Commit
•
eafe8b7
1
Parent(s):
ca2c2e4
Model save
Browse files- README.md +119 -0
- adapter_model.safetensors +1 -1
- all_results.json +9 -0
- train_results.json +9 -0
- trainer_state.json +1604 -0
README.md
ADDED
|
@@ -0,0 +1,119 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
|
| 3 |
+
library_name: peft
|
| 4 |
+
license: llama3.1
|
| 5 |
+
tags:
|
| 6 |
+
- trl
|
| 7 |
+
- sft
|
| 8 |
+
- generated_from_trainer
|
| 9 |
+
model-index:
|
| 10 |
+
- name: Llama-31-8B_task-2_60-samples_config-3_full
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# Llama-31-8B_task-2_60-samples_config-3_full
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) on an unknown dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 1.0760
|
| 22 |
+
|
| 23 |
+
## Model description
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Intended uses & limitations
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training and evaluation data
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training procedure
|
| 36 |
+
|
| 37 |
+
### Training hyperparameters
|
| 38 |
+
|
| 39 |
+
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 1e-05
|
| 41 |
+
- train_batch_size: 1
|
| 42 |
+
- eval_batch_size: 1
|
| 43 |
+
- seed: 42
|
| 44 |
+
- distributed_type: multi-GPU
|
| 45 |
+
- gradient_accumulation_steps: 8
|
| 46 |
+
- total_train_batch_size: 8
|
| 47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 48 |
+
- lr_scheduler_type: cosine
|
| 49 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 50 |
+
- num_epochs: 150
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 55 |
+
|:-------------:|:-------:|:----:|:---------------:|
|
| 56 |
+
| 1.5659 | 0.8696 | 5 | 1.5846 |
|
| 57 |
+
| 1.5947 | 1.9130 | 11 | 1.5811 |
|
| 58 |
+
| 1.6305 | 2.9565 | 17 | 1.5758 |
|
| 59 |
+
| 1.5682 | 4.0 | 23 | 1.5673 |
|
| 60 |
+
| 1.5687 | 4.8696 | 28 | 1.5571 |
|
| 61 |
+
| 1.5556 | 5.9130 | 34 | 1.5406 |
|
| 62 |
+
| 1.4699 | 6.9565 | 40 | 1.5190 |
|
| 63 |
+
| 1.5027 | 8.0 | 46 | 1.4958 |
|
| 64 |
+
| 1.5203 | 8.8696 | 51 | 1.4719 |
|
| 65 |
+
| 1.4872 | 9.9130 | 57 | 1.4445 |
|
| 66 |
+
| 1.4184 | 10.9565 | 63 | 1.4151 |
|
| 67 |
+
| 1.3817 | 12.0 | 69 | 1.3868 |
|
| 68 |
+
| 1.3397 | 12.8696 | 74 | 1.3648 |
|
| 69 |
+
| 1.3234 | 13.9130 | 80 | 1.3390 |
|
| 70 |
+
| 1.2893 | 14.9565 | 86 | 1.3122 |
|
| 71 |
+
| 1.2999 | 16.0 | 92 | 1.2852 |
|
| 72 |
+
| 1.2212 | 16.8696 | 97 | 1.2628 |
|
| 73 |
+
| 1.234 | 17.9130 | 103 | 1.2358 |
|
| 74 |
+
| 1.1704 | 18.9565 | 109 | 1.2078 |
|
| 75 |
+
| 1.1499 | 20.0 | 115 | 1.1796 |
|
| 76 |
+
| 1.1265 | 20.8696 | 120 | 1.1570 |
|
| 77 |
+
| 1.0716 | 21.9130 | 126 | 1.1357 |
|
| 78 |
+
| 1.0332 | 22.9565 | 132 | 1.1223 |
|
| 79 |
+
| 1.0631 | 24.0 | 138 | 1.1155 |
|
| 80 |
+
| 1.0659 | 24.8696 | 143 | 1.1111 |
|
| 81 |
+
| 1.0637 | 25.9130 | 149 | 1.1068 |
|
| 82 |
+
| 0.9979 | 26.9565 | 155 | 1.1031 |
|
| 83 |
+
| 1.0495 | 28.0 | 161 | 1.0993 |
|
| 84 |
+
| 1.0126 | 28.8696 | 166 | 1.0966 |
|
| 85 |
+
| 0.9884 | 29.9130 | 172 | 1.0938 |
|
| 86 |
+
| 1.0366 | 30.9565 | 178 | 1.0909 |
|
| 87 |
+
| 1.0434 | 32.0 | 184 | 1.0886 |
|
| 88 |
+
| 1.0222 | 32.8696 | 189 | 1.0862 |
|
| 89 |
+
| 0.9978 | 33.9130 | 195 | 1.0842 |
|
| 90 |
+
| 0.9593 | 34.9565 | 201 | 1.0824 |
|
| 91 |
+
| 1.0383 | 36.0 | 207 | 1.0804 |
|
| 92 |
+
| 0.9958 | 36.8696 | 212 | 1.0792 |
|
| 93 |
+
| 0.9774 | 37.9130 | 218 | 1.0778 |
|
| 94 |
+
| 0.9853 | 38.9565 | 224 | 1.0763 |
|
| 95 |
+
| 0.9241 | 40.0 | 230 | 1.0747 |
|
| 96 |
+
| 1.0387 | 40.8696 | 235 | 1.0743 |
|
| 97 |
+
| 0.9616 | 41.9130 | 241 | 1.0733 |
|
| 98 |
+
| 0.9909 | 42.9565 | 247 | 1.0724 |
|
| 99 |
+
| 0.9055 | 44.0 | 253 | 1.0720 |
|
| 100 |
+
| 1.0025 | 44.8696 | 258 | 1.0722 |
|
| 101 |
+
| 0.9325 | 45.9130 | 264 | 1.0711 |
|
| 102 |
+
| 0.8921 | 46.9565 | 270 | 1.0723 |
|
| 103 |
+
| 0.9079 | 48.0 | 276 | 1.0710 |
|
| 104 |
+
| 0.9615 | 48.8696 | 281 | 1.0729 |
|
| 105 |
+
| 0.9517 | 49.9130 | 287 | 1.0718 |
|
| 106 |
+
| 0.8619 | 50.9565 | 293 | 1.0730 |
|
| 107 |
+
| 0.8894 | 52.0 | 299 | 1.0739 |
|
| 108 |
+
| 0.8389 | 52.8696 | 304 | 1.0742 |
|
| 109 |
+
| 0.9032 | 53.9130 | 310 | 1.0750 |
|
| 110 |
+
| 0.9015 | 54.9565 | 316 | 1.0760 |
|
| 111 |
+
|
| 112 |
+
|
| 113 |
+
### Framework versions
|
| 114 |
+
|
| 115 |
+
- PEFT 0.12.0
|
| 116 |
+
- Transformers 4.44.0
|
| 117 |
+
- Pytorch 2.1.2+cu121
|
| 118 |
+
- Datasets 2.20.0
|
| 119 |
+
- Tokenizers 0.19.1
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 167832240
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca0c7976f93db32a2e144301314f86633543b33b420bdf909a2e692fc3b6d9f8
|
| 3 |
size 167832240
|
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 54.95652173913044,
|
| 3 |
+
"total_flos": 2.4451647665917133e+17,
|
| 4 |
+
"train_loss": 1.137867835975146,
|
| 5 |
+
"train_runtime": 8799.2233,
|
| 6 |
+
"train_samples": 46,
|
| 7 |
+
"train_samples_per_second": 0.784,
|
| 8 |
+
"train_steps_per_second": 0.085
|
| 9 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 54.95652173913044,
|
| 3 |
+
"total_flos": 2.4451647665917133e+17,
|
| 4 |
+
"train_loss": 1.137867835975146,
|
| 5 |
+
"train_runtime": 8799.2233,
|
| 6 |
+
"train_samples": 46,
|
| 7 |
+
"train_samples_per_second": 0.784,
|
| 8 |
+
"train_steps_per_second": 0.085
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1604 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.0710123777389526,
|
| 3 |
+
"best_model_checkpoint": "data/Llama-31-8B_task-2_60-samples_config-3_full/checkpoint-276",
|
| 4 |
+
"epoch": 54.95652173913044,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 316,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.17391304347826086,
|
| 13 |
+
"grad_norm": 0.5168920755386353,
|
| 14 |
+
"learning_rate": 1.3333333333333336e-07,
|
| 15 |
+
"loss": 1.5956,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.34782608695652173,
|
| 20 |
+
"grad_norm": 0.5719501376152039,
|
| 21 |
+
"learning_rate": 2.666666666666667e-07,
|
| 22 |
+
"loss": 1.6046,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.6956521739130435,
|
| 27 |
+
"grad_norm": 0.4981832504272461,
|
| 28 |
+
"learning_rate": 5.333333333333335e-07,
|
| 29 |
+
"loss": 1.5659,
|
| 30 |
+
"step": 4
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.8695652173913043,
|
| 34 |
+
"eval_loss": 1.5845621824264526,
|
| 35 |
+
"eval_runtime": 12.9809,
|
| 36 |
+
"eval_samples_per_second": 0.924,
|
| 37 |
+
"eval_steps_per_second": 0.924,
|
| 38 |
+
"step": 5
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 1.0434782608695652,
|
| 42 |
+
"grad_norm": 0.4701167941093445,
|
| 43 |
+
"learning_rate": 8.000000000000001e-07,
|
| 44 |
+
"loss": 1.5639,
|
| 45 |
+
"step": 6
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 1.391304347826087,
|
| 49 |
+
"grad_norm": 0.5071099996566772,
|
| 50 |
+
"learning_rate": 1.066666666666667e-06,
|
| 51 |
+
"loss": 1.5807,
|
| 52 |
+
"step": 8
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 1.7391304347826086,
|
| 56 |
+
"grad_norm": 0.5001740455627441,
|
| 57 |
+
"learning_rate": 1.3333333333333334e-06,
|
| 58 |
+
"loss": 1.5947,
|
| 59 |
+
"step": 10
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 1.9130434782608696,
|
| 63 |
+
"eval_loss": 1.581119179725647,
|
| 64 |
+
"eval_runtime": 12.9812,
|
| 65 |
+
"eval_samples_per_second": 0.924,
|
| 66 |
+
"eval_steps_per_second": 0.924,
|
| 67 |
+
"step": 11
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 2.0869565217391304,
|
| 71 |
+
"grad_norm": 0.5267815589904785,
|
| 72 |
+
"learning_rate": 1.6000000000000001e-06,
|
| 73 |
+
"loss": 1.589,
|
| 74 |
+
"step": 12
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 2.4347826086956523,
|
| 78 |
+
"grad_norm": 0.49407559633255005,
|
| 79 |
+
"learning_rate": 1.8666666666666669e-06,
|
| 80 |
+
"loss": 1.5287,
|
| 81 |
+
"step": 14
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 2.782608695652174,
|
| 85 |
+
"grad_norm": 0.45030105113983154,
|
| 86 |
+
"learning_rate": 2.133333333333334e-06,
|
| 87 |
+
"loss": 1.6305,
|
| 88 |
+
"step": 16
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 2.9565217391304346,
|
| 92 |
+
"eval_loss": 1.5758260488510132,
|
| 93 |
+
"eval_runtime": 12.9766,
|
| 94 |
+
"eval_samples_per_second": 0.925,
|
| 95 |
+
"eval_steps_per_second": 0.925,
|
| 96 |
+
"step": 17
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 3.130434782608696,
|
| 100 |
+
"grad_norm": 0.4595053493976593,
|
| 101 |
+
"learning_rate": 2.4000000000000003e-06,
|
| 102 |
+
"loss": 1.5404,
|
| 103 |
+
"step": 18
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 3.4782608695652173,
|
| 107 |
+
"grad_norm": 0.519245982170105,
|
| 108 |
+
"learning_rate": 2.666666666666667e-06,
|
| 109 |
+
"loss": 1.5737,
|
| 110 |
+
"step": 20
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 3.8260869565217392,
|
| 114 |
+
"grad_norm": 0.4773900508880615,
|
| 115 |
+
"learning_rate": 2.9333333333333338e-06,
|
| 116 |
+
"loss": 1.5682,
|
| 117 |
+
"step": 22
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 4.0,
|
| 121 |
+
"eval_loss": 1.5672565698623657,
|
| 122 |
+
"eval_runtime": 12.9785,
|
| 123 |
+
"eval_samples_per_second": 0.925,
|
| 124 |
+
"eval_steps_per_second": 0.925,
|
| 125 |
+
"step": 23
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 4.173913043478261,
|
| 129 |
+
"grad_norm": 0.4907453954219818,
|
| 130 |
+
"learning_rate": 3.2000000000000003e-06,
|
| 131 |
+
"loss": 1.5736,
|
| 132 |
+
"step": 24
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 4.521739130434782,
|
| 136 |
+
"grad_norm": 0.4995110332965851,
|
| 137 |
+
"learning_rate": 3.4666666666666672e-06,
|
| 138 |
+
"loss": 1.548,
|
| 139 |
+
"step": 26
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 4.869565217391305,
|
| 143 |
+
"grad_norm": 0.48306918144226074,
|
| 144 |
+
"learning_rate": 3.7333333333333337e-06,
|
| 145 |
+
"loss": 1.5687,
|
| 146 |
+
"step": 28
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 4.869565217391305,
|
| 150 |
+
"eval_loss": 1.5570815801620483,
|
| 151 |
+
"eval_runtime": 12.977,
|
| 152 |
+
"eval_samples_per_second": 0.925,
|
| 153 |
+
"eval_steps_per_second": 0.925,
|
| 154 |
+
"step": 28
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 5.217391304347826,
|
| 158 |
+
"grad_norm": 0.5053550601005554,
|
| 159 |
+
"learning_rate": 4.000000000000001e-06,
|
| 160 |
+
"loss": 1.5427,
|
| 161 |
+
"step": 30
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 5.565217391304348,
|
| 165 |
+
"grad_norm": 0.5055222511291504,
|
| 166 |
+
"learning_rate": 4.266666666666668e-06,
|
| 167 |
+
"loss": 1.5277,
|
| 168 |
+
"step": 32
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 5.913043478260869,
|
| 172 |
+
"grad_norm": 0.45084983110427856,
|
| 173 |
+
"learning_rate": 4.533333333333334e-06,
|
| 174 |
+
"loss": 1.5556,
|
| 175 |
+
"step": 34
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"epoch": 5.913043478260869,
|
| 179 |
+
"eval_loss": 1.5406227111816406,
|
| 180 |
+
"eval_runtime": 12.9754,
|
| 181 |
+
"eval_samples_per_second": 0.925,
|
| 182 |
+
"eval_steps_per_second": 0.925,
|
| 183 |
+
"step": 34
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 6.260869565217392,
|
| 187 |
+
"grad_norm": 0.5172422528266907,
|
| 188 |
+
"learning_rate": 4.800000000000001e-06,
|
| 189 |
+
"loss": 1.5111,
|
| 190 |
+
"step": 36
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 6.608695652173913,
|
| 194 |
+
"grad_norm": 0.571245551109314,
|
| 195 |
+
"learning_rate": 5.0666666666666676e-06,
|
| 196 |
+
"loss": 1.5721,
|
| 197 |
+
"step": 38
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 6.956521739130435,
|
| 201 |
+
"grad_norm": 0.46223798394203186,
|
| 202 |
+
"learning_rate": 5.333333333333334e-06,
|
| 203 |
+
"loss": 1.4699,
|
| 204 |
+
"step": 40
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 6.956521739130435,
|
| 208 |
+
"eval_loss": 1.5189919471740723,
|
| 209 |
+
"eval_runtime": 12.9806,
|
| 210 |
+
"eval_samples_per_second": 0.924,
|
| 211 |
+
"eval_steps_per_second": 0.924,
|
| 212 |
+
"step": 40
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 7.304347826086957,
|
| 216 |
+
"grad_norm": 0.44059333205223083,
|
| 217 |
+
"learning_rate": 5.600000000000001e-06,
|
| 218 |
+
"loss": 1.5389,
|
| 219 |
+
"step": 42
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 7.6521739130434785,
|
| 223 |
+
"grad_norm": 0.39538195729255676,
|
| 224 |
+
"learning_rate": 5.8666666666666675e-06,
|
| 225 |
+
"loss": 1.4685,
|
| 226 |
+
"step": 44
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 8.0,
|
| 230 |
+
"grad_norm": 0.44168609380722046,
|
| 231 |
+
"learning_rate": 6.133333333333334e-06,
|
| 232 |
+
"loss": 1.5027,
|
| 233 |
+
"step": 46
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 8.0,
|
| 237 |
+
"eval_loss": 1.4957526922225952,
|
| 238 |
+
"eval_runtime": 12.982,
|
| 239 |
+
"eval_samples_per_second": 0.924,
|
| 240 |
+
"eval_steps_per_second": 0.924,
|
| 241 |
+
"step": 46
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 8.347826086956522,
|
| 245 |
+
"grad_norm": 0.4372757375240326,
|
| 246 |
+
"learning_rate": 6.4000000000000006e-06,
|
| 247 |
+
"loss": 1.4465,
|
| 248 |
+
"step": 48
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 8.695652173913043,
|
| 252 |
+
"grad_norm": 0.4501511752605438,
|
| 253 |
+
"learning_rate": 6.666666666666667e-06,
|
| 254 |
+
"loss": 1.5203,
|
| 255 |
+
"step": 50
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 8.869565217391305,
|
| 259 |
+
"eval_loss": 1.4718750715255737,
|
| 260 |
+
"eval_runtime": 12.9768,
|
| 261 |
+
"eval_samples_per_second": 0.925,
|
| 262 |
+
"eval_steps_per_second": 0.925,
|
| 263 |
+
"step": 51
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 9.043478260869565,
|
| 267 |
+
"grad_norm": 0.38575872778892517,
|
| 268 |
+
"learning_rate": 6.9333333333333344e-06,
|
| 269 |
+
"loss": 1.4364,
|
| 270 |
+
"step": 52
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 9.391304347826088,
|
| 274 |
+
"grad_norm": 0.3618987798690796,
|
| 275 |
+
"learning_rate": 7.2000000000000005e-06,
|
| 276 |
+
"loss": 1.4197,
|
| 277 |
+
"step": 54
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 9.73913043478261,
|
| 281 |
+
"grad_norm": 0.3317548930644989,
|
| 282 |
+
"learning_rate": 7.4666666666666675e-06,
|
| 283 |
+
"loss": 1.4872,
|
| 284 |
+
"step": 56
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 9.91304347826087,
|
| 288 |
+
"eval_loss": 1.4444891214370728,
|
| 289 |
+
"eval_runtime": 12.9775,
|
| 290 |
+
"eval_samples_per_second": 0.925,
|
| 291 |
+
"eval_steps_per_second": 0.925,
|
| 292 |
+
"step": 57
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 10.08695652173913,
|
| 296 |
+
"grad_norm": 0.3010832369327545,
|
| 297 |
+
"learning_rate": 7.733333333333334e-06,
|
| 298 |
+
"loss": 1.4324,
|
| 299 |
+
"step": 58
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 10.434782608695652,
|
| 303 |
+
"grad_norm": 0.32329097390174866,
|
| 304 |
+
"learning_rate": 8.000000000000001e-06,
|
| 305 |
+
"loss": 1.4333,
|
| 306 |
+
"step": 60
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 10.782608695652174,
|
| 310 |
+
"grad_norm": 0.3354980945587158,
|
| 311 |
+
"learning_rate": 8.266666666666667e-06,
|
| 312 |
+
"loss": 1.4184,
|
| 313 |
+
"step": 62
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 10.956521739130435,
|
| 317 |
+
"eval_loss": 1.4150630235671997,
|
| 318 |
+
"eval_runtime": 12.9754,
|
| 319 |
+
"eval_samples_per_second": 0.925,
|
| 320 |
+
"eval_steps_per_second": 0.925,
|
| 321 |
+
"step": 63
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 11.130434782608695,
|
| 325 |
+
"grad_norm": 0.33713477849960327,
|
| 326 |
+
"learning_rate": 8.533333333333335e-06,
|
| 327 |
+
"loss": 1.3763,
|
| 328 |
+
"step": 64
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 11.478260869565217,
|
| 332 |
+
"grad_norm": 0.23276787996292114,
|
| 333 |
+
"learning_rate": 8.8e-06,
|
| 334 |
+
"loss": 1.3969,
|
| 335 |
+
"step": 66
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 11.826086956521738,
|
| 339 |
+
"grad_norm": 0.2602153718471527,
|
| 340 |
+
"learning_rate": 9.066666666666667e-06,
|
| 341 |
+
"loss": 1.3817,
|
| 342 |
+
"step": 68
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 12.0,
|
| 346 |
+
"eval_loss": 1.386828064918518,
|
| 347 |
+
"eval_runtime": 12.979,
|
| 348 |
+
"eval_samples_per_second": 0.925,
|
| 349 |
+
"eval_steps_per_second": 0.925,
|
| 350 |
+
"step": 69
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 12.173913043478262,
|
| 354 |
+
"grad_norm": 0.2566069960594177,
|
| 355 |
+
"learning_rate": 9.333333333333334e-06,
|
| 356 |
+
"loss": 1.3523,
|
| 357 |
+
"step": 70
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 12.521739130434783,
|
| 361 |
+
"grad_norm": 0.2781592607498169,
|
| 362 |
+
"learning_rate": 9.600000000000001e-06,
|
| 363 |
+
"loss": 1.3737,
|
| 364 |
+
"step": 72
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 12.869565217391305,
|
| 368 |
+
"grad_norm": 0.2503822147846222,
|
| 369 |
+
"learning_rate": 9.866666666666668e-06,
|
| 370 |
+
"loss": 1.3397,
|
| 371 |
+
"step": 74
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 12.869565217391305,
|
| 375 |
+
"eval_loss": 1.3647750616073608,
|
| 376 |
+
"eval_runtime": 12.9767,
|
| 377 |
+
"eval_samples_per_second": 0.925,
|
| 378 |
+
"eval_steps_per_second": 0.925,
|
| 379 |
+
"step": 74
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 13.217391304347826,
|
| 383 |
+
"grad_norm": 0.269147664308548,
|
| 384 |
+
"learning_rate": 9.999945845889795e-06,
|
| 385 |
+
"loss": 1.3282,
|
| 386 |
+
"step": 76
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 13.565217391304348,
|
| 390 |
+
"grad_norm": 0.25336846709251404,
|
| 391 |
+
"learning_rate": 9.999512620046523e-06,
|
| 392 |
+
"loss": 1.3328,
|
| 393 |
+
"step": 78
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 13.91304347826087,
|
| 397 |
+
"grad_norm": 0.24610716104507446,
|
| 398 |
+
"learning_rate": 9.99864620589731e-06,
|
| 399 |
+
"loss": 1.3234,
|
| 400 |
+
"step": 80
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 13.91304347826087,
|
| 404 |
+
"eval_loss": 1.3389836549758911,
|
| 405 |
+
"eval_runtime": 12.9781,
|
| 406 |
+
"eval_samples_per_second": 0.925,
|
| 407 |
+
"eval_steps_per_second": 0.925,
|
| 408 |
+
"step": 80
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 14.26086956521739,
|
| 412 |
+
"grad_norm": 0.23158159852027893,
|
| 413 |
+
"learning_rate": 9.99734667851357e-06,
|
| 414 |
+
"loss": 1.2771,
|
| 415 |
+
"step": 82
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 14.608695652173914,
|
| 419 |
+
"grad_norm": 0.2516274154186249,
|
| 420 |
+
"learning_rate": 9.995614150494293e-06,
|
| 421 |
+
"loss": 1.3073,
|
| 422 |
+
"step": 84
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 14.956521739130435,
|
| 426 |
+
"grad_norm": 0.28719547390937805,
|
| 427 |
+
"learning_rate": 9.993448771956285e-06,
|
| 428 |
+
"loss": 1.2893,
|
| 429 |
+
"step": 86
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 14.956521739130435,
|
| 433 |
+
"eval_loss": 1.3121906518936157,
|
| 434 |
+
"eval_runtime": 12.9801,
|
| 435 |
+
"eval_samples_per_second": 0.924,
|
| 436 |
+
"eval_steps_per_second": 0.924,
|
| 437 |
+
"step": 86
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 15.304347826086957,
|
| 441 |
+
"grad_norm": 0.2287660539150238,
|
| 442 |
+
"learning_rate": 9.99085073052117e-06,
|
| 443 |
+
"loss": 1.2679,
|
| 444 |
+
"step": 88
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 15.652173913043478,
|
| 448 |
+
"grad_norm": 0.29683366417884827,
|
| 449 |
+
"learning_rate": 9.987820251299121e-06,
|
| 450 |
+
"loss": 1.2504,
|
| 451 |
+
"step": 90
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 16.0,
|
| 455 |
+
"grad_norm": 0.20408132672309875,
|
| 456 |
+
"learning_rate": 9.984357596869369e-06,
|
| 457 |
+
"loss": 1.2999,
|
| 458 |
+
"step": 92
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 16.0,
|
| 462 |
+
"eval_loss": 1.2852083444595337,
|
| 463 |
+
"eval_runtime": 12.9826,
|
| 464 |
+
"eval_samples_per_second": 0.924,
|
| 465 |
+
"eval_steps_per_second": 0.924,
|
| 466 |
+
"step": 92
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 16.347826086956523,
|
| 470 |
+
"grad_norm": 0.2704583406448364,
|
| 471 |
+
"learning_rate": 9.980463067257437e-06,
|
| 472 |
+
"loss": 1.2504,
|
| 473 |
+
"step": 94
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 16.695652173913043,
|
| 477 |
+
"grad_norm": 0.2368343323469162,
|
| 478 |
+
"learning_rate": 9.976136999909156e-06,
|
| 479 |
+
"loss": 1.2212,
|
| 480 |
+
"step": 96
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 16.869565217391305,
|
| 484 |
+
"eval_loss": 1.2628425359725952,
|
| 485 |
+
"eval_runtime": 12.9802,
|
| 486 |
+
"eval_samples_per_second": 0.924,
|
| 487 |
+
"eval_steps_per_second": 0.924,
|
| 488 |
+
"step": 97
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 17.043478260869566,
|
| 492 |
+
"grad_norm": 0.22224029898643494,
|
| 493 |
+
"learning_rate": 9.971379769661422e-06,
|
| 494 |
+
"loss": 1.2242,
|
| 495 |
+
"step": 98
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 17.391304347826086,
|
| 499 |
+
"grad_norm": 0.2928115725517273,
|
| 500 |
+
"learning_rate": 9.966191788709716e-06,
|
| 501 |
+
"loss": 1.2211,
|
| 502 |
+
"step": 100
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 17.73913043478261,
|
| 506 |
+
"grad_norm": 0.22390316426753998,
|
| 507 |
+
"learning_rate": 9.960573506572391e-06,
|
| 508 |
+
"loss": 1.234,
|
| 509 |
+
"step": 102
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 17.91304347826087,
|
| 513 |
+
"eval_loss": 1.2357784509658813,
|
| 514 |
+
"eval_runtime": 12.9749,
|
| 515 |
+
"eval_samples_per_second": 0.925,
|
| 516 |
+
"eval_steps_per_second": 0.925,
|
| 517 |
+
"step": 103
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"epoch": 18.08695652173913,
|
| 521 |
+
"grad_norm": 0.25287434458732605,
|
| 522 |
+
"learning_rate": 9.95452541005172e-06,
|
| 523 |
+
"loss": 1.1594,
|
| 524 |
+
"step": 104
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 18.434782608695652,
|
| 528 |
+
"grad_norm": 0.22554974257946014,
|
| 529 |
+
"learning_rate": 9.948048023191728e-06,
|
| 530 |
+
"loss": 1.1941,
|
| 531 |
+
"step": 106
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 18.782608695652176,
|
| 535 |
+
"grad_norm": 0.28337913751602173,
|
| 536 |
+
"learning_rate": 9.941141907232766e-06,
|
| 537 |
+
"loss": 1.1704,
|
| 538 |
+
"step": 108
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 18.956521739130434,
|
| 542 |
+
"eval_loss": 1.2077757120132446,
|
| 543 |
+
"eval_runtime": 12.9864,
|
| 544 |
+
"eval_samples_per_second": 0.924,
|
| 545 |
+
"eval_steps_per_second": 0.924,
|
| 546 |
+
"step": 109
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 19.130434782608695,
|
| 550 |
+
"grad_norm": 0.2129991501569748,
|
| 551 |
+
"learning_rate": 9.933807660562898e-06,
|
| 552 |
+
"loss": 1.1575,
|
| 553 |
+
"step": 110
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 19.47826086956522,
|
| 557 |
+
"grad_norm": 0.3318869471549988,
|
| 558 |
+
"learning_rate": 9.926045918666045e-06,
|
| 559 |
+
"loss": 1.1555,
|
| 560 |
+
"step": 112
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 19.82608695652174,
|
| 564 |
+
"grad_norm": 0.3031323552131653,
|
| 565 |
+
"learning_rate": 9.91785735406693e-06,
|
| 566 |
+
"loss": 1.1499,
|
| 567 |
+
"step": 114
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 20.0,
|
| 571 |
+
"eval_loss": 1.1795598268508911,
|
| 572 |
+
"eval_runtime": 12.9743,
|
| 573 |
+
"eval_samples_per_second": 0.925,
|
| 574 |
+
"eval_steps_per_second": 0.925,
|
| 575 |
+
"step": 115
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 20.17391304347826,
|
| 579 |
+
"grad_norm": 0.2700609862804413,
|
| 580 |
+
"learning_rate": 9.909242676272797e-06,
|
| 581 |
+
"loss": 1.1176,
|
| 582 |
+
"step": 116
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 20.52173913043478,
|
| 586 |
+
"grad_norm": 0.24468179047107697,
|
| 587 |
+
"learning_rate": 9.90020263171194e-06,
|
| 588 |
+
"loss": 1.1005,
|
| 589 |
+
"step": 118
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 20.869565217391305,
|
| 593 |
+
"grad_norm": 0.2991030216217041,
|
| 594 |
+
"learning_rate": 9.890738003669029e-06,
|
| 595 |
+
"loss": 1.1265,
|
| 596 |
+
"step": 120
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 20.869565217391305,
|
| 600 |
+
"eval_loss": 1.1569637060165405,
|
| 601 |
+
"eval_runtime": 12.9777,
|
| 602 |
+
"eval_samples_per_second": 0.925,
|
| 603 |
+
"eval_steps_per_second": 0.925,
|
| 604 |
+
"step": 120
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 21.217391304347824,
|
| 608 |
+
"grad_norm": 0.2351488173007965,
|
| 609 |
+
"learning_rate": 9.880849612217238e-06,
|
| 610 |
+
"loss": 1.1073,
|
| 611 |
+
"step": 122
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 21.565217391304348,
|
| 615 |
+
"grad_norm": 0.26138749718666077,
|
| 616 |
+
"learning_rate": 9.870538314147194e-06,
|
| 617 |
+
"loss": 1.0675,
|
| 618 |
+
"step": 124
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 21.91304347826087,
|
| 622 |
+
"grad_norm": 0.2605469226837158,
|
| 623 |
+
"learning_rate": 9.859805002892733e-06,
|
| 624 |
+
"loss": 1.0716,
|
| 625 |
+
"step": 126
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 21.91304347826087,
|
| 629 |
+
"eval_loss": 1.1357496976852417,
|
| 630 |
+
"eval_runtime": 12.9785,
|
| 631 |
+
"eval_samples_per_second": 0.925,
|
| 632 |
+
"eval_steps_per_second": 0.925,
|
| 633 |
+
"step": 126
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 22.26086956521739,
|
| 637 |
+
"grad_norm": 0.2572947144508362,
|
| 638 |
+
"learning_rate": 9.84865060845349e-06,
|
| 639 |
+
"loss": 1.0791,
|
| 640 |
+
"step": 128
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 22.608695652173914,
|
| 644 |
+
"grad_norm": 0.2186698317527771,
|
| 645 |
+
"learning_rate": 9.83707609731432e-06,
|
| 646 |
+
"loss": 1.0729,
|
| 647 |
+
"step": 130
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 22.956521739130434,
|
| 651 |
+
"grad_norm": 0.3026718199253082,
|
| 652 |
+
"learning_rate": 9.825082472361558e-06,
|
| 653 |
+
"loss": 1.0332,
|
| 654 |
+
"step": 132
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 22.956521739130434,
|
| 658 |
+
"eval_loss": 1.122292160987854,
|
| 659 |
+
"eval_runtime": 12.9802,
|
| 660 |
+
"eval_samples_per_second": 0.924,
|
| 661 |
+
"eval_steps_per_second": 0.924,
|
| 662 |
+
"step": 132
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 23.304347826086957,
|
| 666 |
+
"grad_norm": 0.21330009400844574,
|
| 667 |
+
"learning_rate": 9.812670772796113e-06,
|
| 668 |
+
"loss": 1.0612,
|
| 669 |
+
"step": 134
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 23.652173913043477,
|
| 673 |
+
"grad_norm": 0.17287513613700867,
|
| 674 |
+
"learning_rate": 9.799842074043438e-06,
|
| 675 |
+
"loss": 1.05,
|
| 676 |
+
"step": 136
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 24.0,
|
| 680 |
+
"grad_norm": 0.17213226854801178,
|
| 681 |
+
"learning_rate": 9.786597487660336e-06,
|
| 682 |
+
"loss": 1.0631,
|
| 683 |
+
"step": 138
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 24.0,
|
| 687 |
+
"eval_loss": 1.1154590845108032,
|
| 688 |
+
"eval_runtime": 12.9794,
|
| 689 |
+
"eval_samples_per_second": 0.925,
|
| 690 |
+
"eval_steps_per_second": 0.925,
|
| 691 |
+
"step": 138
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 24.347826086956523,
|
| 695 |
+
"grad_norm": 0.17510361969470978,
|
| 696 |
+
"learning_rate": 9.77293816123866e-06,
|
| 697 |
+
"loss": 1.0322,
|
| 698 |
+
"step": 140
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 24.695652173913043,
|
| 702 |
+
"grad_norm": 0.16553597152233124,
|
| 703 |
+
"learning_rate": 9.75886527830587e-06,
|
| 704 |
+
"loss": 1.0659,
|
| 705 |
+
"step": 142
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 24.869565217391305,
|
| 709 |
+
"eval_loss": 1.1110743284225464,
|
| 710 |
+
"eval_runtime": 12.9742,
|
| 711 |
+
"eval_samples_per_second": 0.925,
|
| 712 |
+
"eval_steps_per_second": 0.925,
|
| 713 |
+
"step": 143
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 25.043478260869566,
|
| 717 |
+
"grad_norm": 0.17666411399841309,
|
| 718 |
+
"learning_rate": 9.744380058222483e-06,
|
| 719 |
+
"loss": 1.0226,
|
| 720 |
+
"step": 144
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 25.391304347826086,
|
| 724 |
+
"grad_norm": 0.1684177666902542,
|
| 725 |
+
"learning_rate": 9.729483756076436e-06,
|
| 726 |
+
"loss": 1.0355,
|
| 727 |
+
"step": 146
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 25.73913043478261,
|
| 731 |
+
"grad_norm": 0.18400514125823975,
|
| 732 |
+
"learning_rate": 9.714177662574316e-06,
|
| 733 |
+
"loss": 1.0637,
|
| 734 |
+
"step": 148
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 25.91304347826087,
|
| 738 |
+
"eval_loss": 1.1067678928375244,
|
| 739 |
+
"eval_runtime": 12.9821,
|
| 740 |
+
"eval_samples_per_second": 0.924,
|
| 741 |
+
"eval_steps_per_second": 0.924,
|
| 742 |
+
"step": 149
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 26.08695652173913,
|
| 746 |
+
"grad_norm": 0.16044579446315765,
|
| 747 |
+
"learning_rate": 9.698463103929542e-06,
|
| 748 |
+
"loss": 1.0691,
|
| 749 |
+
"step": 150
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 26.434782608695652,
|
| 753 |
+
"grad_norm": 0.17162466049194336,
|
| 754 |
+
"learning_rate": 9.682341441747446e-06,
|
| 755 |
+
"loss": 1.0148,
|
| 756 |
+
"step": 152
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 26.782608695652176,
|
| 760 |
+
"grad_norm": 0.16096869111061096,
|
| 761 |
+
"learning_rate": 9.665814072907293e-06,
|
| 762 |
+
"loss": 0.9979,
|
| 763 |
+
"step": 154
|
| 764 |
+
},
|
| 765 |
+
{
|
| 766 |
+
"epoch": 26.956521739130434,
|
| 767 |
+
"eval_loss": 1.1030863523483276,
|
| 768 |
+
"eval_runtime": 12.9795,
|
| 769 |
+
"eval_samples_per_second": 0.925,
|
| 770 |
+
"eval_steps_per_second": 0.925,
|
| 771 |
+
"step": 155
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 27.130434782608695,
|
| 775 |
+
"grad_norm": 0.15515439212322235,
|
| 776 |
+
"learning_rate": 9.648882429441258e-06,
|
| 777 |
+
"loss": 1.0792,
|
| 778 |
+
"step": 156
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"epoch": 27.47826086956522,
|
| 782 |
+
"grad_norm": 0.21910764276981354,
|
| 783 |
+
"learning_rate": 9.63154797841033e-06,
|
| 784 |
+
"loss": 0.9741,
|
| 785 |
+
"step": 158
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 27.82608695652174,
|
| 789 |
+
"grad_norm": 0.15719705820083618,
|
| 790 |
+
"learning_rate": 9.613812221777212e-06,
|
| 791 |
+
"loss": 1.0495,
|
| 792 |
+
"step": 160
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"epoch": 28.0,
|
| 796 |
+
"eval_loss": 1.0992634296417236,
|
| 797 |
+
"eval_runtime": 12.9823,
|
| 798 |
+
"eval_samples_per_second": 0.924,
|
| 799 |
+
"eval_steps_per_second": 0.924,
|
| 800 |
+
"step": 161
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 28.17391304347826,
|
| 804 |
+
"grad_norm": 0.17963844537734985,
|
| 805 |
+
"learning_rate": 9.595676696276173e-06,
|
| 806 |
+
"loss": 0.956,
|
| 807 |
+
"step": 162
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 28.52173913043478,
|
| 811 |
+
"grad_norm": 0.1683446168899536,
|
| 812 |
+
"learning_rate": 9.577142973279896e-06,
|
| 813 |
+
"loss": 1.0629,
|
| 814 |
+
"step": 164
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 28.869565217391305,
|
| 818 |
+
"grad_norm": 0.18944136798381805,
|
| 819 |
+
"learning_rate": 9.55821265866333e-06,
|
| 820 |
+
"loss": 1.0126,
|
| 821 |
+
"step": 166
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 28.869565217391305,
|
| 825 |
+
"eval_loss": 1.096557378768921,
|
| 826 |
+
"eval_runtime": 12.9756,
|
| 827 |
+
"eval_samples_per_second": 0.925,
|
| 828 |
+
"eval_steps_per_second": 0.925,
|
| 829 |
+
"step": 166
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 29.217391304347824,
|
| 833 |
+
"grad_norm": 0.17034175992012024,
|
| 834 |
+
"learning_rate": 9.538887392664544e-06,
|
| 835 |
+
"loss": 1.0652,
|
| 836 |
+
"step": 168
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 29.565217391304348,
|
| 840 |
+
"grad_norm": 0.17872415482997894,
|
| 841 |
+
"learning_rate": 9.519168849742603e-06,
|
| 842 |
+
"loss": 0.9865,
|
| 843 |
+
"step": 170
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 29.91304347826087,
|
| 847 |
+
"grad_norm": 0.17247214913368225,
|
| 848 |
+
"learning_rate": 9.499058738432492e-06,
|
| 849 |
+
"loss": 0.9884,
|
| 850 |
+
"step": 172
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 29.91304347826087,
|
| 854 |
+
"eval_loss": 1.0938386917114258,
|
| 855 |
+
"eval_runtime": 12.9748,
|
| 856 |
+
"eval_samples_per_second": 0.925,
|
| 857 |
+
"eval_steps_per_second": 0.925,
|
| 858 |
+
"step": 172
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 30.26086956521739,
|
| 862 |
+
"grad_norm": 0.18095757067203522,
|
| 863 |
+
"learning_rate": 9.478558801197065e-06,
|
| 864 |
+
"loss": 1.026,
|
| 865 |
+
"step": 174
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 30.608695652173914,
|
| 869 |
+
"grad_norm": 0.17440937459468842,
|
| 870 |
+
"learning_rate": 9.457670814276083e-06,
|
| 871 |
+
"loss": 1.007,
|
| 872 |
+
"step": 176
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 30.956521739130434,
|
| 876 |
+
"grad_norm": 0.17576059699058533,
|
| 877 |
+
"learning_rate": 9.436396587532297e-06,
|
| 878 |
+
"loss": 1.0366,
|
| 879 |
+
"step": 178
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 30.956521739130434,
|
| 883 |
+
"eval_loss": 1.0909334421157837,
|
| 884 |
+
"eval_runtime": 12.9767,
|
| 885 |
+
"eval_samples_per_second": 0.925,
|
| 886 |
+
"eval_steps_per_second": 0.925,
|
| 887 |
+
"step": 178
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 31.304347826086957,
|
| 891 |
+
"grad_norm": 0.18143777549266815,
|
| 892 |
+
"learning_rate": 9.414737964294636e-06,
|
| 893 |
+
"loss": 0.9512,
|
| 894 |
+
"step": 180
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 31.652173913043477,
|
| 898 |
+
"grad_norm": 0.1847611963748932,
|
| 899 |
+
"learning_rate": 9.392696821198488e-06,
|
| 900 |
+
"loss": 1.0277,
|
| 901 |
+
"step": 182
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 32.0,
|
| 905 |
+
"grad_norm": 0.18112817406654358,
|
| 906 |
+
"learning_rate": 9.370275068023097e-06,
|
| 907 |
+
"loss": 1.0434,
|
| 908 |
+
"step": 184
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 32.0,
|
| 912 |
+
"eval_loss": 1.0885893106460571,
|
| 913 |
+
"eval_runtime": 12.9743,
|
| 914 |
+
"eval_samples_per_second": 0.925,
|
| 915 |
+
"eval_steps_per_second": 0.925,
|
| 916 |
+
"step": 184
|
| 917 |
+
},
|
| 918 |
+
{
|
| 919 |
+
"epoch": 32.34782608695652,
|
| 920 |
+
"grad_norm": 0.2060151845216751,
|
| 921 |
+
"learning_rate": 9.347474647526095e-06,
|
| 922 |
+
"loss": 1.0112,
|
| 923 |
+
"step": 186
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 32.69565217391305,
|
| 927 |
+
"grad_norm": 0.18784299492835999,
|
| 928 |
+
"learning_rate": 9.324297535275156e-06,
|
| 929 |
+
"loss": 1.0222,
|
| 930 |
+
"step": 188
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 32.869565217391305,
|
| 934 |
+
"eval_loss": 1.086158037185669,
|
| 935 |
+
"eval_runtime": 12.9781,
|
| 936 |
+
"eval_samples_per_second": 0.925,
|
| 937 |
+
"eval_steps_per_second": 0.925,
|
| 938 |
+
"step": 189
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 33.04347826086956,
|
| 942 |
+
"grad_norm": 0.20884543657302856,
|
| 943 |
+
"learning_rate": 9.30074573947683e-06,
|
| 944 |
+
"loss": 0.9734,
|
| 945 |
+
"step": 190
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 33.391304347826086,
|
| 949 |
+
"grad_norm": 0.19983573257923126,
|
| 950 |
+
"learning_rate": 9.276821300802535e-06,
|
| 951 |
+
"loss": 0.9753,
|
| 952 |
+
"step": 192
|
| 953 |
+
},
|
| 954 |
+
{
|
| 955 |
+
"epoch": 33.73913043478261,
|
| 956 |
+
"grad_norm": 0.1889132559299469,
|
| 957 |
+
"learning_rate": 9.25252629221175e-06,
|
| 958 |
+
"loss": 0.9978,
|
| 959 |
+
"step": 194
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 33.91304347826087,
|
| 963 |
+
"eval_loss": 1.0842341184616089,
|
| 964 |
+
"eval_runtime": 12.9762,
|
| 965 |
+
"eval_samples_per_second": 0.925,
|
| 966 |
+
"eval_steps_per_second": 0.925,
|
| 967 |
+
"step": 195
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"epoch": 34.08695652173913,
|
| 971 |
+
"grad_norm": 0.1903546005487442,
|
| 972 |
+
"learning_rate": 9.227862818772392e-06,
|
| 973 |
+
"loss": 0.993,
|
| 974 |
+
"step": 196
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 34.43478260869565,
|
| 978 |
+
"grad_norm": 0.1973000466823578,
|
| 979 |
+
"learning_rate": 9.202833017478421e-06,
|
| 980 |
+
"loss": 0.9973,
|
| 981 |
+
"step": 198
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 34.78260869565217,
|
| 985 |
+
"grad_norm": 0.23764756321907043,
|
| 986 |
+
"learning_rate": 9.177439057064684e-06,
|
| 987 |
+
"loss": 0.9593,
|
| 988 |
+
"step": 200
|
| 989 |
+
},
|
| 990 |
+
{
|
| 991 |
+
"epoch": 34.95652173913044,
|
| 992 |
+
"eval_loss": 1.0823968648910522,
|
| 993 |
+
"eval_runtime": 12.9773,
|
| 994 |
+
"eval_samples_per_second": 0.925,
|
| 995 |
+
"eval_steps_per_second": 0.925,
|
| 996 |
+
"step": 201
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 35.130434782608695,
|
| 1000 |
+
"grad_norm": 0.1871621310710907,
|
| 1001 |
+
"learning_rate": 9.151683137818989e-06,
|
| 1002 |
+
"loss": 1.066,
|
| 1003 |
+
"step": 202
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 35.47826086956522,
|
| 1007 |
+
"grad_norm": 0.20576035976409912,
|
| 1008 |
+
"learning_rate": 9.125567491391476e-06,
|
| 1009 |
+
"loss": 0.9734,
|
| 1010 |
+
"step": 204
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 35.82608695652174,
|
| 1014 |
+
"grad_norm": 0.1983082890510559,
|
| 1015 |
+
"learning_rate": 9.099094380601244e-06,
|
| 1016 |
+
"loss": 1.0383,
|
| 1017 |
+
"step": 206
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 36.0,
|
| 1021 |
+
"eval_loss": 1.0803947448730469,
|
| 1022 |
+
"eval_runtime": 12.9755,
|
| 1023 |
+
"eval_samples_per_second": 0.925,
|
| 1024 |
+
"eval_steps_per_second": 0.925,
|
| 1025 |
+
"step": 207
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 36.17391304347826,
|
| 1029 |
+
"grad_norm": 0.18446066975593567,
|
| 1030 |
+
"learning_rate": 9.072266099240286e-06,
|
| 1031 |
+
"loss": 0.9198,
|
| 1032 |
+
"step": 208
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 36.52173913043478,
|
| 1036 |
+
"grad_norm": 0.20637229084968567,
|
| 1037 |
+
"learning_rate": 9.045084971874738e-06,
|
| 1038 |
+
"loss": 1.0071,
|
| 1039 |
+
"step": 210
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 36.869565217391305,
|
| 1043 |
+
"grad_norm": 0.21963337063789368,
|
| 1044 |
+
"learning_rate": 9.017553353643479e-06,
|
| 1045 |
+
"loss": 0.9958,
|
| 1046 |
+
"step": 212
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 36.869565217391305,
|
| 1050 |
+
"eval_loss": 1.0792189836502075,
|
| 1051 |
+
"eval_runtime": 12.9787,
|
| 1052 |
+
"eval_samples_per_second": 0.925,
|
| 1053 |
+
"eval_steps_per_second": 0.925,
|
| 1054 |
+
"step": 212
|
| 1055 |
+
},
|
| 1056 |
+
{
|
| 1057 |
+
"epoch": 37.21739130434783,
|
| 1058 |
+
"grad_norm": 0.2046482264995575,
|
| 1059 |
+
"learning_rate": 8.989673630054044e-06,
|
| 1060 |
+
"loss": 0.9336,
|
| 1061 |
+
"step": 214
|
| 1062 |
+
},
|
| 1063 |
+
{
|
| 1064 |
+
"epoch": 37.56521739130435,
|
| 1065 |
+
"grad_norm": 0.21577562391757965,
|
| 1066 |
+
"learning_rate": 8.961448216775955e-06,
|
| 1067 |
+
"loss": 1.01,
|
| 1068 |
+
"step": 216
|
| 1069 |
+
},
|
| 1070 |
+
{
|
| 1071 |
+
"epoch": 37.91304347826087,
|
| 1072 |
+
"grad_norm": 0.21256496012210846,
|
| 1073 |
+
"learning_rate": 8.932879559431392e-06,
|
| 1074 |
+
"loss": 0.9774,
|
| 1075 |
+
"step": 218
|
| 1076 |
+
},
|
| 1077 |
+
{
|
| 1078 |
+
"epoch": 37.91304347826087,
|
| 1079 |
+
"eval_loss": 1.0778032541275024,
|
| 1080 |
+
"eval_runtime": 12.9805,
|
| 1081 |
+
"eval_samples_per_second": 0.924,
|
| 1082 |
+
"eval_steps_per_second": 0.924,
|
| 1083 |
+
"step": 218
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 38.26086956521739,
|
| 1087 |
+
"grad_norm": 0.2028392106294632,
|
| 1088 |
+
"learning_rate": 8.903970133383297e-06,
|
| 1089 |
+
"loss": 0.9966,
|
| 1090 |
+
"step": 220
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"epoch": 38.608695652173914,
|
| 1094 |
+
"grad_norm": 0.22231891751289368,
|
| 1095 |
+
"learning_rate": 8.874722443520898e-06,
|
| 1096 |
+
"loss": 0.936,
|
| 1097 |
+
"step": 222
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 38.95652173913044,
|
| 1101 |
+
"grad_norm": 0.23805910348892212,
|
| 1102 |
+
"learning_rate": 8.845139024042664e-06,
|
| 1103 |
+
"loss": 0.9853,
|
| 1104 |
+
"step": 224
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 38.95652173913044,
|
| 1108 |
+
"eval_loss": 1.0763030052185059,
|
| 1109 |
+
"eval_runtime": 12.9799,
|
| 1110 |
+
"eval_samples_per_second": 0.925,
|
| 1111 |
+
"eval_steps_per_second": 0.925,
|
| 1112 |
+
"step": 224
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 39.30434782608695,
|
| 1116 |
+
"grad_norm": 0.21919763088226318,
|
| 1117 |
+
"learning_rate": 8.815222438236726e-06,
|
| 1118 |
+
"loss": 1.0162,
|
| 1119 |
+
"step": 226
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 39.65217391304348,
|
| 1123 |
+
"grad_norm": 0.24376323819160461,
|
| 1124 |
+
"learning_rate": 8.784975278258783e-06,
|
| 1125 |
+
"loss": 0.9777,
|
| 1126 |
+
"step": 228
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 40.0,
|
| 1130 |
+
"grad_norm": 0.2683652639389038,
|
| 1131 |
+
"learning_rate": 8.754400164907496e-06,
|
| 1132 |
+
"loss": 0.9241,
|
| 1133 |
+
"step": 230
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 40.0,
|
| 1137 |
+
"eval_loss": 1.07473886013031,
|
| 1138 |
+
"eval_runtime": 12.9776,
|
| 1139 |
+
"eval_samples_per_second": 0.925,
|
| 1140 |
+
"eval_steps_per_second": 0.925,
|
| 1141 |
+
"step": 230
|
| 1142 |
+
},
|
| 1143 |
+
{
|
| 1144 |
+
"epoch": 40.34782608695652,
|
| 1145 |
+
"grad_norm": 0.23253561556339264,
|
| 1146 |
+
"learning_rate": 8.723499747397415e-06,
|
| 1147 |
+
"loss": 0.9221,
|
| 1148 |
+
"step": 232
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 40.69565217391305,
|
| 1152 |
+
"grad_norm": 0.2230878323316574,
|
| 1153 |
+
"learning_rate": 8.692276703129421e-06,
|
| 1154 |
+
"loss": 1.0387,
|
| 1155 |
+
"step": 234
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 40.869565217391305,
|
| 1159 |
+
"eval_loss": 1.0742899179458618,
|
| 1160 |
+
"eval_runtime": 12.9772,
|
| 1161 |
+
"eval_samples_per_second": 0.925,
|
| 1162 |
+
"eval_steps_per_second": 0.925,
|
| 1163 |
+
"step": 235
|
| 1164 |
+
},
|
| 1165 |
+
{
|
| 1166 |
+
"epoch": 41.04347826086956,
|
| 1167 |
+
"grad_norm": 0.23267078399658203,
|
| 1168 |
+
"learning_rate": 8.660733737458751e-06,
|
| 1169 |
+
"loss": 0.9551,
|
| 1170 |
+
"step": 236
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 41.391304347826086,
|
| 1174 |
+
"grad_norm": 0.25790396332740784,
|
| 1175 |
+
"learning_rate": 8.628873583460593e-06,
|
| 1176 |
+
"loss": 0.9623,
|
| 1177 |
+
"step": 238
|
| 1178 |
+
},
|
| 1179 |
+
{
|
| 1180 |
+
"epoch": 41.73913043478261,
|
| 1181 |
+
"grad_norm": 0.23886793851852417,
|
| 1182 |
+
"learning_rate": 8.596699001693257e-06,
|
| 1183 |
+
"loss": 0.9616,
|
| 1184 |
+
"step": 240
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 41.91304347826087,
|
| 1188 |
+
"eval_loss": 1.073310375213623,
|
| 1189 |
+
"eval_runtime": 12.9821,
|
| 1190 |
+
"eval_samples_per_second": 0.924,
|
| 1191 |
+
"eval_steps_per_second": 0.924,
|
| 1192 |
+
"step": 241
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 42.08695652173913,
|
| 1196 |
+
"grad_norm": 0.24948331713676453,
|
| 1197 |
+
"learning_rate": 8.564212779959003e-06,
|
| 1198 |
+
"loss": 0.9294,
|
| 1199 |
+
"step": 242
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 42.43478260869565,
|
| 1203 |
+
"grad_norm": 0.24044832587242126,
|
| 1204 |
+
"learning_rate": 8.531417733062476e-06,
|
| 1205 |
+
"loss": 0.9579,
|
| 1206 |
+
"step": 244
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 42.78260869565217,
|
| 1210 |
+
"grad_norm": 0.2429089993238449,
|
| 1211 |
+
"learning_rate": 8.498316702566828e-06,
|
| 1212 |
+
"loss": 0.9909,
|
| 1213 |
+
"step": 246
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 42.95652173913044,
|
| 1217 |
+
"eval_loss": 1.0724002122879028,
|
| 1218 |
+
"eval_runtime": 12.9815,
|
| 1219 |
+
"eval_samples_per_second": 0.924,
|
| 1220 |
+
"eval_steps_per_second": 0.924,
|
| 1221 |
+
"step": 247
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 43.130434782608695,
|
| 1225 |
+
"grad_norm": 0.25010445713996887,
|
| 1226 |
+
"learning_rate": 8.464912556547486e-06,
|
| 1227 |
+
"loss": 0.9609,
|
| 1228 |
+
"step": 248
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 43.47826086956522,
|
| 1232 |
+
"grad_norm": 0.25847363471984863,
|
| 1233 |
+
"learning_rate": 8.43120818934367e-06,
|
| 1234 |
+
"loss": 0.9271,
|
| 1235 |
+
"step": 250
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 43.82608695652174,
|
| 1239 |
+
"grad_norm": 0.25236183404922485,
|
| 1240 |
+
"learning_rate": 8.397206521307584e-06,
|
| 1241 |
+
"loss": 0.9055,
|
| 1242 |
+
"step": 252
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 44.0,
|
| 1246 |
+
"eval_loss": 1.0719984769821167,
|
| 1247 |
+
"eval_runtime": 12.9768,
|
| 1248 |
+
"eval_samples_per_second": 0.925,
|
| 1249 |
+
"eval_steps_per_second": 0.925,
|
| 1250 |
+
"step": 253
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 44.17391304347826,
|
| 1254 |
+
"grad_norm": 0.2587444484233856,
|
| 1255 |
+
"learning_rate": 8.362910498551402e-06,
|
| 1256 |
+
"loss": 0.9453,
|
| 1257 |
+
"step": 254
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 44.52173913043478,
|
| 1261 |
+
"grad_norm": 0.2820061147212982,
|
| 1262 |
+
"learning_rate": 8.328323092691985e-06,
|
| 1263 |
+
"loss": 0.952,
|
| 1264 |
+
"step": 256
|
| 1265 |
+
},
|
| 1266 |
+
{
|
| 1267 |
+
"epoch": 44.869565217391305,
|
| 1268 |
+
"grad_norm": 0.2769736349582672,
|
| 1269 |
+
"learning_rate": 8.293447300593402e-06,
|
| 1270 |
+
"loss": 1.0025,
|
| 1271 |
+
"step": 258
|
| 1272 |
+
},
|
| 1273 |
+
{
|
| 1274 |
+
"epoch": 44.869565217391305,
|
| 1275 |
+
"eval_loss": 1.0721515417099,
|
| 1276 |
+
"eval_runtime": 12.979,
|
| 1277 |
+
"eval_samples_per_second": 0.925,
|
| 1278 |
+
"eval_steps_per_second": 0.925,
|
| 1279 |
+
"step": 258
|
| 1280 |
+
},
|
| 1281 |
+
{
|
| 1282 |
+
"epoch": 45.21739130434783,
|
| 1283 |
+
"grad_norm": 0.2502345144748688,
|
| 1284 |
+
"learning_rate": 8.258286144107277e-06,
|
| 1285 |
+
"loss": 0.9481,
|
| 1286 |
+
"step": 260
|
| 1287 |
+
},
|
| 1288 |
+
{
|
| 1289 |
+
"epoch": 45.56521739130435,
|
| 1290 |
+
"grad_norm": 0.2711241841316223,
|
| 1291 |
+
"learning_rate": 8.222842669810936e-06,
|
| 1292 |
+
"loss": 0.9477,
|
| 1293 |
+
"step": 262
|
| 1294 |
+
},
|
| 1295 |
+
{
|
| 1296 |
+
"epoch": 45.91304347826087,
|
| 1297 |
+
"grad_norm": 0.25015076994895935,
|
| 1298 |
+
"learning_rate": 8.18711994874345e-06,
|
| 1299 |
+
"loss": 0.9325,
|
| 1300 |
+
"step": 264
|
| 1301 |
+
},
|
| 1302 |
+
{
|
| 1303 |
+
"epoch": 45.91304347826087,
|
| 1304 |
+
"eval_loss": 1.0710887908935547,
|
| 1305 |
+
"eval_runtime": 12.9806,
|
| 1306 |
+
"eval_samples_per_second": 0.924,
|
| 1307 |
+
"eval_steps_per_second": 0.924,
|
| 1308 |
+
"step": 264
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 46.26086956521739,
|
| 1312 |
+
"grad_norm": 0.3114207088947296,
|
| 1313 |
+
"learning_rate": 8.151121076139534e-06,
|
| 1314 |
+
"loss": 0.8994,
|
| 1315 |
+
"step": 266
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 46.608695652173914,
|
| 1319 |
+
"grad_norm": 0.2907244861125946,
|
| 1320 |
+
"learning_rate": 8.11484917116136e-06,
|
| 1321 |
+
"loss": 1.0092,
|
| 1322 |
+
"step": 268
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 46.95652173913044,
|
| 1326 |
+
"grad_norm": 0.3372167646884918,
|
| 1327 |
+
"learning_rate": 8.078307376628292e-06,
|
| 1328 |
+
"loss": 0.8921,
|
| 1329 |
+
"step": 270
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 46.95652173913044,
|
| 1333 |
+
"eval_loss": 1.0723286867141724,
|
| 1334 |
+
"eval_runtime": 12.9797,
|
| 1335 |
+
"eval_samples_per_second": 0.925,
|
| 1336 |
+
"eval_steps_per_second": 0.925,
|
| 1337 |
+
"step": 270
|
| 1338 |
+
},
|
| 1339 |
+
{
|
| 1340 |
+
"epoch": 47.30434782608695,
|
| 1341 |
+
"grad_norm": 0.32444846630096436,
|
| 1342 |
+
"learning_rate": 8.041498858744572e-06,
|
| 1343 |
+
"loss": 0.954,
|
| 1344 |
+
"step": 272
|
| 1345 |
+
},
|
| 1346 |
+
{
|
| 1347 |
+
"epoch": 47.65217391304348,
|
| 1348 |
+
"grad_norm": 0.2917410731315613,
|
| 1349 |
+
"learning_rate": 8.004426806824985e-06,
|
| 1350 |
+
"loss": 0.9444,
|
| 1351 |
+
"step": 274
|
| 1352 |
+
},
|
| 1353 |
+
{
|
| 1354 |
+
"epoch": 48.0,
|
| 1355 |
+
"grad_norm": 0.3161114454269409,
|
| 1356 |
+
"learning_rate": 7.967094433018508e-06,
|
| 1357 |
+
"loss": 0.9079,
|
| 1358 |
+
"step": 276
|
| 1359 |
+
},
|
| 1360 |
+
{
|
| 1361 |
+
"epoch": 48.0,
|
| 1362 |
+
"eval_loss": 1.0710123777389526,
|
| 1363 |
+
"eval_runtime": 12.9764,
|
| 1364 |
+
"eval_samples_per_second": 0.925,
|
| 1365 |
+
"eval_steps_per_second": 0.925,
|
| 1366 |
+
"step": 276
|
| 1367 |
+
},
|
| 1368 |
+
{
|
| 1369 |
+
"epoch": 48.34782608695652,
|
| 1370 |
+
"grad_norm": 0.27982279658317566,
|
| 1371 |
+
"learning_rate": 7.929504972030003e-06,
|
| 1372 |
+
"loss": 0.8982,
|
| 1373 |
+
"step": 278
|
| 1374 |
+
},
|
| 1375 |
+
{
|
| 1376 |
+
"epoch": 48.69565217391305,
|
| 1377 |
+
"grad_norm": 0.29784122109413147,
|
| 1378 |
+
"learning_rate": 7.891661680839932e-06,
|
| 1379 |
+
"loss": 0.9615,
|
| 1380 |
+
"step": 280
|
| 1381 |
+
},
|
| 1382 |
+
{
|
| 1383 |
+
"epoch": 48.869565217391305,
|
| 1384 |
+
"eval_loss": 1.07285475730896,
|
| 1385 |
+
"eval_runtime": 12.9818,
|
| 1386 |
+
"eval_samples_per_second": 0.924,
|
| 1387 |
+
"eval_steps_per_second": 0.924,
|
| 1388 |
+
"step": 281
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 49.04347826086956,
|
| 1392 |
+
"grad_norm": 0.3300091326236725,
|
| 1393 |
+
"learning_rate": 7.85356783842216e-06,
|
| 1394 |
+
"loss": 0.8969,
|
| 1395 |
+
"step": 282
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 49.391304347826086,
|
| 1399 |
+
"grad_norm": 0.3034118413925171,
|
| 1400 |
+
"learning_rate": 7.815226745459831e-06,
|
| 1401 |
+
"loss": 0.9267,
|
| 1402 |
+
"step": 284
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 49.73913043478261,
|
| 1406 |
+
"grad_norm": 0.28807440400123596,
|
| 1407 |
+
"learning_rate": 7.776641724059398e-06,
|
| 1408 |
+
"loss": 0.9517,
|
| 1409 |
+
"step": 286
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 49.91304347826087,
|
| 1413 |
+
"eval_loss": 1.0717887878417969,
|
| 1414 |
+
"eval_runtime": 12.9755,
|
| 1415 |
+
"eval_samples_per_second": 0.925,
|
| 1416 |
+
"eval_steps_per_second": 0.925,
|
| 1417 |
+
"step": 287
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 50.08695652173913,
|
| 1421 |
+
"grad_norm": 0.34060779213905334,
|
| 1422 |
+
"learning_rate": 7.737816117462752e-06,
|
| 1423 |
+
"loss": 0.9092,
|
| 1424 |
+
"step": 288
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 50.43478260869565,
|
| 1428 |
+
"grad_norm": 0.28578662872314453,
|
| 1429 |
+
"learning_rate": 7.698753289757565e-06,
|
| 1430 |
+
"loss": 0.9824,
|
| 1431 |
+
"step": 290
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 50.78260869565217,
|
| 1435 |
+
"grad_norm": 0.316270112991333,
|
| 1436 |
+
"learning_rate": 7.65945662558579e-06,
|
| 1437 |
+
"loss": 0.8619,
|
| 1438 |
+
"step": 292
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 50.95652173913044,
|
| 1442 |
+
"eval_loss": 1.0729678869247437,
|
| 1443 |
+
"eval_runtime": 12.9784,
|
| 1444 |
+
"eval_samples_per_second": 0.925,
|
| 1445 |
+
"eval_steps_per_second": 0.925,
|
| 1446 |
+
"step": 293
|
| 1447 |
+
},
|
| 1448 |
+
{
|
| 1449 |
+
"epoch": 51.130434782608695,
|
| 1450 |
+
"grad_norm": 0.2928197681903839,
|
| 1451 |
+
"learning_rate": 7.619929529850397e-06,
|
| 1452 |
+
"loss": 0.946,
|
| 1453 |
+
"step": 294
|
| 1454 |
+
},
|
| 1455 |
+
{
|
| 1456 |
+
"epoch": 51.47826086956522,
|
| 1457 |
+
"grad_norm": 0.30175477266311646,
|
| 1458 |
+
"learning_rate": 7.580175427420358e-06,
|
| 1459 |
+
"loss": 0.9319,
|
| 1460 |
+
"step": 296
|
| 1461 |
+
},
|
| 1462 |
+
{
|
| 1463 |
+
"epoch": 51.82608695652174,
|
| 1464 |
+
"grad_norm": 0.3955518305301666,
|
| 1465 |
+
"learning_rate": 7.54019776283389e-06,
|
| 1466 |
+
"loss": 0.8894,
|
| 1467 |
+
"step": 298
|
| 1468 |
+
},
|
| 1469 |
+
{
|
| 1470 |
+
"epoch": 52.0,
|
| 1471 |
+
"eval_loss": 1.0739282369613647,
|
| 1472 |
+
"eval_runtime": 12.9857,
|
| 1473 |
+
"eval_samples_per_second": 0.924,
|
| 1474 |
+
"eval_steps_per_second": 0.924,
|
| 1475 |
+
"step": 299
|
| 1476 |
+
},
|
| 1477 |
+
{
|
| 1478 |
+
"epoch": 52.17391304347826,
|
| 1479 |
+
"grad_norm": 0.33545202016830444,
|
| 1480 |
+
"learning_rate": 7.500000000000001e-06,
|
| 1481 |
+
"loss": 0.8967,
|
| 1482 |
+
"step": 300
|
| 1483 |
+
},
|
| 1484 |
+
{
|
| 1485 |
+
"epoch": 52.52173913043478,
|
| 1486 |
+
"grad_norm": 0.3249565362930298,
|
| 1487 |
+
"learning_rate": 7.459585621898353e-06,
|
| 1488 |
+
"loss": 0.9514,
|
| 1489 |
+
"step": 302
|
| 1490 |
+
},
|
| 1491 |
+
{
|
| 1492 |
+
"epoch": 52.869565217391305,
|
| 1493 |
+
"grad_norm": 0.3969457745552063,
|
| 1494 |
+
"learning_rate": 7.418958130277483e-06,
|
| 1495 |
+
"loss": 0.8389,
|
| 1496 |
+
"step": 304
|
| 1497 |
+
},
|
| 1498 |
+
{
|
| 1499 |
+
"epoch": 52.869565217391305,
|
| 1500 |
+
"eval_loss": 1.0741795301437378,
|
| 1501 |
+
"eval_runtime": 12.9752,
|
| 1502 |
+
"eval_samples_per_second": 0.925,
|
| 1503 |
+
"eval_steps_per_second": 0.925,
|
| 1504 |
+
"step": 304
|
| 1505 |
+
},
|
| 1506 |
+
{
|
| 1507 |
+
"epoch": 53.21739130434783,
|
| 1508 |
+
"grad_norm": 0.3565354347229004,
|
| 1509 |
+
"learning_rate": 7.378121045351378e-06,
|
| 1510 |
+
"loss": 0.882,
|
| 1511 |
+
"step": 306
|
| 1512 |
+
},
|
| 1513 |
+
{
|
| 1514 |
+
"epoch": 53.56521739130435,
|
| 1515 |
+
"grad_norm": 0.41273507475852966,
|
| 1516 |
+
"learning_rate": 7.337077905494472e-06,
|
| 1517 |
+
"loss": 0.8992,
|
| 1518 |
+
"step": 308
|
| 1519 |
+
},
|
| 1520 |
+
{
|
| 1521 |
+
"epoch": 53.91304347826087,
|
| 1522 |
+
"grad_norm": 0.3917119801044464,
|
| 1523 |
+
"learning_rate": 7.295832266935059e-06,
|
| 1524 |
+
"loss": 0.9032,
|
| 1525 |
+
"step": 310
|
| 1526 |
+
},
|
| 1527 |
+
{
|
| 1528 |
+
"epoch": 53.91304347826087,
|
| 1529 |
+
"eval_loss": 1.0749919414520264,
|
| 1530 |
+
"eval_runtime": 12.9751,
|
| 1531 |
+
"eval_samples_per_second": 0.925,
|
| 1532 |
+
"eval_steps_per_second": 0.925,
|
| 1533 |
+
"step": 310
|
| 1534 |
+
},
|
| 1535 |
+
{
|
| 1536 |
+
"epoch": 54.26086956521739,
|
| 1537 |
+
"grad_norm": 0.34160563349723816,
|
| 1538 |
+
"learning_rate": 7.254387703447154e-06,
|
| 1539 |
+
"loss": 0.9499,
|
| 1540 |
+
"step": 312
|
| 1541 |
+
},
|
| 1542 |
+
{
|
| 1543 |
+
"epoch": 54.608695652173914,
|
| 1544 |
+
"grad_norm": 0.4153737723827362,
|
| 1545 |
+
"learning_rate": 7.212747806040845e-06,
|
| 1546 |
+
"loss": 0.9246,
|
| 1547 |
+
"step": 314
|
| 1548 |
+
},
|
| 1549 |
+
{
|
| 1550 |
+
"epoch": 54.95652173913044,
|
| 1551 |
+
"grad_norm": 0.3735916316509247,
|
| 1552 |
+
"learning_rate": 7.170916182651141e-06,
|
| 1553 |
+
"loss": 0.9015,
|
| 1554 |
+
"step": 316
|
| 1555 |
+
},
|
| 1556 |
+
{
|
| 1557 |
+
"epoch": 54.95652173913044,
|
| 1558 |
+
"eval_loss": 1.0760287046432495,
|
| 1559 |
+
"eval_runtime": 12.9763,
|
| 1560 |
+
"eval_samples_per_second": 0.925,
|
| 1561 |
+
"eval_steps_per_second": 0.925,
|
| 1562 |
+
"step": 316
|
| 1563 |
+
},
|
| 1564 |
+
{
|
| 1565 |
+
"epoch": 54.95652173913044,
|
| 1566 |
+
"step": 316,
|
| 1567 |
+
"total_flos": 2.4451647665917133e+17,
|
| 1568 |
+
"train_loss": 1.137867835975146,
|
| 1569 |
+
"train_runtime": 8799.2233,
|
| 1570 |
+
"train_samples_per_second": 0.784,
|
| 1571 |
+
"train_steps_per_second": 0.085
|
| 1572 |
+
}
|
| 1573 |
+
],
|
| 1574 |
+
"logging_steps": 2,
|
| 1575 |
+
"max_steps": 750,
|
| 1576 |
+
"num_input_tokens_seen": 0,
|
| 1577 |
+
"num_train_epochs": 150,
|
| 1578 |
+
"save_steps": 25,
|
| 1579 |
+
"stateful_callbacks": {
|
| 1580 |
+
"EarlyStoppingCallback": {
|
| 1581 |
+
"args": {
|
| 1582 |
+
"early_stopping_patience": 7,
|
| 1583 |
+
"early_stopping_threshold": 0.0
|
| 1584 |
+
},
|
| 1585 |
+
"attributes": {
|
| 1586 |
+
"early_stopping_patience_counter": 0
|
| 1587 |
+
}
|
| 1588 |
+
},
|
| 1589 |
+
"TrainerControl": {
|
| 1590 |
+
"args": {
|
| 1591 |
+
"should_epoch_stop": false,
|
| 1592 |
+
"should_evaluate": false,
|
| 1593 |
+
"should_log": false,
|
| 1594 |
+
"should_save": true,
|
| 1595 |
+
"should_training_stop": true
|
| 1596 |
+
},
|
| 1597 |
+
"attributes": {}
|
| 1598 |
+
}
|
| 1599 |
+
},
|
| 1600 |
+
"total_flos": 2.4451647665917133e+17,
|
| 1601 |
+
"train_batch_size": 1,
|
| 1602 |
+
"trial_name": null,
|
| 1603 |
+
"trial_params": null
|
| 1604 |
+
}
|