step": 6
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "eval_accuracy": 0.4722222222222222,
+      "eval_loss": 0.8946533203125,
+      "eval_runtime": 0.6095,
+      "eval_samples_per_second": 118.131,
+      "eval_steps_per_second": 8.204,
+      "step": 6
+    },
+    {
+      "epoch": 1.5555555555555556,
+      "grad_norm": 7.34375,
+      "learning_rate": 4.342105263157895e-05,
+      "loss": 0.6496,
+      "step": 7
+    },
+    {
+      "epoch": 1.5555555555555556,
+      "eval_accuracy": 0.4583333333333333,
+      "eval_loss": 0.9147610068321228,
+      "eval_runtime": 0.6082,
+      "eval_samples_per_second": 118.375,
+      "eval_steps_per_second": 8.22,
+      "step": 7
+    },
+    {
+      "epoch": 1.7777777777777777,
+      "grad_norm": 8.9375,
+      "learning_rate": 4.210526315789474e-05,
+      "loss": 0.8145,
+      "step": 8
+    },
+    {
+      "epoch": 1.7777777777777777,
+      "eval_accuracy": 0.4722222222222222,
+      "eval_loss": 0.8886311650276184,
+      "eval_runtime": 0.6076,
+      "eval_samples_per_second": 118.496,
+      "eval_steps_per_second": 8.229,
+      "step": 8
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 3.578125,
+      "learning_rate": 4.078947368421053e-05,
+      "loss": 0.7133,
+      "step": 9
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.4583333333333333,
+      "eval_loss": 0.8463134765625,
+      "eval_runtime": 0.6081,
+      "eval_samples_per_second": 118.399,
+      "eval_steps_per_second": 8.222,
+      "step": 9
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 4.9375,
+      "learning_rate": 3.9473684210526316e-05,
+      "loss": 0.7018,
+      "step": 10
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "eval_accuracy": 0.4861111111111111,
+      "eval_loss": 0.7938368320465088,
+      "eval_runtime": 0.6078,
+      "eval_samples_per_second": 118.455,
+      "eval_steps_per_second": 8.226,
+      "step": 10
+    },
+    {
+      "epoch": 2.4444444444444446,
+      "grad_norm": 4.96875,
+      "learning_rate": 3.815789473684211e-05,
+      "loss": 0.7119,
+      "step": 11
+    },
+    {
+      "epoch": 2.4444444444444446,
+      "eval_accuracy": 0.4861111111111111,
+      "eval_loss": 0.7457139492034912,
+      "eval_runtime": 0.6077,
+      "eval_samples_per_second": 118.489,
+      "eval_steps_per_second": 8.228,
+      "step": 11
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 10.1875,
+      "learning_rate": 3.6842105263157895e-05,
+      "loss": 0.7619,
+      "step": 12
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "eval_accuracy": 0.5,
+      "eval_loss": 0.7044270634651184,
+      "eval_runtime": 0.608,
+      "eval_samples_per_second": 118.417,
+      "eval_steps_per_second": 8.223,
+      "step": 12
+    },
+    {
+      "epoch": 2.888888888888889,
+      "grad_norm": 2.6875,
+      "learning_rate": 3.5526315789473684e-05,
+      "loss": 0.7001,
+      "step": 13
+    },
+    {
+      "epoch": 2.888888888888889,
+      "eval_accuracy": 0.6111111111111112,
+      "eval_loss": 0.6843125820159912,
+      "eval_runtime": 0.608,
+      "eval_samples_per_second": 118.411,
+      "eval_steps_per_second": 8.223,
+      "step": 13
+    },
+    {
+      "epoch": 3.111111111111111,
+      "grad_norm": 4.90625,
+      "learning_rate": 3.421052631578947e-05,
+      "loss": 0.7011,
+      "step": 14
+    },
+    {
+      "epoch": 3.111111111111111,
+      "eval_accuracy": 0.6111111111111112,
+      "eval_loss": 0.6841227412223816,
+      "eval_runtime": 0.6072,
+      "eval_samples_per_second": 118.583,
+      "eval_steps_per_second": 8.235,
+      "step": 14
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 7.15625,
+      "learning_rate": 3.289473684210527e-05,
+      "loss": 0.6936,
+      "step": 15
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "eval_accuracy": 0.6527777777777778,
+      "eval_loss": 0.6861708164215088,
+      "eval_runtime": 0.6089,
+      "eval_samples_per_second": 118.237,
+      "eval_steps_per_second": 8.211,
+      "step": 15
+    },
+    {
+      "epoch": 3.5555555555555554,
+      "grad_norm": 3.125,
+      "learning_rate": 3.157894736842105e-05,
+      "loss": 0.6712,
+      "step": 16
+    },
+    {
+      "epoch": 3.5555555555555554,
+      "eval_accuracy": 0.6388888888888888,
+      "eval_loss": 0.689697265625,
+      "eval_runtime": 0.6077,
+      "eval_samples_per_second": 118.487,
+      "eval_steps_per_second": 8.228,
+      "step": 16
+    },
+    {
+      "epoch": 3.7777777777777777,
+      "grad_norm": 3.8125,
+      "learning_rate": 3.0263157894736844e-05,
+      "loss": 0.7103,
+      "step": 17
+    },
+    {
+      "epoch": 3.7777777777777777,
+      "eval_accuracy": 0.6111111111111112,
+      "eval_loss": 0.6951768398284912,
+      "eval_runtime": 0.6084,
+      "eval_samples_per_second": 118.35,
+      "eval_steps_per_second": 8.219,
+      "step": 17
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 6.03125,
+      "learning_rate": 2.8947368421052634e-05,
+      "loss": 0.7363,
+      "step": 18
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.5972222222222222,
+      "eval_loss": 0.7005886435508728,
+      "eval_runtime": 0.6084,
+      "eval_samples_per_second": 118.351,
+      "eval_steps_per_second": 8.219,
+      "step": 18
+    },
+    {
+      "epoch": 4.222222222222222,
+      "grad_norm": 11.1875,
+      "learning_rate": 2.7631578947368426e-05,
+      "loss": 0.6435,
+      "step": 19
+    },
+    {
+      "epoch": 4.222222222222222,
+      "eval_accuracy": 0.5833333333333334,
+      "eval_loss": 0.7067057490348816,
+      "eval_runtime": 0.6096,
+      "eval_samples_per_second": 118.111,
+      "eval_steps_per_second": 8.202,
+      "step": 19
+    },
+    {
+      "epoch": 4.444444444444445,
+      "grad_norm": 4.65625,
+      "learning_rate": 2.6315789473684212e-05,
+      "loss": 0.6981,
+      "step": 20
+    },
+    {
+      "epoch": 4.444444444444445,
+      "eval_accuracy": 0.5833333333333334,
+      "eval_loss": 0.7121039628982544,
+      "eval_runtime": 0.6082,
+      "eval_samples_per_second": 118.379,
+      "eval_steps_per_second": 8.221,
+      "step": 20
+    },
+    {
+      "epoch": 4.666666666666667,
+      "grad_norm": 2.703125,
+      "learning_rate": 2.5e-05,
+      "loss": 0.6926,
+      "step": 21
+    },
+    {
+      "epoch": 4.666666666666667,
+      "eval_accuracy": 0.5416666666666666,
+      "eval_loss": 0.7211371660232544,
+      "eval_runtime": 0.6081,
+      "eval_samples_per_second": 118.398,
+      "eval_steps_per_second": 8.222,
+      "step": 21
+    },
+    {
+      "epoch": 4.888888888888889,
+      "grad_norm": 5.15625,
+      "learning_rate": 2.368421052631579e-05,
+      "loss": 0.7108,
+      "step": 22
+    },
+    {
+      "epoch": 4.888888888888889,
+      "eval_accuracy": 0.5,
+      "eval_loss": 0.73095703125,
+      "eval_runtime": 0.6083,
+      "eval_samples_per_second": 118.372,
+      "eval_steps_per_second": 8.22,
+      "step": 22
+    },
+    {
+      "epoch": 5.111111111111111,
+      "grad_norm": 5.15625,
+      "learning_rate": 2.236842105263158e-05,
+      "loss": 0.672,
+      "step": 23
+    },
+    {
+      "epoch": 5.111111111111111,
+      "eval_accuracy": 0.4861111111111111,
+      "eval_loss": 0.7393120527267456,
+      "eval_runtime": 0.6079,
+      "eval_samples_per_second": 118.437,
+      "eval_steps_per_second": 8.225,
+      "step": 23
+    },
+    {
+      "epoch": 5.333333333333333,
+      "grad_norm": 3.140625,
+      "learning_rate": 2.105263157894737e-05,
+      "loss": 0.7141,
+      "step": 24
+    },
+    {
+      "epoch": 5.333333333333333,
+      "eval_accuracy": 0.4722222222222222,
+      "eval_loss": 0.7498372197151184,
+      "eval_runtime": 0.6082,
+      "eval_samples_per_second": 118.379,
+      "eval_steps_per_second": 8.221,
+      "step": 24
+    },
+    {
+      "epoch": 5.555555555555555,
+      "grad_norm": 2.359375,
+      "learning_rate": 1.9736842105263158e-05,
+      "loss": 0.6683,
+      "step": 25
+    },
+    {
+      "epoch": 5.555555555555555,
+      "eval_accuracy": 0.4861111111111111,
+      "eval_loss": 0.7597113847732544,
+      "eval_runtime": 0.6096,
+      "eval_samples_per_second": 118.114,
+      "eval_steps_per_second": 8.202,
+      "step": 25
+    },
+    {
+      "epoch": 5.777777777777778,
+      "grad_norm": 10.5625,
+      "learning_rate": 1.8421052631578947e-05,
+      "loss": 0.7034,
+      "step": 26
+    },
+    {
+      "epoch": 5.777777777777778,
+      "eval_accuracy": 0.4722222222222222,
+      "eval_loss": 0.7664387822151184,
+      "eval_runtime": 0.6087,
+      "eval_samples_per_second": 118.28,
+      "eval_steps_per_second": 8.214,
+      "step": 26
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 10.0625,
+      "learning_rate": 1.7105263157894737e-05,
+      "loss": 0.692,
+      "step": 27
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.4722222222222222,
+      "eval_loss": 0.7706434726715088,
+      "eval_runtime": 0.6079,
+      "eval_samples_per_second": 118.431,
+      "eval_steps_per_second": 8.224,
+      "step": 27
+    },
+    {
+      "epoch": 6.222222222222222,
+      "grad_norm": 2.578125,
+      "learning_rate": 1.5789473684210526e-05,
+      "loss": 0.6832,
+      "step": 28
+    },
+    {
+      "epoch": 6.222222222222222,
+      "eval_accuracy": 0.4722222222222222,
+      "eval_loss": 0.7749837040901184,
+      "eval_runtime": 0.6081,
+      "eval_samples_per_second": 118.408,
+      "eval_steps_per_second": 8.223,
+      "step": 28
+    },
+    {
+      "epoch": 6.444444444444445,
+      "grad_norm": 4.34375,
+      "learning_rate": 1.4473684210526317e-05,
+      "loss": 0.7021,
+      "step": 29
+    },
+    {
+      "epoch": 6.444444444444445,
+      "eval_accuracy": 0.4583333333333333,
+      "eval_loss": 0.7776963710784912,
+      "eval_runtime": 0.6079,
+      "eval_samples_per_second": 118.436,
+      "eval_steps_per_second": 8.225,
+      "step": 29
+    },
+    {
+      "epoch": 6.666666666666667,
+      "grad_norm": 2.625,
+      "learning_rate": 1.3157894736842106e-05,
+      "loss": 0.6819,
+      "step": 30
+    },
+    {
+      "epoch": 6.666666666666667,
+      "eval_accuracy": 0.4722222222222222,
+      "eval_loss": 0.7759331464767456,
+      "eval_runtime": 0.6086,
+      "eval_samples_per_second": 118.3,
+      "eval_steps_per_second": 8.215,
+      "step": 30
+    },
+    {
+      "epoch": 6.888888888888889,
+      "grad_norm": 3.53125,
+      "learning_rate": 1.1842105263157895e-05,
+      "loss": 0.6352,
+      "step": 31
+    },
+    {
+      "epoch": 6.888888888888889,
+      "eval_accuracy": 0.4583333333333333,
+      "eval_loss": 0.7765842080116272,
+      "eval_runtime": 0.6091,
+      "eval_samples_per_second": 118.211,
+      "eval_steps_per_second": 8.209,
+      "step": 31
+    },
+    {
+      "epoch": 7.111111111111111,
+      "grad_norm": 2.46875,
+      "learning_rate": 1.0526315789473684e-05,
+      "loss": 0.6888,
+      "step": 32
+    },
+    {
+      "epoch": 7.111111111111111,
+      "eval_accuracy": 0.4722222222222222,
+      "eval_loss": 0.7748752236366272,
+      "eval_runtime": 0.6086,
+      "eval_samples_per_second": 118.309,
+      "eval_steps_per_second": 8.216,
+      "step": 32
+    },
+    {
+      "epoch": 7.333333333333333,
+      "grad_norm": 3.375,
+      "learning_rate": 9.210526315789474e-06,
+      "loss": 0.6618,
+      "step": 33
+    },
+    {
+      "epoch": 7.333333333333333,
+      "eval_accuracy": 0.5,
+      "eval_loss": 0.7731662392616272,
+      "eval_runtime": 0.6075,
+      "eval_samples_per_second": 118.515,
+      "eval_steps_per_second": 8.23,
+      "step": 33
+    },
+    {
+      "epoch": 7.555555555555555,
+      "grad_norm": 6.65625,
+      "learning_rate": 7.894736842105263e-06,
+      "loss": 0.6754,
+      "step": 34
+    },
+    {
+      "epoch": 7.555555555555555,
+      "eval_accuracy": 0.5138888888888888,
+      "eval_loss": 0.7746039628982544,
+      "eval_runtime": 0.6088,
+      "eval_samples_per_second": 118.274,
+      "eval_steps_per_second": 8.214,
+      "step": 34
+    },
+    {
+      "epoch": 7.777777777777778,
+      "grad_norm": 6.375,
+      "learning_rate": 6.578947368421053e-06,
+      "loss": 0.6597,
+      "step": 35
+    },
+    {
+      "epoch": 7.777777777777778,
+      "eval_accuracy": 0.5138888888888888,
+      "eval_loss": 0.7731662392616272,
+      "eval_runtime": 0.6081,
+      "eval_samples_per_second": 118.392,
+      "eval_steps_per_second": 8.222,
+      "step": 35
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 5.75,
+      "learning_rate": 5.263157894736842e-06,
+      "loss": 0.6567,
+      "step": 36
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.5138888888888888,
+      "eval_loss": 0.7737358808517456,
+      "eval_runtime": 0.6081,
+      "eval_samples_per_second": 118.395,
+      "eval_steps_per_second": 8.222,
+      "step": 36
+    },
+    {
+      "epoch": 8.222222222222221,
+      "grad_norm": 4.90625,
+      "learning_rate": 3.9473684210526315e-06,
+      "loss": 0.6282,
+      "step": 37
+    },
+    {
+      "epoch": 8.222222222222221,
+      "eval_accuracy": 0.5138888888888888,
+      "eval_loss": 0.7725694179534912,
+      "eval_runtime": 0.6079,
+      "eval_samples_per_second": 118.436,
+      "eval_steps_per_second": 8.225,
+      "step": 37
+    },
+    {
+      "epoch": 8.444444444444445,
+      "grad_norm": 7.71875,
+      "learning_rate": 2.631578947368421e-06,
+      "loss": 0.6826,
+      "step": 38
+    },
+    {
+      "epoch": 8.444444444444445,
+      "eval_accuracy": 0.5138888888888888,
+      "eval_loss": 0.7727593183517456,
+      "eval_runtime": 0.6088,
+      "eval_samples_per_second": 118.264,
+      "eval_steps_per_second": 8.213,
+      "step": 38
+    },
+    {
+      "epoch": 8.666666666666666,
+      "grad_norm": 4.53125,
+      "learning_rate": 1.3157894736842106e-06,
+      "loss": 0.6556,
+      "step": 39
+    },
+    {
+      "epoch": 8.666666666666666,
+      "eval_accuracy": 0.5138888888888888,
+      "eval_loss": 0.7752007246017456,
+      "eval_runtime": 0.6082,
+      "eval_samples_per_second": 118.385,
+      "eval_steps_per_second": 8.221,
+      "step": 39
+    },
+    {
+      "epoch": 8.88888888888889,
+      "grad_norm": 3.796875,
+      "learning_rate": 0.0,
+      "loss": 0.6745,
+      "step": 40
+    },
+    {
+      "epoch": 8.88888888888889,
+      "eval_accuracy": 0.5138888888888888,
+      "eval_loss": 0.7738173007965088,
+      "eval_runtime": 0.6087,
+      "eval_samples_per_second": 118.294,
+      "eval_steps_per_second": 8.215,
+      "step": 40
+    },
+    {
+      "epoch": 8.88888888888889,
+      "step": 40,
+      "total_flos": 3923745857077248.0,
+      "train_loss": 0.695129108428955,
+      "train_runtime": 77.1509,
+      "train_samples_per_second": 36.811,
+      "train_steps_per_second": 0.518
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 40,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3923745857077248.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b59541e082b3010735170aaacb9cc96a83dd078e422a650f332ae2d6021a3b32
+size 5112