Commit
•
6ad0939
1
Parent(s):
f995372
Model save
Browse files- README.md +113 -0
- adapter_model.safetensors +1 -1
- all_results.json +9 -0
- train_results.json +9 -0
- trainer_state.json +1430 -0
README.md
ADDED
|
@@ -0,0 +1,113 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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-1_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-1_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: 0.9393
|
| 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 |
+
| 2.5395 | 0.8696 | 5 | 2.4149 |
|
| 57 |
+
| 2.4512 | 1.9130 | 11 | 2.3973 |
|
| 58 |
+
| 2.4419 | 2.9565 | 17 | 2.3721 |
|
| 59 |
+
| 2.3921 | 4.0 | 23 | 2.3361 |
|
| 60 |
+
| 2.3357 | 4.8696 | 28 | 2.2954 |
|
| 61 |
+
| 2.3559 | 5.9130 | 34 | 2.2287 |
|
| 62 |
+
| 2.2622 | 6.9565 | 40 | 2.1654 |
|
| 63 |
+
| 2.186 | 8.0 | 46 | 2.0752 |
|
| 64 |
+
| 2.0842 | 8.8696 | 51 | 2.0000 |
|
| 65 |
+
| 2.0522 | 9.9130 | 57 | 1.8960 |
|
| 66 |
+
| 1.911 | 10.9565 | 63 | 1.7942 |
|
| 67 |
+
| 1.8076 | 12.0 | 69 | 1.6760 |
|
| 68 |
+
| 1.659 | 12.8696 | 74 | 1.5645 |
|
| 69 |
+
| 1.5002 | 13.9130 | 80 | 1.4214 |
|
| 70 |
+
| 1.309 | 14.9565 | 86 | 1.2940 |
|
| 71 |
+
| 1.2079 | 16.0 | 92 | 1.1837 |
|
| 72 |
+
| 1.1738 | 16.8696 | 97 | 1.1230 |
|
| 73 |
+
| 1.0304 | 17.9130 | 103 | 1.0781 |
|
| 74 |
+
| 1.0485 | 18.9565 | 109 | 1.0459 |
|
| 75 |
+
| 0.9687 | 20.0 | 115 | 1.0258 |
|
| 76 |
+
| 0.9883 | 20.8696 | 120 | 1.0147 |
|
| 77 |
+
| 0.974 | 21.9130 | 126 | 1.0013 |
|
| 78 |
+
| 0.9397 | 22.9565 | 132 | 0.9905 |
|
| 79 |
+
| 0.9522 | 24.0 | 138 | 0.9816 |
|
| 80 |
+
| 0.9115 | 24.8696 | 143 | 0.9739 |
|
| 81 |
+
| 0.9412 | 25.9130 | 149 | 0.9668 |
|
| 82 |
+
| 0.9168 | 26.9565 | 155 | 0.9610 |
|
| 83 |
+
| 0.9461 | 28.0 | 161 | 0.9547 |
|
| 84 |
+
| 0.8579 | 28.8696 | 166 | 0.9499 |
|
| 85 |
+
| 0.8857 | 29.9130 | 172 | 0.9454 |
|
| 86 |
+
| 0.8465 | 30.9565 | 178 | 0.9405 |
|
| 87 |
+
| 0.8681 | 32.0 | 184 | 0.9393 |
|
| 88 |
+
| 0.8257 | 32.8696 | 189 | 0.9344 |
|
| 89 |
+
| 0.8425 | 33.9130 | 195 | 0.9336 |
|
| 90 |
+
| 0.8405 | 34.9565 | 201 | 0.9281 |
|
| 91 |
+
| 0.8101 | 36.0 | 207 | 0.9283 |
|
| 92 |
+
| 0.7808 | 36.8696 | 212 | 0.9259 |
|
| 93 |
+
| 0.7971 | 37.9130 | 218 | 0.9259 |
|
| 94 |
+
| 0.7766 | 38.9565 | 224 | 0.9235 |
|
| 95 |
+
| 0.7748 | 40.0 | 230 | 0.9245 |
|
| 96 |
+
| 0.7476 | 40.8696 | 235 | 0.9253 |
|
| 97 |
+
| 0.7007 | 41.9130 | 241 | 0.9224 |
|
| 98 |
+
| 0.741 | 42.9565 | 247 | 0.9261 |
|
| 99 |
+
| 0.7371 | 44.0 | 253 | 0.9239 |
|
| 100 |
+
| 0.7239 | 44.8696 | 258 | 0.9323 |
|
| 101 |
+
| 0.671 | 45.9130 | 264 | 0.9269 |
|
| 102 |
+
| 0.7312 | 46.9565 | 270 | 0.9333 |
|
| 103 |
+
| 0.6826 | 48.0 | 276 | 0.9345 |
|
| 104 |
+
| 0.6472 | 48.8696 | 281 | 0.9393 |
|
| 105 |
+
|
| 106 |
+
|
| 107 |
+
### Framework versions
|
| 108 |
+
|
| 109 |
+
- PEFT 0.12.0
|
| 110 |
+
- Transformers 4.44.0
|
| 111 |
+
- Pytorch 2.1.2+cu121
|
| 112 |
+
- Datasets 2.20.0
|
| 113 |
+
- 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 sha256:2d524596e71aa758bd36b6151aaf9c3b3f9beab52dbcc769c6bcc9fd18b14cbe
|
| 3 |
size 167832240
|
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 48.869565217391305,
|
| 3 |
+
"total_flos": 3.3738755183476736e+16,
|
| 4 |
+
"train_loss": 1.2498505263990354,
|
| 5 |
+
"train_runtime": 2644.3439,
|
| 6 |
+
"train_samples": 46,
|
| 7 |
+
"train_samples_per_second": 2.609,
|
| 8 |
+
"train_steps_per_second": 0.284
|
| 9 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 48.869565217391305,
|
| 3 |
+
"total_flos": 3.3738755183476736e+16,
|
| 4 |
+
"train_loss": 1.2498505263990354,
|
| 5 |
+
"train_runtime": 2644.3439,
|
| 6 |
+
"train_samples": 46,
|
| 7 |
+
"train_samples_per_second": 2.609,
|
| 8 |
+
"train_steps_per_second": 0.284
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1430 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.922440230846405,
|
| 3 |
+
"best_model_checkpoint": "data/Llama-31-8B_task-1_60-samples_config-3_full/checkpoint-241",
|
| 4 |
+
"epoch": 48.869565217391305,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 281,
|
| 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": 2.0927231311798096,
|
| 14 |
+
"learning_rate": 1.3333333333333336e-07,
|
| 15 |
+
"loss": 2.45,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.34782608695652173,
|
| 20 |
+
"grad_norm": 2.0467705726623535,
|
| 21 |
+
"learning_rate": 2.666666666666667e-07,
|
| 22 |
+
"loss": 2.5615,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.6956521739130435,
|
| 27 |
+
"grad_norm": 1.8534517288208008,
|
| 28 |
+
"learning_rate": 5.333333333333335e-07,
|
| 29 |
+
"loss": 2.5395,
|
| 30 |
+
"step": 4
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.8695652173913043,
|
| 34 |
+
"eval_loss": 2.414898633956909,
|
| 35 |
+
"eval_runtime": 4.8246,
|
| 36 |
+
"eval_samples_per_second": 2.487,
|
| 37 |
+
"eval_steps_per_second": 2.487,
|
| 38 |
+
"step": 5
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 1.0434782608695652,
|
| 42 |
+
"grad_norm": 1.889623761177063,
|
| 43 |
+
"learning_rate": 8.000000000000001e-07,
|
| 44 |
+
"loss": 2.4961,
|
| 45 |
+
"step": 6
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 1.391304347826087,
|
| 49 |
+
"grad_norm": 2.059065103530884,
|
| 50 |
+
"learning_rate": 1.066666666666667e-06,
|
| 51 |
+
"loss": 2.5344,
|
| 52 |
+
"step": 8
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 1.7391304347826086,
|
| 56 |
+
"grad_norm": 1.8490760326385498,
|
| 57 |
+
"learning_rate": 1.3333333333333334e-06,
|
| 58 |
+
"loss": 2.4512,
|
| 59 |
+
"step": 10
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 1.9130434782608696,
|
| 63 |
+
"eval_loss": 2.3973469734191895,
|
| 64 |
+
"eval_runtime": 4.826,
|
| 65 |
+
"eval_samples_per_second": 2.487,
|
| 66 |
+
"eval_steps_per_second": 2.487,
|
| 67 |
+
"step": 11
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 2.0869565217391304,
|
| 71 |
+
"grad_norm": 1.871017336845398,
|
| 72 |
+
"learning_rate": 1.6000000000000001e-06,
|
| 73 |
+
"loss": 2.5467,
|
| 74 |
+
"step": 12
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 2.4347826086956523,
|
| 78 |
+
"grad_norm": 1.7037708759307861,
|
| 79 |
+
"learning_rate": 1.8666666666666669e-06,
|
| 80 |
+
"loss": 2.5079,
|
| 81 |
+
"step": 14
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 2.782608695652174,
|
| 85 |
+
"grad_norm": 1.658904790878296,
|
| 86 |
+
"learning_rate": 2.133333333333334e-06,
|
| 87 |
+
"loss": 2.4419,
|
| 88 |
+
"step": 16
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 2.9565217391304346,
|
| 92 |
+
"eval_loss": 2.372079372406006,
|
| 93 |
+
"eval_runtime": 4.8248,
|
| 94 |
+
"eval_samples_per_second": 2.487,
|
| 95 |
+
"eval_steps_per_second": 2.487,
|
| 96 |
+
"step": 17
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 3.130434782608696,
|
| 100 |
+
"grad_norm": 1.583447813987732,
|
| 101 |
+
"learning_rate": 2.4000000000000003e-06,
|
| 102 |
+
"loss": 2.4868,
|
| 103 |
+
"step": 18
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 3.4782608695652173,
|
| 107 |
+
"grad_norm": 1.6701875925064087,
|
| 108 |
+
"learning_rate": 2.666666666666667e-06,
|
| 109 |
+
"loss": 2.459,
|
| 110 |
+
"step": 20
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 3.8260869565217392,
|
| 114 |
+
"grad_norm": 1.580588936805725,
|
| 115 |
+
"learning_rate": 2.9333333333333338e-06,
|
| 116 |
+
"loss": 2.3921,
|
| 117 |
+
"step": 22
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 4.0,
|
| 121 |
+
"eval_loss": 2.3361399173736572,
|
| 122 |
+
"eval_runtime": 4.8269,
|
| 123 |
+
"eval_samples_per_second": 2.486,
|
| 124 |
+
"eval_steps_per_second": 2.486,
|
| 125 |
+
"step": 23
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 4.173913043478261,
|
| 129 |
+
"grad_norm": 1.8148592710494995,
|
| 130 |
+
"learning_rate": 3.2000000000000003e-06,
|
| 131 |
+
"loss": 2.5221,
|
| 132 |
+
"step": 24
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 4.521739130434782,
|
| 136 |
+
"grad_norm": 1.5363281965255737,
|
| 137 |
+
"learning_rate": 3.4666666666666672e-06,
|
| 138 |
+
"loss": 2.4424,
|
| 139 |
+
"step": 26
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 4.869565217391305,
|
| 143 |
+
"grad_norm": 1.7005550861358643,
|
| 144 |
+
"learning_rate": 3.7333333333333337e-06,
|
| 145 |
+
"loss": 2.3357,
|
| 146 |
+
"step": 28
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 4.869565217391305,
|
| 150 |
+
"eval_loss": 2.295424461364746,
|
| 151 |
+
"eval_runtime": 4.8298,
|
| 152 |
+
"eval_samples_per_second": 2.485,
|
| 153 |
+
"eval_steps_per_second": 2.485,
|
| 154 |
+
"step": 28
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 5.217391304347826,
|
| 158 |
+
"grad_norm": 1.866983413696289,
|
| 159 |
+
"learning_rate": 4.000000000000001e-06,
|
| 160 |
+
"loss": 2.3658,
|
| 161 |
+
"step": 30
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 5.565217391304348,
|
| 165 |
+
"grad_norm": 1.9320333003997803,
|
| 166 |
+
"learning_rate": 4.266666666666668e-06,
|
| 167 |
+
"loss": 2.3898,
|
| 168 |
+
"step": 32
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 5.913043478260869,
|
| 172 |
+
"grad_norm": 1.7484076023101807,
|
| 173 |
+
"learning_rate": 4.533333333333334e-06,
|
| 174 |
+
"loss": 2.3559,
|
| 175 |
+
"step": 34
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"epoch": 5.913043478260869,
|
| 179 |
+
"eval_loss": 2.2286934852600098,
|
| 180 |
+
"eval_runtime": 4.8271,
|
| 181 |
+
"eval_samples_per_second": 2.486,
|
| 182 |
+
"eval_steps_per_second": 2.486,
|
| 183 |
+
"step": 34
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 6.260869565217392,
|
| 187 |
+
"grad_norm": 1.423509955406189,
|
| 188 |
+
"learning_rate": 4.800000000000001e-06,
|
| 189 |
+
"loss": 2.2329,
|
| 190 |
+
"step": 36
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 6.608695652173913,
|
| 194 |
+
"grad_norm": 1.3438361883163452,
|
| 195 |
+
"learning_rate": 5.0666666666666676e-06,
|
| 196 |
+
"loss": 2.2697,
|
| 197 |
+
"step": 38
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 6.956521739130435,
|
| 201 |
+
"grad_norm": 1.4381420612335205,
|
| 202 |
+
"learning_rate": 5.333333333333334e-06,
|
| 203 |
+
"loss": 2.2622,
|
| 204 |
+
"step": 40
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 6.956521739130435,
|
| 208 |
+
"eval_loss": 2.165445566177368,
|
| 209 |
+
"eval_runtime": 4.8282,
|
| 210 |
+
"eval_samples_per_second": 2.485,
|
| 211 |
+
"eval_steps_per_second": 2.485,
|
| 212 |
+
"step": 40
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 7.304347826086957,
|
| 216 |
+
"grad_norm": 1.5358691215515137,
|
| 217 |
+
"learning_rate": 5.600000000000001e-06,
|
| 218 |
+
"loss": 2.2903,
|
| 219 |
+
"step": 42
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 7.6521739130434785,
|
| 223 |
+
"grad_norm": 1.7526369094848633,
|
| 224 |
+
"learning_rate": 5.8666666666666675e-06,
|
| 225 |
+
"loss": 2.1646,
|
| 226 |
+
"step": 44
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 8.0,
|
| 230 |
+
"grad_norm": 1.6337189674377441,
|
| 231 |
+
"learning_rate": 6.133333333333334e-06,
|
| 232 |
+
"loss": 2.186,
|
| 233 |
+
"step": 46
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 8.0,
|
| 237 |
+
"eval_loss": 2.0752172470092773,
|
| 238 |
+
"eval_runtime": 4.8264,
|
| 239 |
+
"eval_samples_per_second": 2.486,
|
| 240 |
+
"eval_steps_per_second": 2.486,
|
| 241 |
+
"step": 46
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 8.347826086956522,
|
| 245 |
+
"grad_norm": 1.175416350364685,
|
| 246 |
+
"learning_rate": 6.4000000000000006e-06,
|
| 247 |
+
"loss": 2.1512,
|
| 248 |
+
"step": 48
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 8.695652173913043,
|
| 252 |
+
"grad_norm": 1.0512149333953857,
|
| 253 |
+
"learning_rate": 6.666666666666667e-06,
|
| 254 |
+
"loss": 2.0842,
|
| 255 |
+
"step": 50
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 8.869565217391305,
|
| 259 |
+
"eval_loss": 2.0000388622283936,
|
| 260 |
+
"eval_runtime": 4.8255,
|
| 261 |
+
"eval_samples_per_second": 2.487,
|
| 262 |
+
"eval_steps_per_second": 2.487,
|
| 263 |
+
"step": 51
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 9.043478260869565,
|
| 267 |
+
"grad_norm": 1.13035249710083,
|
| 268 |
+
"learning_rate": 6.9333333333333344e-06,
|
| 269 |
+
"loss": 2.0837,
|
| 270 |
+
"step": 52
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 9.391304347826088,
|
| 274 |
+
"grad_norm": 1.1123379468917847,
|
| 275 |
+
"learning_rate": 7.2000000000000005e-06,
|
| 276 |
+
"loss": 2.0165,
|
| 277 |
+
"step": 54
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 9.73913043478261,
|
| 281 |
+
"grad_norm": 1.0869874954223633,
|
| 282 |
+
"learning_rate": 7.4666666666666675e-06,
|
| 283 |
+
"loss": 2.0522,
|
| 284 |
+
"step": 56
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 9.91304347826087,
|
| 288 |
+
"eval_loss": 1.895993709564209,
|
| 289 |
+
"eval_runtime": 4.8268,
|
| 290 |
+
"eval_samples_per_second": 2.486,
|
| 291 |
+
"eval_steps_per_second": 2.486,
|
| 292 |
+
"step": 57
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 10.08695652173913,
|
| 296 |
+
"grad_norm": 0.8969458341598511,
|
| 297 |
+
"learning_rate": 7.733333333333334e-06,
|
| 298 |
+
"loss": 1.9308,
|
| 299 |
+
"step": 58
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 10.434782608695652,
|
| 303 |
+
"grad_norm": 0.9428701400756836,
|
| 304 |
+
"learning_rate": 8.000000000000001e-06,
|
| 305 |
+
"loss": 1.9244,
|
| 306 |
+
"step": 60
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 10.782608695652174,
|
| 310 |
+
"grad_norm": 0.8733699321746826,
|
| 311 |
+
"learning_rate": 8.266666666666667e-06,
|
| 312 |
+
"loss": 1.911,
|
| 313 |
+
"step": 62
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 10.956521739130435,
|
| 317 |
+
"eval_loss": 1.7942091226577759,
|
| 318 |
+
"eval_runtime": 4.8257,
|
| 319 |
+
"eval_samples_per_second": 2.487,
|
| 320 |
+
"eval_steps_per_second": 2.487,
|
| 321 |
+
"step": 63
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 11.130434782608695,
|
| 325 |
+
"grad_norm": 0.8451066613197327,
|
| 326 |
+
"learning_rate": 8.533333333333335e-06,
|
| 327 |
+
"loss": 1.8571,
|
| 328 |
+
"step": 64
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 11.478260869565217,
|
| 332 |
+
"grad_norm": 0.8815340995788574,
|
| 333 |
+
"learning_rate": 8.8e-06,
|
| 334 |
+
"loss": 1.7567,
|
| 335 |
+
"step": 66
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 11.826086956521738,
|
| 339 |
+
"grad_norm": 0.9107153415679932,
|
| 340 |
+
"learning_rate": 9.066666666666667e-06,
|
| 341 |
+
"loss": 1.8076,
|
| 342 |
+
"step": 68
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 12.0,
|
| 346 |
+
"eval_loss": 1.6759809255599976,
|
| 347 |
+
"eval_runtime": 4.8213,
|
| 348 |
+
"eval_samples_per_second": 2.489,
|
| 349 |
+
"eval_steps_per_second": 2.489,
|
| 350 |
+
"step": 69
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 12.173913043478262,
|
| 354 |
+
"grad_norm": 0.9571322202682495,
|
| 355 |
+
"learning_rate": 9.333333333333334e-06,
|
| 356 |
+
"loss": 1.6998,
|
| 357 |
+
"step": 70
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 12.521739130434783,
|
| 361 |
+
"grad_norm": 0.9073280096054077,
|
| 362 |
+
"learning_rate": 9.600000000000001e-06,
|
| 363 |
+
"loss": 1.701,
|
| 364 |
+
"step": 72
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 12.869565217391305,
|
| 368 |
+
"grad_norm": 1.23154878616333,
|
| 369 |
+
"learning_rate": 9.866666666666668e-06,
|
| 370 |
+
"loss": 1.659,
|
| 371 |
+
"step": 74
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 12.869565217391305,
|
| 375 |
+
"eval_loss": 1.564476490020752,
|
| 376 |
+
"eval_runtime": 4.83,
|
| 377 |
+
"eval_samples_per_second": 2.484,
|
| 378 |
+
"eval_steps_per_second": 2.484,
|
| 379 |
+
"step": 74
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 13.217391304347826,
|
| 383 |
+
"grad_norm": 1.1613293886184692,
|
| 384 |
+
"learning_rate": 9.999945845889795e-06,
|
| 385 |
+
"loss": 1.5798,
|
| 386 |
+
"step": 76
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 13.565217391304348,
|
| 390 |
+
"grad_norm": 1.0568084716796875,
|
| 391 |
+
"learning_rate": 9.999512620046523e-06,
|
| 392 |
+
"loss": 1.4833,
|
| 393 |
+
"step": 78
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 13.91304347826087,
|
| 397 |
+
"grad_norm": 0.9477815628051758,
|
| 398 |
+
"learning_rate": 9.99864620589731e-06,
|
| 399 |
+
"loss": 1.5002,
|
| 400 |
+
"step": 80
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 13.91304347826087,
|
| 404 |
+
"eval_loss": 1.4213947057724,
|
| 405 |
+
"eval_runtime": 4.834,
|
| 406 |
+
"eval_samples_per_second": 2.482,
|
| 407 |
+
"eval_steps_per_second": 2.482,
|
| 408 |
+
"step": 80
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 14.26086956521739,
|
| 412 |
+
"grad_norm": 1.0447523593902588,
|
| 413 |
+
"learning_rate": 9.99734667851357e-06,
|
| 414 |
+
"loss": 1.4439,
|
| 415 |
+
"step": 82
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 14.608695652173914,
|
| 419 |
+
"grad_norm": 0.9249804019927979,
|
| 420 |
+
"learning_rate": 9.995614150494293e-06,
|
| 421 |
+
"loss": 1.3666,
|
| 422 |
+
"step": 84
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 14.956521739130435,
|
| 426 |
+
"grad_norm": 1.0063517093658447,
|
| 427 |
+
"learning_rate": 9.993448771956285e-06,
|
| 428 |
+
"loss": 1.309,
|
| 429 |
+
"step": 86
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 14.956521739130435,
|
| 433 |
+
"eval_loss": 1.294012188911438,
|
| 434 |
+
"eval_runtime": 4.8245,
|
| 435 |
+
"eval_samples_per_second": 2.487,
|
| 436 |
+
"eval_steps_per_second": 2.487,
|
| 437 |
+
"step": 86
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 15.304347826086957,
|
| 441 |
+
"grad_norm": 1.0014103651046753,
|
| 442 |
+
"learning_rate": 9.99085073052117e-06,
|
| 443 |
+
"loss": 1.3033,
|
| 444 |
+
"step": 88
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 15.652173913043478,
|
| 448 |
+
"grad_norm": 0.9277029037475586,
|
| 449 |
+
"learning_rate": 9.987820251299121e-06,
|
| 450 |
+
"loss": 1.2597,
|
| 451 |
+
"step": 90
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 16.0,
|
| 455 |
+
"grad_norm": 0.8152615427970886,
|
| 456 |
+
"learning_rate": 9.984357596869369e-06,
|
| 457 |
+
"loss": 1.2079,
|
| 458 |
+
"step": 92
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 16.0,
|
| 462 |
+
"eval_loss": 1.183652400970459,
|
| 463 |
+
"eval_runtime": 4.8266,
|
| 464 |
+
"eval_samples_per_second": 2.486,
|
| 465 |
+
"eval_steps_per_second": 2.486,
|
| 466 |
+
"step": 92
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 16.347826086956523,
|
| 470 |
+
"grad_norm": 0.7255731821060181,
|
| 471 |
+
"learning_rate": 9.980463067257437e-06,
|
| 472 |
+
"loss": 1.1647,
|
| 473 |
+
"step": 94
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 16.695652173913043,
|
| 477 |
+
"grad_norm": 0.755571186542511,
|
| 478 |
+
"learning_rate": 9.976136999909156e-06,
|
| 479 |
+
"loss": 1.1738,
|
| 480 |
+
"step": 96
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 16.869565217391305,
|
| 484 |
+
"eval_loss": 1.1230496168136597,
|
| 485 |
+
"eval_runtime": 4.8268,
|
| 486 |
+
"eval_samples_per_second": 2.486,
|
| 487 |
+
"eval_steps_per_second": 2.486,
|
| 488 |
+
"step": 97
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 17.043478260869566,
|
| 492 |
+
"grad_norm": 0.7182919383049011,
|
| 493 |
+
"learning_rate": 9.971379769661422e-06,
|
| 494 |
+
"loss": 1.122,
|
| 495 |
+
"step": 98
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 17.391304347826086,
|
| 499 |
+
"grad_norm": 0.7512508034706116,
|
| 500 |
+
"learning_rate": 9.966191788709716e-06,
|
| 501 |
+
"loss": 1.131,
|
| 502 |
+
"step": 100
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 17.73913043478261,
|
| 506 |
+
"grad_norm": 0.6947119235992432,
|
| 507 |
+
"learning_rate": 9.960573506572391e-06,
|
| 508 |
+
"loss": 1.0304,
|
| 509 |
+
"step": 102
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 17.91304347826087,
|
| 513 |
+
"eval_loss": 1.0780998468399048,
|
| 514 |
+
"eval_runtime": 4.8327,
|
| 515 |
+
"eval_samples_per_second": 2.483,
|
| 516 |
+
"eval_steps_per_second": 2.483,
|
| 517 |
+
"step": 103
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"epoch": 18.08695652173913,
|
| 521 |
+
"grad_norm": 0.6211488246917725,
|
| 522 |
+
"learning_rate": 9.95452541005172e-06,
|
| 523 |
+
"loss": 1.0439,
|
| 524 |
+
"step": 104
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 18.434782608695652,
|
| 528 |
+
"grad_norm": 0.6497947573661804,
|
| 529 |
+
"learning_rate": 9.948048023191728e-06,
|
| 530 |
+
"loss": 1.0278,
|
| 531 |
+
"step": 106
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 18.782608695652176,
|
| 535 |
+
"grad_norm": 0.5914028882980347,
|
| 536 |
+
"learning_rate": 9.941141907232766e-06,
|
| 537 |
+
"loss": 1.0485,
|
| 538 |
+
"step": 108
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 18.956521739130434,
|
| 542 |
+
"eval_loss": 1.0459355115890503,
|
| 543 |
+
"eval_runtime": 4.8455,
|
| 544 |
+
"eval_samples_per_second": 2.477,
|
| 545 |
+
"eval_steps_per_second": 2.477,
|
| 546 |
+
"step": 109
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 19.130434782608695,
|
| 550 |
+
"grad_norm": 0.6026037931442261,
|
| 551 |
+
"learning_rate": 9.933807660562898e-06,
|
| 552 |
+
"loss": 1.0755,
|
| 553 |
+
"step": 110
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 19.47826086956522,
|
| 557 |
+
"grad_norm": 0.5290880799293518,
|
| 558 |
+
"learning_rate": 9.926045918666045e-06,
|
| 559 |
+
"loss": 1.0554,
|
| 560 |
+
"step": 112
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 19.82608695652174,
|
| 564 |
+
"grad_norm": 0.5054655075073242,
|
| 565 |
+
"learning_rate": 9.91785735406693e-06,
|
| 566 |
+
"loss": 0.9687,
|
| 567 |
+
"step": 114
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 20.0,
|
| 571 |
+
"eval_loss": 1.0257662534713745,
|
| 572 |
+
"eval_runtime": 4.8234,
|
| 573 |
+
"eval_samples_per_second": 2.488,
|
| 574 |
+
"eval_steps_per_second": 2.488,
|
| 575 |
+
"step": 115
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 20.17391304347826,
|
| 579 |
+
"grad_norm": 0.5547760725021362,
|
| 580 |
+
"learning_rate": 9.909242676272797e-06,
|
| 581 |
+
"loss": 0.9625,
|
| 582 |
+
"step": 116
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 20.52173913043478,
|
| 586 |
+
"grad_norm": 0.5321418642997742,
|
| 587 |
+
"learning_rate": 9.90020263171194e-06,
|
| 588 |
+
"loss": 1.0313,
|
| 589 |
+
"step": 118
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 20.869565217391305,
|
| 593 |
+
"grad_norm": 0.4589158296585083,
|
| 594 |
+
"learning_rate": 9.890738003669029e-06,
|
| 595 |
+
"loss": 0.9883,
|
| 596 |
+
"step": 120
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 20.869565217391305,
|
| 600 |
+
"eval_loss": 1.0146735906600952,
|
| 601 |
+
"eval_runtime": 4.8436,
|
| 602 |
+
"eval_samples_per_second": 2.478,
|
| 603 |
+
"eval_steps_per_second": 2.478,
|
| 604 |
+
"step": 120
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 21.217391304347824,
|
| 608 |
+
"grad_norm": 0.47460901737213135,
|
| 609 |
+
"learning_rate": 9.880849612217238e-06,
|
| 610 |
+
"loss": 0.9519,
|
| 611 |
+
"step": 122
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 21.565217391304348,
|
| 615 |
+
"grad_norm": 0.4670533835887909,
|
| 616 |
+
"learning_rate": 9.870538314147194e-06,
|
| 617 |
+
"loss": 1.0113,
|
| 618 |
+
"step": 124
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 21.91304347826087,
|
| 622 |
+
"grad_norm": 0.5945753455162048,
|
| 623 |
+
"learning_rate": 9.859805002892733e-06,
|
| 624 |
+
"loss": 0.974,
|
| 625 |
+
"step": 126
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 21.91304347826087,
|
| 629 |
+
"eval_loss": 1.00125253200531,
|
| 630 |
+
"eval_runtime": 4.8426,
|
| 631 |
+
"eval_samples_per_second": 2.478,
|
| 632 |
+
"eval_steps_per_second": 2.478,
|
| 633 |
+
"step": 126
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 22.26086956521739,
|
| 637 |
+
"grad_norm": 0.45630648732185364,
|
| 638 |
+
"learning_rate": 9.84865060845349e-06,
|
| 639 |
+
"loss": 0.9679,
|
| 640 |
+
"step": 128
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 22.608695652173914,
|
| 644 |
+
"grad_norm": 0.4838283360004425,
|
| 645 |
+
"learning_rate": 9.83707609731432e-06,
|
| 646 |
+
"loss": 0.9776,
|
| 647 |
+
"step": 130
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 22.956521739130434,
|
| 651 |
+
"grad_norm": 0.44602882862091064,
|
| 652 |
+
"learning_rate": 9.825082472361558e-06,
|
| 653 |
+
"loss": 0.9397,
|
| 654 |
+
"step": 132
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 22.956521739130434,
|
| 658 |
+
"eval_loss": 0.9904754757881165,
|
| 659 |
+
"eval_runtime": 4.8474,
|
| 660 |
+
"eval_samples_per_second": 2.476,
|
| 661 |
+
"eval_steps_per_second": 2.476,
|
| 662 |
+
"step": 132
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 23.304347826086957,
|
| 666 |
+
"grad_norm": 0.5826734304428101,
|
| 667 |
+
"learning_rate": 9.812670772796113e-06,
|
| 668 |
+
"loss": 0.9607,
|
| 669 |
+
"step": 134
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 23.652173913043477,
|
| 673 |
+
"grad_norm": 0.4837598204612732,
|
| 674 |
+
"learning_rate": 9.799842074043438e-06,
|
| 675 |
+
"loss": 0.949,
|
| 676 |
+
"step": 136
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 24.0,
|
| 680 |
+
"grad_norm": 0.6160168051719666,
|
| 681 |
+
"learning_rate": 9.786597487660336e-06,
|
| 682 |
+
"loss": 0.9522,
|
| 683 |
+
"step": 138
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 24.0,
|
| 687 |
+
"eval_loss": 0.9816201329231262,
|
| 688 |
+
"eval_runtime": 4.84,
|
| 689 |
+
"eval_samples_per_second": 2.479,
|
| 690 |
+
"eval_steps_per_second": 2.479,
|
| 691 |
+
"step": 138
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 24.347826086956523,
|
| 695 |
+
"grad_norm": 0.5032287836074829,
|
| 696 |
+
"learning_rate": 9.77293816123866e-06,
|
| 697 |
+
"loss": 0.9474,
|
| 698 |
+
"step": 140
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 24.695652173913043,
|
| 702 |
+
"grad_norm": 0.5077723860740662,
|
| 703 |
+
"learning_rate": 9.75886527830587e-06,
|
| 704 |
+
"loss": 0.9115,
|
| 705 |
+
"step": 142
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 24.869565217391305,
|
| 709 |
+
"eval_loss": 0.9739218354225159,
|
| 710 |
+
"eval_runtime": 4.8407,
|
| 711 |
+
"eval_samples_per_second": 2.479,
|
| 712 |
+
"eval_steps_per_second": 2.479,
|
| 713 |
+
"step": 143
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 25.043478260869566,
|
| 717 |
+
"grad_norm": 0.49520373344421387,
|
| 718 |
+
"learning_rate": 9.744380058222483e-06,
|
| 719 |
+
"loss": 0.9696,
|
| 720 |
+
"step": 144
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 25.391304347826086,
|
| 724 |
+
"grad_norm": 0.6057612299919128,
|
| 725 |
+
"learning_rate": 9.729483756076436e-06,
|
| 726 |
+
"loss": 0.9363,
|
| 727 |
+
"step": 146
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 25.73913043478261,
|
| 731 |
+
"grad_norm": 0.5979700088500977,
|
| 732 |
+
"learning_rate": 9.714177662574316e-06,
|
| 733 |
+
"loss": 0.9412,
|
| 734 |
+
"step": 148
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 25.91304347826087,
|
| 738 |
+
"eval_loss": 0.9668495655059814,
|
| 739 |
+
"eval_runtime": 4.8393,
|
| 740 |
+
"eval_samples_per_second": 2.48,
|
| 741 |
+
"eval_steps_per_second": 2.48,
|
| 742 |
+
"step": 149
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 26.08695652173913,
|
| 746 |
+
"grad_norm": 0.5768654942512512,
|
| 747 |
+
"learning_rate": 9.698463103929542e-06,
|
| 748 |
+
"loss": 0.9277,
|
| 749 |
+
"step": 150
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 26.434782608695652,
|
| 753 |
+
"grad_norm": 0.5760251879692078,
|
| 754 |
+
"learning_rate": 9.682341441747446e-06,
|
| 755 |
+
"loss": 0.8601,
|
| 756 |
+
"step": 152
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 26.782608695652176,
|
| 760 |
+
"grad_norm": 0.569760799407959,
|
| 761 |
+
"learning_rate": 9.665814072907293e-06,
|
| 762 |
+
"loss": 0.9168,
|
| 763 |
+
"step": 154
|
| 764 |
+
},
|
| 765 |
+
{
|
| 766 |
+
"epoch": 26.956521739130434,
|
| 767 |
+
"eval_loss": 0.9610000252723694,
|
| 768 |
+
"eval_runtime": 4.8499,
|
| 769 |
+
"eval_samples_per_second": 2.474,
|
| 770 |
+
"eval_steps_per_second": 2.474,
|
| 771 |
+
"step": 155
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 27.130434782608695,
|
| 775 |
+
"grad_norm": 0.5672867894172668,
|
| 776 |
+
"learning_rate": 9.648882429441258e-06,
|
| 777 |
+
"loss": 0.9273,
|
| 778 |
+
"step": 156
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"epoch": 27.47826086956522,
|
| 782 |
+
"grad_norm": 0.5984346866607666,
|
| 783 |
+
"learning_rate": 9.63154797841033e-06,
|
| 784 |
+
"loss": 0.9134,
|
| 785 |
+
"step": 158
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 27.82608695652174,
|
| 789 |
+
"grad_norm": 0.5996063947677612,
|
| 790 |
+
"learning_rate": 9.613812221777212e-06,
|
| 791 |
+
"loss": 0.9461,
|
| 792 |
+
"step": 160
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"epoch": 28.0,
|
| 796 |
+
"eval_loss": 0.9547294974327087,
|
| 797 |
+
"eval_runtime": 4.8363,
|
| 798 |
+
"eval_samples_per_second": 2.481,
|
| 799 |
+
"eval_steps_per_second": 2.481,
|
| 800 |
+
"step": 161
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 28.17391304347826,
|
| 804 |
+
"grad_norm": 0.5729570984840393,
|
| 805 |
+
"learning_rate": 9.595676696276173e-06,
|
| 806 |
+
"loss": 0.8601,
|
| 807 |
+
"step": 162
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 28.52173913043478,
|
| 811 |
+
"grad_norm": 0.6671696305274963,
|
| 812 |
+
"learning_rate": 9.577142973279896e-06,
|
| 813 |
+
"loss": 0.9214,
|
| 814 |
+
"step": 164
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 28.869565217391305,
|
| 818 |
+
"grad_norm": 0.6552798748016357,
|
| 819 |
+
"learning_rate": 9.55821265866333e-06,
|
| 820 |
+
"loss": 0.8579,
|
| 821 |
+
"step": 166
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 28.869565217391305,
|
| 825 |
+
"eval_loss": 0.9499099850654602,
|
| 826 |
+
"eval_runtime": 4.8467,
|
| 827 |
+
"eval_samples_per_second": 2.476,
|
| 828 |
+
"eval_steps_per_second": 2.476,
|
| 829 |
+
"step": 166
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 29.217391304347824,
|
| 833 |
+
"grad_norm": 0.6634982824325562,
|
| 834 |
+
"learning_rate": 9.538887392664544e-06,
|
| 835 |
+
"loss": 0.869,
|
| 836 |
+
"step": 168
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 29.565217391304348,
|
| 840 |
+
"grad_norm": 0.6576085090637207,
|
| 841 |
+
"learning_rate": 9.519168849742603e-06,
|
| 842 |
+
"loss": 0.9128,
|
| 843 |
+
"step": 170
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 29.91304347826087,
|
| 847 |
+
"grad_norm": 0.6544057130813599,
|
| 848 |
+
"learning_rate": 9.499058738432492e-06,
|
| 849 |
+
"loss": 0.8857,
|
| 850 |
+
"step": 172
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 29.91304347826087,
|
| 854 |
+
"eval_loss": 0.9454047083854675,
|
| 855 |
+
"eval_runtime": 4.8567,
|
| 856 |
+
"eval_samples_per_second": 2.471,
|
| 857 |
+
"eval_steps_per_second": 2.471,
|
| 858 |
+
"step": 172
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 30.26086956521739,
|
| 862 |
+
"grad_norm": 0.7192568778991699,
|
| 863 |
+
"learning_rate": 9.478558801197065e-06,
|
| 864 |
+
"loss": 0.8608,
|
| 865 |
+
"step": 174
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 30.608695652173914,
|
| 869 |
+
"grad_norm": 0.8773357272148132,
|
| 870 |
+
"learning_rate": 9.457670814276083e-06,
|
| 871 |
+
"loss": 0.8683,
|
| 872 |
+
"step": 176
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 30.956521739130434,
|
| 876 |
+
"grad_norm": 0.6999642252922058,
|
| 877 |
+
"learning_rate": 9.436396587532297e-06,
|
| 878 |
+
"loss": 0.8465,
|
| 879 |
+
"step": 178
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 30.956521739130434,
|
| 883 |
+
"eval_loss": 0.9405279755592346,
|
| 884 |
+
"eval_runtime": 4.8418,
|
| 885 |
+
"eval_samples_per_second": 2.478,
|
| 886 |
+
"eval_steps_per_second": 2.478,
|
| 887 |
+
"step": 178
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 31.304347826086957,
|
| 891 |
+
"grad_norm": 0.8239638805389404,
|
| 892 |
+
"learning_rate": 9.414737964294636e-06,
|
| 893 |
+
"loss": 0.911,
|
| 894 |
+
"step": 180
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 31.652173913043477,
|
| 898 |
+
"grad_norm": 0.672042965888977,
|
| 899 |
+
"learning_rate": 9.392696821198488e-06,
|
| 900 |
+
"loss": 0.8287,
|
| 901 |
+
"step": 182
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 32.0,
|
| 905 |
+
"grad_norm": 0.8173245191574097,
|
| 906 |
+
"learning_rate": 9.370275068023097e-06,
|
| 907 |
+
"loss": 0.8681,
|
| 908 |
+
"step": 184
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 32.0,
|
| 912 |
+
"eval_loss": 0.939335286617279,
|
| 913 |
+
"eval_runtime": 4.8393,
|
| 914 |
+
"eval_samples_per_second": 2.48,
|
| 915 |
+
"eval_steps_per_second": 2.48,
|
| 916 |
+
"step": 184
|
| 917 |
+
},
|
| 918 |
+
{
|
| 919 |
+
"epoch": 32.34782608695652,
|
| 920 |
+
"grad_norm": 0.7714847326278687,
|
| 921 |
+
"learning_rate": 9.347474647526095e-06,
|
| 922 |
+
"loss": 0.8525,
|
| 923 |
+
"step": 186
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 32.69565217391305,
|
| 927 |
+
"grad_norm": 0.7664777040481567,
|
| 928 |
+
"learning_rate": 9.324297535275156e-06,
|
| 929 |
+
"loss": 0.8257,
|
| 930 |
+
"step": 188
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 32.869565217391305,
|
| 934 |
+
"eval_loss": 0.9344443678855896,
|
| 935 |
+
"eval_runtime": 4.8421,
|
| 936 |
+
"eval_samples_per_second": 2.478,
|
| 937 |
+
"eval_steps_per_second": 2.478,
|
| 938 |
+
"step": 189
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 33.04347826086956,
|
| 942 |
+
"grad_norm": 0.9124040007591248,
|
| 943 |
+
"learning_rate": 9.30074573947683e-06,
|
| 944 |
+
"loss": 0.8519,
|
| 945 |
+
"step": 190
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 33.391304347826086,
|
| 949 |
+
"grad_norm": 0.8003515005111694,
|
| 950 |
+
"learning_rate": 9.276821300802535e-06,
|
| 951 |
+
"loss": 0.8863,
|
| 952 |
+
"step": 192
|
| 953 |
+
},
|
| 954 |
+
{
|
| 955 |
+
"epoch": 33.73913043478261,
|
| 956 |
+
"grad_norm": 0.8585532903671265,
|
| 957 |
+
"learning_rate": 9.25252629221175e-06,
|
| 958 |
+
"loss": 0.8425,
|
| 959 |
+
"step": 194
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 33.91304347826087,
|
| 963 |
+
"eval_loss": 0.9336052536964417,
|
| 964 |
+
"eval_runtime": 4.8393,
|
| 965 |
+
"eval_samples_per_second": 2.48,
|
| 966 |
+
"eval_steps_per_second": 2.48,
|
| 967 |
+
"step": 195
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"epoch": 34.08695652173913,
|
| 971 |
+
"grad_norm": 0.8088707327842712,
|
| 972 |
+
"learning_rate": 9.227862818772392e-06,
|
| 973 |
+
"loss": 0.7927,
|
| 974 |
+
"step": 196
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 34.43478260869565,
|
| 978 |
+
"grad_norm": 1.031660795211792,
|
| 979 |
+
"learning_rate": 9.202833017478421e-06,
|
| 980 |
+
"loss": 0.8326,
|
| 981 |
+
"step": 198
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 34.78260869565217,
|
| 985 |
+
"grad_norm": 0.9502612352371216,
|
| 986 |
+
"learning_rate": 9.177439057064684e-06,
|
| 987 |
+
"loss": 0.8405,
|
| 988 |
+
"step": 200
|
| 989 |
+
},
|
| 990 |
+
{
|
| 991 |
+
"epoch": 34.95652173913044,
|
| 992 |
+
"eval_loss": 0.9280831217765808,
|
| 993 |
+
"eval_runtime": 4.8396,
|
| 994 |
+
"eval_samples_per_second": 2.48,
|
| 995 |
+
"eval_steps_per_second": 2.48,
|
| 996 |
+
"step": 201
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 35.130434782608695,
|
| 1000 |
+
"grad_norm": 0.836633026599884,
|
| 1001 |
+
"learning_rate": 9.151683137818989e-06,
|
| 1002 |
+
"loss": 0.8087,
|
| 1003 |
+
"step": 202
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 35.47826086956522,
|
| 1007 |
+
"grad_norm": 0.8722138404846191,
|
| 1008 |
+
"learning_rate": 9.125567491391476e-06,
|
| 1009 |
+
"loss": 0.8281,
|
| 1010 |
+
"step": 204
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 35.82608695652174,
|
| 1014 |
+
"grad_norm": 0.9598701596260071,
|
| 1015 |
+
"learning_rate": 9.099094380601244e-06,
|
| 1016 |
+
"loss": 0.8101,
|
| 1017 |
+
"step": 206
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 36.0,
|
| 1021 |
+
"eval_loss": 0.9282541275024414,
|
| 1022 |
+
"eval_runtime": 4.8408,
|
| 1023 |
+
"eval_samples_per_second": 2.479,
|
| 1024 |
+
"eval_steps_per_second": 2.479,
|
| 1025 |
+
"step": 207
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 36.17391304347826,
|
| 1029 |
+
"grad_norm": 0.9185284972190857,
|
| 1030 |
+
"learning_rate": 9.072266099240286e-06,
|
| 1031 |
+
"loss": 0.8047,
|
| 1032 |
+
"step": 208
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 36.52173913043478,
|
| 1036 |
+
"grad_norm": 0.9987873435020447,
|
| 1037 |
+
"learning_rate": 9.045084971874738e-06,
|
| 1038 |
+
"loss": 0.8261,
|
| 1039 |
+
"step": 210
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 36.869565217391305,
|
| 1043 |
+
"grad_norm": 0.9007511138916016,
|
| 1044 |
+
"learning_rate": 9.017553353643479e-06,
|
| 1045 |
+
"loss": 0.7808,
|
| 1046 |
+
"step": 212
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 36.869565217391305,
|
| 1050 |
+
"eval_loss": 0.9258975982666016,
|
| 1051 |
+
"eval_runtime": 4.8444,
|
| 1052 |
+
"eval_samples_per_second": 2.477,
|
| 1053 |
+
"eval_steps_per_second": 2.477,
|
| 1054 |
+
"step": 212
|
| 1055 |
+
},
|
| 1056 |
+
{
|
| 1057 |
+
"epoch": 37.21739130434783,
|
| 1058 |
+
"grad_norm": 0.9600070714950562,
|
| 1059 |
+
"learning_rate": 8.989673630054044e-06,
|
| 1060 |
+
"loss": 0.8273,
|
| 1061 |
+
"step": 214
|
| 1062 |
+
},
|
| 1063 |
+
{
|
| 1064 |
+
"epoch": 37.56521739130435,
|
| 1065 |
+
"grad_norm": 0.8776330351829529,
|
| 1066 |
+
"learning_rate": 8.961448216775955e-06,
|
| 1067 |
+
"loss": 0.7458,
|
| 1068 |
+
"step": 216
|
| 1069 |
+
},
|
| 1070 |
+
{
|
| 1071 |
+
"epoch": 37.91304347826087,
|
| 1072 |
+
"grad_norm": 1.0257493257522583,
|
| 1073 |
+
"learning_rate": 8.932879559431392e-06,
|
| 1074 |
+
"loss": 0.7971,
|
| 1075 |
+
"step": 218
|
| 1076 |
+
},
|
| 1077 |
+
{
|
| 1078 |
+
"epoch": 37.91304347826087,
|
| 1079 |
+
"eval_loss": 0.9259226322174072,
|
| 1080 |
+
"eval_runtime": 4.8247,
|
| 1081 |
+
"eval_samples_per_second": 2.487,
|
| 1082 |
+
"eval_steps_per_second": 2.487,
|
| 1083 |
+
"step": 218
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 38.26086956521739,
|
| 1087 |
+
"grad_norm": 0.9936304092407227,
|
| 1088 |
+
"learning_rate": 8.903970133383297e-06,
|
| 1089 |
+
"loss": 0.8089,
|
| 1090 |
+
"step": 220
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"epoch": 38.608695652173914,
|
| 1094 |
+
"grad_norm": 0.9844217896461487,
|
| 1095 |
+
"learning_rate": 8.874722443520898e-06,
|
| 1096 |
+
"loss": 0.7994,
|
| 1097 |
+
"step": 222
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 38.95652173913044,
|
| 1101 |
+
"grad_norm": 1.0099091529846191,
|
| 1102 |
+
"learning_rate": 8.845139024042664e-06,
|
| 1103 |
+
"loss": 0.7766,
|
| 1104 |
+
"step": 224
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 38.95652173913044,
|
| 1108 |
+
"eval_loss": 0.9234599471092224,
|
| 1109 |
+
"eval_runtime": 4.8243,
|
| 1110 |
+
"eval_samples_per_second": 2.487,
|
| 1111 |
+
"eval_steps_per_second": 2.487,
|
| 1112 |
+
"step": 224
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 39.30434782608695,
|
| 1116 |
+
"grad_norm": 0.9933149814605713,
|
| 1117 |
+
"learning_rate": 8.815222438236726e-06,
|
| 1118 |
+
"loss": 0.7425,
|
| 1119 |
+
"step": 226
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 39.65217391304348,
|
| 1123 |
+
"grad_norm": 0.9792707562446594,
|
| 1124 |
+
"learning_rate": 8.784975278258783e-06,
|
| 1125 |
+
"loss": 0.7805,
|
| 1126 |
+
"step": 228
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 40.0,
|
| 1130 |
+
"grad_norm": 1.1036958694458008,
|
| 1131 |
+
"learning_rate": 8.754400164907496e-06,
|
| 1132 |
+
"loss": 0.7748,
|
| 1133 |
+
"step": 230
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 40.0,
|
| 1137 |
+
"eval_loss": 0.9245247840881348,
|
| 1138 |
+
"eval_runtime": 4.8317,
|
| 1139 |
+
"eval_samples_per_second": 2.484,
|
| 1140 |
+
"eval_steps_per_second": 2.484,
|
| 1141 |
+
"step": 230
|
| 1142 |
+
},
|
| 1143 |
+
{
|
| 1144 |
+
"epoch": 40.34782608695652,
|
| 1145 |
+
"grad_norm": 1.0168761014938354,
|
| 1146 |
+
"learning_rate": 8.723499747397415e-06,
|
| 1147 |
+
"loss": 0.7756,
|
| 1148 |
+
"step": 232
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 40.69565217391305,
|
| 1152 |
+
"grad_norm": 1.0455681085586548,
|
| 1153 |
+
"learning_rate": 8.692276703129421e-06,
|
| 1154 |
+
"loss": 0.7476,
|
| 1155 |
+
"step": 234
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 40.869565217391305,
|
| 1159 |
+
"eval_loss": 0.9252880215644836,
|
| 1160 |
+
"eval_runtime": 4.8248,
|
| 1161 |
+
"eval_samples_per_second": 2.487,
|
| 1162 |
+
"eval_steps_per_second": 2.487,
|
| 1163 |
+
"step": 235
|
| 1164 |
+
},
|
| 1165 |
+
{
|
| 1166 |
+
"epoch": 41.04347826086956,
|
| 1167 |
+
"grad_norm": 1.2682240009307861,
|
| 1168 |
+
"learning_rate": 8.660733737458751e-06,
|
| 1169 |
+
"loss": 0.7633,
|
| 1170 |
+
"step": 236
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 41.391304347826086,
|
| 1174 |
+
"grad_norm": 1.054377555847168,
|
| 1175 |
+
"learning_rate": 8.628873583460593e-06,
|
| 1176 |
+
"loss": 0.7528,
|
| 1177 |
+
"step": 238
|
| 1178 |
+
},
|
| 1179 |
+
{
|
| 1180 |
+
"epoch": 41.73913043478261,
|
| 1181 |
+
"grad_norm": 1.2782171964645386,
|
| 1182 |
+
"learning_rate": 8.596699001693257e-06,
|
| 1183 |
+
"loss": 0.7007,
|
| 1184 |
+
"step": 240
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 41.91304347826087,
|
| 1188 |
+
"eval_loss": 0.922440230846405,
|
| 1189 |
+
"eval_runtime": 4.8272,
|
| 1190 |
+
"eval_samples_per_second": 2.486,
|
| 1191 |
+
"eval_steps_per_second": 2.486,
|
| 1192 |
+
"step": 241
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 42.08695652173913,
|
| 1196 |
+
"grad_norm": 1.09280526638031,
|
| 1197 |
+
"learning_rate": 8.564212779959003e-06,
|
| 1198 |
+
"loss": 0.7865,
|
| 1199 |
+
"step": 242
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 42.43478260869565,
|
| 1203 |
+
"grad_norm": 1.2800565958023071,
|
| 1204 |
+
"learning_rate": 8.531417733062476e-06,
|
| 1205 |
+
"loss": 0.742,
|
| 1206 |
+
"step": 244
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 42.78260869565217,
|
| 1210 |
+
"grad_norm": 1.2969675064086914,
|
| 1211 |
+
"learning_rate": 8.498316702566828e-06,
|
| 1212 |
+
"loss": 0.741,
|
| 1213 |
+
"step": 246
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 42.95652173913044,
|
| 1217 |
+
"eval_loss": 0.9261074066162109,
|
| 1218 |
+
"eval_runtime": 4.8284,
|
| 1219 |
+
"eval_samples_per_second": 2.485,
|
| 1220 |
+
"eval_steps_per_second": 2.485,
|
| 1221 |
+
"step": 247
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 43.130434782608695,
|
| 1225 |
+
"grad_norm": 1.0573549270629883,
|
| 1226 |
+
"learning_rate": 8.464912556547486e-06,
|
| 1227 |
+
"loss": 0.7027,
|
| 1228 |
+
"step": 248
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 43.47826086956522,
|
| 1232 |
+
"grad_norm": 1.2901216745376587,
|
| 1233 |
+
"learning_rate": 8.43120818934367e-06,
|
| 1234 |
+
"loss": 0.7325,
|
| 1235 |
+
"step": 250
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 43.82608695652174,
|
| 1239 |
+
"grad_norm": 1.110465407371521,
|
| 1240 |
+
"learning_rate": 8.397206521307584e-06,
|
| 1241 |
+
"loss": 0.7371,
|
| 1242 |
+
"step": 252
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 44.0,
|
| 1246 |
+
"eval_loss": 0.9239481091499329,
|
| 1247 |
+
"eval_runtime": 4.8243,
|
| 1248 |
+
"eval_samples_per_second": 2.487,
|
| 1249 |
+
"eval_steps_per_second": 2.487,
|
| 1250 |
+
"step": 253
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 44.17391304347826,
|
| 1254 |
+
"grad_norm": 1.1729587316513062,
|
| 1255 |
+
"learning_rate": 8.362910498551402e-06,
|
| 1256 |
+
"loss": 0.7156,
|
| 1257 |
+
"step": 254
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 44.52173913043478,
|
| 1261 |
+
"grad_norm": 1.1838419437408447,
|
| 1262 |
+
"learning_rate": 8.328323092691985e-06,
|
| 1263 |
+
"loss": 0.712,
|
| 1264 |
+
"step": 256
|
| 1265 |
+
},
|
| 1266 |
+
{
|
| 1267 |
+
"epoch": 44.869565217391305,
|
| 1268 |
+
"grad_norm": 1.4539400339126587,
|
| 1269 |
+
"learning_rate": 8.293447300593402e-06,
|
| 1270 |
+
"loss": 0.7239,
|
| 1271 |
+
"step": 258
|
| 1272 |
+
},
|
| 1273 |
+
{
|
| 1274 |
+
"epoch": 44.869565217391305,
|
| 1275 |
+
"eval_loss": 0.9323117136955261,
|
| 1276 |
+
"eval_runtime": 4.8254,
|
| 1277 |
+
"eval_samples_per_second": 2.487,
|
| 1278 |
+
"eval_steps_per_second": 2.487,
|
| 1279 |
+
"step": 258
|
| 1280 |
+
},
|
| 1281 |
+
{
|
| 1282 |
+
"epoch": 45.21739130434783,
|
| 1283 |
+
"grad_norm": 1.2814104557037354,
|
| 1284 |
+
"learning_rate": 8.258286144107277e-06,
|
| 1285 |
+
"loss": 0.729,
|
| 1286 |
+
"step": 260
|
| 1287 |
+
},
|
| 1288 |
+
{
|
| 1289 |
+
"epoch": 45.56521739130435,
|
| 1290 |
+
"grad_norm": 1.1663718223571777,
|
| 1291 |
+
"learning_rate": 8.222842669810936e-06,
|
| 1292 |
+
"loss": 0.6689,
|
| 1293 |
+
"step": 262
|
| 1294 |
+
},
|
| 1295 |
+
{
|
| 1296 |
+
"epoch": 45.91304347826087,
|
| 1297 |
+
"grad_norm": 1.2235040664672852,
|
| 1298 |
+
"learning_rate": 8.18711994874345e-06,
|
| 1299 |
+
"loss": 0.671,
|
| 1300 |
+
"step": 264
|
| 1301 |
+
},
|
| 1302 |
+
{
|
| 1303 |
+
"epoch": 45.91304347826087,
|
| 1304 |
+
"eval_loss": 0.9268998503684998,
|
| 1305 |
+
"eval_runtime": 4.8329,
|
| 1306 |
+
"eval_samples_per_second": 2.483,
|
| 1307 |
+
"eval_steps_per_second": 2.483,
|
| 1308 |
+
"step": 264
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 46.26086956521739,
|
| 1312 |
+
"grad_norm": 1.2671639919281006,
|
| 1313 |
+
"learning_rate": 8.151121076139534e-06,
|
| 1314 |
+
"loss": 0.7247,
|
| 1315 |
+
"step": 266
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 46.608695652173914,
|
| 1319 |
+
"grad_norm": 1.2693313360214233,
|
| 1320 |
+
"learning_rate": 8.11484917116136e-06,
|
| 1321 |
+
"loss": 0.6697,
|
| 1322 |
+
"step": 268
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 46.95652173913044,
|
| 1326 |
+
"grad_norm": 1.452881932258606,
|
| 1327 |
+
"learning_rate": 8.078307376628292e-06,
|
| 1328 |
+
"loss": 0.7312,
|
| 1329 |
+
"step": 270
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 46.95652173913044,
|
| 1333 |
+
"eval_loss": 0.9332544207572937,
|
| 1334 |
+
"eval_runtime": 4.8317,
|
| 1335 |
+
"eval_samples_per_second": 2.484,
|
| 1336 |
+
"eval_steps_per_second": 2.484,
|
| 1337 |
+
"step": 270
|
| 1338 |
+
},
|
| 1339 |
+
{
|
| 1340 |
+
"epoch": 47.30434782608695,
|
| 1341 |
+
"grad_norm": 1.3550682067871094,
|
| 1342 |
+
"learning_rate": 8.041498858744572e-06,
|
| 1343 |
+
"loss": 0.7067,
|
| 1344 |
+
"step": 272
|
| 1345 |
+
},
|
| 1346 |
+
{
|
| 1347 |
+
"epoch": 47.65217391304348,
|
| 1348 |
+
"grad_norm": 1.3532733917236328,
|
| 1349 |
+
"learning_rate": 8.004426806824985e-06,
|
| 1350 |
+
"loss": 0.6586,
|
| 1351 |
+
"step": 274
|
| 1352 |
+
},
|
| 1353 |
+
{
|
| 1354 |
+
"epoch": 48.0,
|
| 1355 |
+
"grad_norm": 1.4842863082885742,
|
| 1356 |
+
"learning_rate": 7.967094433018508e-06,
|
| 1357 |
+
"loss": 0.6826,
|
| 1358 |
+
"step": 276
|
| 1359 |
+
},
|
| 1360 |
+
{
|
| 1361 |
+
"epoch": 48.0,
|
| 1362 |
+
"eval_loss": 0.934523344039917,
|
| 1363 |
+
"eval_runtime": 4.8197,
|
| 1364 |
+
"eval_samples_per_second": 2.49,
|
| 1365 |
+
"eval_steps_per_second": 2.49,
|
| 1366 |
+
"step": 276
|
| 1367 |
+
},
|
| 1368 |
+
{
|
| 1369 |
+
"epoch": 48.34782608695652,
|
| 1370 |
+
"grad_norm": 1.209937334060669,
|
| 1371 |
+
"learning_rate": 7.929504972030003e-06,
|
| 1372 |
+
"loss": 0.6882,
|
| 1373 |
+
"step": 278
|
| 1374 |
+
},
|
| 1375 |
+
{
|
| 1376 |
+
"epoch": 48.69565217391305,
|
| 1377 |
+
"grad_norm": 1.5903738737106323,
|
| 1378 |
+
"learning_rate": 7.891661680839932e-06,
|
| 1379 |
+
"loss": 0.6472,
|
| 1380 |
+
"step": 280
|
| 1381 |
+
},
|
| 1382 |
+
{
|
| 1383 |
+
"epoch": 48.869565217391305,
|
| 1384 |
+
"eval_loss": 0.9393181204795837,
|
| 1385 |
+
"eval_runtime": 4.8289,
|
| 1386 |
+
"eval_samples_per_second": 2.485,
|
| 1387 |
+
"eval_steps_per_second": 2.485,
|
| 1388 |
+
"step": 281
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 48.869565217391305,
|
| 1392 |
+
"step": 281,
|
| 1393 |
+
"total_flos": 3.3738755183476736e+16,
|
| 1394 |
+
"train_loss": 1.2498505263990354,
|
| 1395 |
+
"train_runtime": 2644.3439,
|
| 1396 |
+
"train_samples_per_second": 2.609,
|
| 1397 |
+
"train_steps_per_second": 0.284
|
| 1398 |
+
}
|
| 1399 |
+
],
|
| 1400 |
+
"logging_steps": 2,
|
| 1401 |
+
"max_steps": 750,
|
| 1402 |
+
"num_input_tokens_seen": 0,
|
| 1403 |
+
"num_train_epochs": 150,
|
| 1404 |
+
"save_steps": 25,
|
| 1405 |
+
"stateful_callbacks": {
|
| 1406 |
+
"EarlyStoppingCallback": {
|
| 1407 |
+
"args": {
|
| 1408 |
+
"early_stopping_patience": 7,
|
| 1409 |
+
"early_stopping_threshold": 0.0
|
| 1410 |
+
},
|
| 1411 |
+
"attributes": {
|
| 1412 |
+
"early_stopping_patience_counter": 0
|
| 1413 |
+
}
|
| 1414 |
+
},
|
| 1415 |
+
"TrainerControl": {
|
| 1416 |
+
"args": {
|
| 1417 |
+
"should_epoch_stop": false,
|
| 1418 |
+
"should_evaluate": false,
|
| 1419 |
+
"should_log": false,
|
| 1420 |
+
"should_save": true,
|
| 1421 |
+
"should_training_stop": true
|
| 1422 |
+
},
|
| 1423 |
+
"attributes": {}
|
| 1424 |
+
}
|
| 1425 |
+
},
|
| 1426 |
+
"total_flos": 3.3738755183476736e+16,
|
| 1427 |
+
"train_batch_size": 1,
|
| 1428 |
+
"trial_name": null,
|
| 1429 |
+
"trial_params": null
|
| 1430 |
+
}
|