Commit
•
2f78413
1
Parent(s):
7d02e2e
Model save
Browse files- README.md +89 -0
- adapter_model.safetensors +1 -1
- all_results.json +9 -0
- train_results.json +9 -0
- trainer_state.json +1217 -0
README.md
ADDED
|
@@ -0,0 +1,89 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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_120-samples_config-3
|
| 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_120-samples_config-3
|
| 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 the None dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 1.5912
|
| 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 |
+
| 1.9625 | 1.0 | 11 | 2.0994 |
|
| 57 |
+
| 2.1365 | 2.0 | 22 | 2.0816 |
|
| 58 |
+
| 2.1371 | 3.0 | 33 | 2.0467 |
|
| 59 |
+
| 2.0536 | 4.0 | 44 | 1.9862 |
|
| 60 |
+
| 1.8317 | 5.0 | 55 | 1.8956 |
|
| 61 |
+
| 1.7607 | 6.0 | 66 | 1.7668 |
|
| 62 |
+
| 1.6452 | 7.0 | 77 | 1.6453 |
|
| 63 |
+
| 1.548 | 8.0 | 88 | 1.5728 |
|
| 64 |
+
| 1.4631 | 9.0 | 99 | 1.5217 |
|
| 65 |
+
| 1.4126 | 10.0 | 110 | 1.4711 |
|
| 66 |
+
| 1.3079 | 11.0 | 121 | 1.4176 |
|
| 67 |
+
| 1.3012 | 12.0 | 132 | 1.3769 |
|
| 68 |
+
| 1.2575 | 13.0 | 143 | 1.3423 |
|
| 69 |
+
| 1.2537 | 14.0 | 154 | 1.3098 |
|
| 70 |
+
| 1.1994 | 15.0 | 165 | 1.2874 |
|
| 71 |
+
| 1.1054 | 16.0 | 176 | 1.2713 |
|
| 72 |
+
| 1.0452 | 17.0 | 187 | 1.2680 |
|
| 73 |
+
| 1.0716 | 18.0 | 198 | 1.2659 |
|
| 74 |
+
| 0.9207 | 19.0 | 209 | 1.2755 |
|
| 75 |
+
| 0.8712 | 20.0 | 220 | 1.2918 |
|
| 76 |
+
| 0.8179 | 21.0 | 231 | 1.3371 |
|
| 77 |
+
| 0.6485 | 22.0 | 242 | 1.3561 |
|
| 78 |
+
| 0.6958 | 23.0 | 253 | 1.4414 |
|
| 79 |
+
| 0.5845 | 24.0 | 264 | 1.5147 |
|
| 80 |
+
| 0.5274 | 25.0 | 275 | 1.5912 |
|
| 81 |
+
|
| 82 |
+
|
| 83 |
+
### Framework versions
|
| 84 |
+
|
| 85 |
+
- PEFT 0.12.0
|
| 86 |
+
- Transformers 4.44.0
|
| 87 |
+
- Pytorch 2.1.2+cu121
|
| 88 |
+
- Datasets 2.20.0
|
| 89 |
+
- 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 sha256:4d0d8c38ec1320a386e00211b36bdd4b23d8014e309e050a2372bc75a038dbe0
|
| 3 |
size 167832240
|
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 25.0,
|
| 3 |
+
"total_flos": 3.3769591557586944e+16,
|
| 4 |
+
"train_loss": 1.3221848821640014,
|
| 5 |
+
"train_runtime": 2580.936,
|
| 6 |
+
"train_samples": 88,
|
| 7 |
+
"train_samples_per_second": 5.114,
|
| 8 |
+
"train_steps_per_second": 0.639
|
| 9 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 25.0,
|
| 3 |
+
"total_flos": 3.3769591557586944e+16,
|
| 4 |
+
"train_loss": 1.3221848821640014,
|
| 5 |
+
"train_runtime": 2580.936,
|
| 6 |
+
"train_samples": 88,
|
| 7 |
+
"train_samples_per_second": 5.114,
|
| 8 |
+
"train_steps_per_second": 0.639
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1217 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.2658852338790894,
|
| 3 |
+
"best_model_checkpoint": "data/Llama-31-8B_task-1_120-samples_config-3/checkpoint-198",
|
| 4 |
+
"epoch": 25.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 275,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.09090909090909091,
|
| 13 |
+
"grad_norm": 1.9471415281295776,
|
| 14 |
+
"learning_rate": 6.060606060606061e-08,
|
| 15 |
+
"loss": 2.2569,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.18181818181818182,
|
| 20 |
+
"grad_norm": 1.9496530294418335,
|
| 21 |
+
"learning_rate": 1.2121212121212122e-07,
|
| 22 |
+
"loss": 2.3228,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.36363636363636365,
|
| 27 |
+
"grad_norm": 1.717644453048706,
|
| 28 |
+
"learning_rate": 2.4242424242424244e-07,
|
| 29 |
+
"loss": 2.0831,
|
| 30 |
+
"step": 4
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.5454545454545454,
|
| 34 |
+
"grad_norm": 1.5924347639083862,
|
| 35 |
+
"learning_rate": 3.6363636363636366e-07,
|
| 36 |
+
"loss": 2.0746,
|
| 37 |
+
"step": 6
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.7272727272727273,
|
| 41 |
+
"grad_norm": 1.8148092031478882,
|
| 42 |
+
"learning_rate": 4.848484848484849e-07,
|
| 43 |
+
"loss": 2.1661,
|
| 44 |
+
"step": 8
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.9090909090909091,
|
| 48 |
+
"grad_norm": 1.6654292345046997,
|
| 49 |
+
"learning_rate": 6.060606060606061e-07,
|
| 50 |
+
"loss": 1.9625,
|
| 51 |
+
"step": 10
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 1.0,
|
| 55 |
+
"eval_loss": 2.0993740558624268,
|
| 56 |
+
"eval_runtime": 9.6328,
|
| 57 |
+
"eval_samples_per_second": 2.491,
|
| 58 |
+
"eval_steps_per_second": 2.491,
|
| 59 |
+
"step": 11
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 1.0909090909090908,
|
| 63 |
+
"grad_norm": 1.543703556060791,
|
| 64 |
+
"learning_rate": 7.272727272727273e-07,
|
| 65 |
+
"loss": 1.9298,
|
| 66 |
+
"step": 12
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 1.2727272727272727,
|
| 70 |
+
"grad_norm": 1.8203456401824951,
|
| 71 |
+
"learning_rate": 8.484848484848486e-07,
|
| 72 |
+
"loss": 2.1289,
|
| 73 |
+
"step": 14
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 1.4545454545454546,
|
| 77 |
+
"grad_norm": 1.7504804134368896,
|
| 78 |
+
"learning_rate": 9.696969696969698e-07,
|
| 79 |
+
"loss": 2.153,
|
| 80 |
+
"step": 16
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 1.6363636363636362,
|
| 84 |
+
"grad_norm": 1.895839810371399,
|
| 85 |
+
"learning_rate": 1.090909090909091e-06,
|
| 86 |
+
"loss": 2.0811,
|
| 87 |
+
"step": 18
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 1.8181818181818183,
|
| 91 |
+
"grad_norm": 1.7807648181915283,
|
| 92 |
+
"learning_rate": 1.2121212121212122e-06,
|
| 93 |
+
"loss": 2.0446,
|
| 94 |
+
"step": 20
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 2.0,
|
| 98 |
+
"grad_norm": 1.8615657091140747,
|
| 99 |
+
"learning_rate": 1.3333333333333334e-06,
|
| 100 |
+
"loss": 2.1365,
|
| 101 |
+
"step": 22
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 2.0,
|
| 105 |
+
"eval_loss": 2.0816335678100586,
|
| 106 |
+
"eval_runtime": 9.6405,
|
| 107 |
+
"eval_samples_per_second": 2.49,
|
| 108 |
+
"eval_steps_per_second": 2.49,
|
| 109 |
+
"step": 22
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 2.1818181818181817,
|
| 113 |
+
"grad_norm": 1.8219581842422485,
|
| 114 |
+
"learning_rate": 1.4545454545454546e-06,
|
| 115 |
+
"loss": 2.1017,
|
| 116 |
+
"step": 24
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 2.3636363636363638,
|
| 120 |
+
"grad_norm": 1.6915614604949951,
|
| 121 |
+
"learning_rate": 1.5757575757575759e-06,
|
| 122 |
+
"loss": 2.0744,
|
| 123 |
+
"step": 26
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 2.5454545454545454,
|
| 127 |
+
"grad_norm": 1.8501787185668945,
|
| 128 |
+
"learning_rate": 1.6969696969696973e-06,
|
| 129 |
+
"loss": 2.0474,
|
| 130 |
+
"step": 28
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 2.7272727272727275,
|
| 134 |
+
"grad_norm": 1.6685246229171753,
|
| 135 |
+
"learning_rate": 1.8181818181818183e-06,
|
| 136 |
+
"loss": 1.9084,
|
| 137 |
+
"step": 30
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 2.909090909090909,
|
| 141 |
+
"grad_norm": 2.073890209197998,
|
| 142 |
+
"learning_rate": 1.9393939393939395e-06,
|
| 143 |
+
"loss": 2.1371,
|
| 144 |
+
"step": 32
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 3.0,
|
| 148 |
+
"eval_loss": 2.0466740131378174,
|
| 149 |
+
"eval_runtime": 9.6342,
|
| 150 |
+
"eval_samples_per_second": 2.491,
|
| 151 |
+
"eval_steps_per_second": 2.491,
|
| 152 |
+
"step": 33
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 3.090909090909091,
|
| 156 |
+
"grad_norm": 1.7652820348739624,
|
| 157 |
+
"learning_rate": 2.0606060606060607e-06,
|
| 158 |
+
"loss": 2.1285,
|
| 159 |
+
"step": 34
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 3.2727272727272725,
|
| 163 |
+
"grad_norm": 2.0258305072784424,
|
| 164 |
+
"learning_rate": 2.181818181818182e-06,
|
| 165 |
+
"loss": 2.0643,
|
| 166 |
+
"step": 36
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 3.4545454545454546,
|
| 170 |
+
"grad_norm": 1.8539706468582153,
|
| 171 |
+
"learning_rate": 2.303030303030303e-06,
|
| 172 |
+
"loss": 1.9892,
|
| 173 |
+
"step": 38
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 3.6363636363636362,
|
| 177 |
+
"grad_norm": 1.8331531286239624,
|
| 178 |
+
"learning_rate": 2.4242424242424244e-06,
|
| 179 |
+
"loss": 1.9928,
|
| 180 |
+
"step": 40
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 3.8181818181818183,
|
| 184 |
+
"grad_norm": 1.7377302646636963,
|
| 185 |
+
"learning_rate": 2.5454545454545456e-06,
|
| 186 |
+
"loss": 1.9357,
|
| 187 |
+
"step": 42
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 4.0,
|
| 191 |
+
"grad_norm": 2.0487308502197266,
|
| 192 |
+
"learning_rate": 2.666666666666667e-06,
|
| 193 |
+
"loss": 2.0536,
|
| 194 |
+
"step": 44
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 4.0,
|
| 198 |
+
"eval_loss": 1.9862397909164429,
|
| 199 |
+
"eval_runtime": 9.6288,
|
| 200 |
+
"eval_samples_per_second": 2.493,
|
| 201 |
+
"eval_steps_per_second": 2.493,
|
| 202 |
+
"step": 44
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 4.181818181818182,
|
| 206 |
+
"grad_norm": 1.935196876525879,
|
| 207 |
+
"learning_rate": 2.7878787878787885e-06,
|
| 208 |
+
"loss": 1.9591,
|
| 209 |
+
"step": 46
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 4.363636363636363,
|
| 213 |
+
"grad_norm": 1.7882719039916992,
|
| 214 |
+
"learning_rate": 2.9090909090909093e-06,
|
| 215 |
+
"loss": 1.9446,
|
| 216 |
+
"step": 48
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 4.545454545454545,
|
| 220 |
+
"grad_norm": 1.80415940284729,
|
| 221 |
+
"learning_rate": 3.0303030303030305e-06,
|
| 222 |
+
"loss": 1.9487,
|
| 223 |
+
"step": 50
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 4.7272727272727275,
|
| 227 |
+
"grad_norm": 1.7832120656967163,
|
| 228 |
+
"learning_rate": 3.1515151515151517e-06,
|
| 229 |
+
"loss": 1.9723,
|
| 230 |
+
"step": 52
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 4.909090909090909,
|
| 234 |
+
"grad_norm": 1.6389567852020264,
|
| 235 |
+
"learning_rate": 3.272727272727273e-06,
|
| 236 |
+
"loss": 1.8317,
|
| 237 |
+
"step": 54
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 5.0,
|
| 241 |
+
"eval_loss": 1.8956037759780884,
|
| 242 |
+
"eval_runtime": 9.6308,
|
| 243 |
+
"eval_samples_per_second": 2.492,
|
| 244 |
+
"eval_steps_per_second": 2.492,
|
| 245 |
+
"step": 55
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 5.090909090909091,
|
| 249 |
+
"grad_norm": 1.7195862531661987,
|
| 250 |
+
"learning_rate": 3.3939393939393946e-06,
|
| 251 |
+
"loss": 1.9008,
|
| 252 |
+
"step": 56
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 5.2727272727272725,
|
| 256 |
+
"grad_norm": 1.8558402061462402,
|
| 257 |
+
"learning_rate": 3.5151515151515154e-06,
|
| 258 |
+
"loss": 1.916,
|
| 259 |
+
"step": 58
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 5.454545454545454,
|
| 263 |
+
"grad_norm": 1.9300419092178345,
|
| 264 |
+
"learning_rate": 3.6363636363636366e-06,
|
| 265 |
+
"loss": 1.8262,
|
| 266 |
+
"step": 60
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 5.636363636363637,
|
| 270 |
+
"grad_norm": 1.8043519258499146,
|
| 271 |
+
"learning_rate": 3.757575757575758e-06,
|
| 272 |
+
"loss": 1.8013,
|
| 273 |
+
"step": 62
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 5.818181818181818,
|
| 277 |
+
"grad_norm": 1.5544039011001587,
|
| 278 |
+
"learning_rate": 3.878787878787879e-06,
|
| 279 |
+
"loss": 1.7996,
|
| 280 |
+
"step": 64
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 6.0,
|
| 284 |
+
"grad_norm": 1.6001099348068237,
|
| 285 |
+
"learning_rate": 4.000000000000001e-06,
|
| 286 |
+
"loss": 1.7607,
|
| 287 |
+
"step": 66
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 6.0,
|
| 291 |
+
"eval_loss": 1.7668356895446777,
|
| 292 |
+
"eval_runtime": 9.6388,
|
| 293 |
+
"eval_samples_per_second": 2.49,
|
| 294 |
+
"eval_steps_per_second": 2.49,
|
| 295 |
+
"step": 66
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 6.181818181818182,
|
| 299 |
+
"grad_norm": 1.52090322971344,
|
| 300 |
+
"learning_rate": 4.1212121212121215e-06,
|
| 301 |
+
"loss": 1.7673,
|
| 302 |
+
"step": 68
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 6.363636363636363,
|
| 306 |
+
"grad_norm": 1.4516123533248901,
|
| 307 |
+
"learning_rate": 4.242424242424243e-06,
|
| 308 |
+
"loss": 1.782,
|
| 309 |
+
"step": 70
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 6.545454545454545,
|
| 313 |
+
"grad_norm": 1.318569540977478,
|
| 314 |
+
"learning_rate": 4.363636363636364e-06,
|
| 315 |
+
"loss": 1.6176,
|
| 316 |
+
"step": 72
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 6.7272727272727275,
|
| 320 |
+
"grad_norm": 1.3474187850952148,
|
| 321 |
+
"learning_rate": 4.4848484848484855e-06,
|
| 322 |
+
"loss": 1.6543,
|
| 323 |
+
"step": 74
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 6.909090909090909,
|
| 327 |
+
"grad_norm": 1.1612062454223633,
|
| 328 |
+
"learning_rate": 4.606060606060606e-06,
|
| 329 |
+
"loss": 1.6452,
|
| 330 |
+
"step": 76
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 7.0,
|
| 334 |
+
"eval_loss": 1.6453262567520142,
|
| 335 |
+
"eval_runtime": 9.6333,
|
| 336 |
+
"eval_samples_per_second": 2.491,
|
| 337 |
+
"eval_steps_per_second": 2.491,
|
| 338 |
+
"step": 77
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 7.090909090909091,
|
| 342 |
+
"grad_norm": 1.062233328819275,
|
| 343 |
+
"learning_rate": 4.727272727272728e-06,
|
| 344 |
+
"loss": 1.5258,
|
| 345 |
+
"step": 78
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 7.2727272727272725,
|
| 349 |
+
"grad_norm": 0.9276080131530762,
|
| 350 |
+
"learning_rate": 4.848484848484849e-06,
|
| 351 |
+
"loss": 1.7018,
|
| 352 |
+
"step": 80
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 7.454545454545454,
|
| 356 |
+
"grad_norm": 0.7713845372200012,
|
| 357 |
+
"learning_rate": 4.9696969696969696e-06,
|
| 358 |
+
"loss": 1.5366,
|
| 359 |
+
"step": 82
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 7.636363636363637,
|
| 363 |
+
"grad_norm": 0.8294752240180969,
|
| 364 |
+
"learning_rate": 5.090909090909091e-06,
|
| 365 |
+
"loss": 1.5103,
|
| 366 |
+
"step": 84
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 7.818181818181818,
|
| 370 |
+
"grad_norm": 0.7149582505226135,
|
| 371 |
+
"learning_rate": 5.212121212121213e-06,
|
| 372 |
+
"loss": 1.5768,
|
| 373 |
+
"step": 86
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 8.0,
|
| 377 |
+
"grad_norm": 0.7764841914176941,
|
| 378 |
+
"learning_rate": 5.333333333333334e-06,
|
| 379 |
+
"loss": 1.548,
|
| 380 |
+
"step": 88
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 8.0,
|
| 384 |
+
"eval_loss": 1.5728096961975098,
|
| 385 |
+
"eval_runtime": 9.6306,
|
| 386 |
+
"eval_samples_per_second": 2.492,
|
| 387 |
+
"eval_steps_per_second": 2.492,
|
| 388 |
+
"step": 88
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 8.181818181818182,
|
| 392 |
+
"grad_norm": 0.7410159111022949,
|
| 393 |
+
"learning_rate": 5.4545454545454545e-06,
|
| 394 |
+
"loss": 1.4837,
|
| 395 |
+
"step": 90
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 8.363636363636363,
|
| 399 |
+
"grad_norm": 0.7778185606002808,
|
| 400 |
+
"learning_rate": 5.575757575757577e-06,
|
| 401 |
+
"loss": 1.518,
|
| 402 |
+
"step": 92
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 8.545454545454545,
|
| 406 |
+
"grad_norm": 0.7047359943389893,
|
| 407 |
+
"learning_rate": 5.696969696969698e-06,
|
| 408 |
+
"loss": 1.5698,
|
| 409 |
+
"step": 94
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 8.727272727272727,
|
| 413 |
+
"grad_norm": 0.8407279253005981,
|
| 414 |
+
"learning_rate": 5.8181818181818185e-06,
|
| 415 |
+
"loss": 1.5277,
|
| 416 |
+
"step": 96
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 8.909090909090908,
|
| 420 |
+
"grad_norm": 0.6757096648216248,
|
| 421 |
+
"learning_rate": 5.93939393939394e-06,
|
| 422 |
+
"loss": 1.4631,
|
| 423 |
+
"step": 98
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 9.0,
|
| 427 |
+
"eval_loss": 1.5217022895812988,
|
| 428 |
+
"eval_runtime": 9.631,
|
| 429 |
+
"eval_samples_per_second": 2.492,
|
| 430 |
+
"eval_steps_per_second": 2.492,
|
| 431 |
+
"step": 99
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 9.090909090909092,
|
| 435 |
+
"grad_norm": 0.6718485355377197,
|
| 436 |
+
"learning_rate": 6.060606060606061e-06,
|
| 437 |
+
"loss": 1.4975,
|
| 438 |
+
"step": 100
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 9.272727272727273,
|
| 442 |
+
"grad_norm": 0.657922089099884,
|
| 443 |
+
"learning_rate": 6.181818181818182e-06,
|
| 444 |
+
"loss": 1.457,
|
| 445 |
+
"step": 102
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 9.454545454545455,
|
| 449 |
+
"grad_norm": 0.8073777556419373,
|
| 450 |
+
"learning_rate": 6.303030303030303e-06,
|
| 451 |
+
"loss": 1.5072,
|
| 452 |
+
"step": 104
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 9.636363636363637,
|
| 456 |
+
"grad_norm": 0.7699378132820129,
|
| 457 |
+
"learning_rate": 6.424242424242425e-06,
|
| 458 |
+
"loss": 1.4021,
|
| 459 |
+
"step": 106
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 9.818181818181818,
|
| 463 |
+
"grad_norm": 0.7344899773597717,
|
| 464 |
+
"learning_rate": 6.545454545454546e-06,
|
| 465 |
+
"loss": 1.4539,
|
| 466 |
+
"step": 108
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 10.0,
|
| 470 |
+
"grad_norm": 0.6962461471557617,
|
| 471 |
+
"learning_rate": 6.666666666666667e-06,
|
| 472 |
+
"loss": 1.4126,
|
| 473 |
+
"step": 110
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 10.0,
|
| 477 |
+
"eval_loss": 1.471091866493225,
|
| 478 |
+
"eval_runtime": 9.628,
|
| 479 |
+
"eval_samples_per_second": 2.493,
|
| 480 |
+
"eval_steps_per_second": 2.493,
|
| 481 |
+
"step": 110
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 10.181818181818182,
|
| 485 |
+
"grad_norm": 0.756142258644104,
|
| 486 |
+
"learning_rate": 6.787878787878789e-06,
|
| 487 |
+
"loss": 1.4482,
|
| 488 |
+
"step": 112
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 10.363636363636363,
|
| 492 |
+
"grad_norm": 0.7393659353256226,
|
| 493 |
+
"learning_rate": 6.90909090909091e-06,
|
| 494 |
+
"loss": 1.45,
|
| 495 |
+
"step": 114
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 10.545454545454545,
|
| 499 |
+
"grad_norm": 0.7522909641265869,
|
| 500 |
+
"learning_rate": 7.030303030303031e-06,
|
| 501 |
+
"loss": 1.4183,
|
| 502 |
+
"step": 116
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 10.727272727272727,
|
| 506 |
+
"grad_norm": 0.632103681564331,
|
| 507 |
+
"learning_rate": 7.151515151515152e-06,
|
| 508 |
+
"loss": 1.4051,
|
| 509 |
+
"step": 118
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 10.909090909090908,
|
| 513 |
+
"grad_norm": 0.6698535680770874,
|
| 514 |
+
"learning_rate": 7.272727272727273e-06,
|
| 515 |
+
"loss": 1.3079,
|
| 516 |
+
"step": 120
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 11.0,
|
| 520 |
+
"eval_loss": 1.4176009893417358,
|
| 521 |
+
"eval_runtime": 9.6277,
|
| 522 |
+
"eval_samples_per_second": 2.493,
|
| 523 |
+
"eval_steps_per_second": 2.493,
|
| 524 |
+
"step": 121
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 11.090909090909092,
|
| 528 |
+
"grad_norm": 0.7236391305923462,
|
| 529 |
+
"learning_rate": 7.393939393939395e-06,
|
| 530 |
+
"loss": 1.3409,
|
| 531 |
+
"step": 122
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 11.272727272727273,
|
| 535 |
+
"grad_norm": 0.7769017219543457,
|
| 536 |
+
"learning_rate": 7.515151515151516e-06,
|
| 537 |
+
"loss": 1.3852,
|
| 538 |
+
"step": 124
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 11.454545454545455,
|
| 542 |
+
"grad_norm": 0.7625659704208374,
|
| 543 |
+
"learning_rate": 7.636363636363638e-06,
|
| 544 |
+
"loss": 1.4075,
|
| 545 |
+
"step": 126
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 11.636363636363637,
|
| 549 |
+
"grad_norm": 0.7391623258590698,
|
| 550 |
+
"learning_rate": 7.757575757575758e-06,
|
| 551 |
+
"loss": 1.3438,
|
| 552 |
+
"step": 128
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 11.818181818181818,
|
| 556 |
+
"grad_norm": 0.7174716591835022,
|
| 557 |
+
"learning_rate": 7.87878787878788e-06,
|
| 558 |
+
"loss": 1.2229,
|
| 559 |
+
"step": 130
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 12.0,
|
| 563 |
+
"grad_norm": 0.6933201551437378,
|
| 564 |
+
"learning_rate": 8.000000000000001e-06,
|
| 565 |
+
"loss": 1.3012,
|
| 566 |
+
"step": 132
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 12.0,
|
| 570 |
+
"eval_loss": 1.3768787384033203,
|
| 571 |
+
"eval_runtime": 9.6401,
|
| 572 |
+
"eval_samples_per_second": 2.49,
|
| 573 |
+
"eval_steps_per_second": 2.49,
|
| 574 |
+
"step": 132
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 12.181818181818182,
|
| 578 |
+
"grad_norm": 0.7602589130401611,
|
| 579 |
+
"learning_rate": 8.121212121212121e-06,
|
| 580 |
+
"loss": 1.3075,
|
| 581 |
+
"step": 134
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 12.363636363636363,
|
| 585 |
+
"grad_norm": 0.7896175384521484,
|
| 586 |
+
"learning_rate": 8.242424242424243e-06,
|
| 587 |
+
"loss": 1.2531,
|
| 588 |
+
"step": 136
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 12.545454545454545,
|
| 592 |
+
"grad_norm": 0.7628654837608337,
|
| 593 |
+
"learning_rate": 8.363636363636365e-06,
|
| 594 |
+
"loss": 1.2487,
|
| 595 |
+
"step": 138
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"epoch": 12.727272727272727,
|
| 599 |
+
"grad_norm": 0.7553589940071106,
|
| 600 |
+
"learning_rate": 8.484848484848486e-06,
|
| 601 |
+
"loss": 1.3375,
|
| 602 |
+
"step": 140
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 12.909090909090908,
|
| 606 |
+
"grad_norm": 0.8193318247795105,
|
| 607 |
+
"learning_rate": 8.606060606060606e-06,
|
| 608 |
+
"loss": 1.2575,
|
| 609 |
+
"step": 142
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 13.0,
|
| 613 |
+
"eval_loss": 1.34230375289917,
|
| 614 |
+
"eval_runtime": 9.6362,
|
| 615 |
+
"eval_samples_per_second": 2.491,
|
| 616 |
+
"eval_steps_per_second": 2.491,
|
| 617 |
+
"step": 143
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 13.090909090909092,
|
| 621 |
+
"grad_norm": 0.7942626476287842,
|
| 622 |
+
"learning_rate": 8.727272727272728e-06,
|
| 623 |
+
"loss": 1.2746,
|
| 624 |
+
"step": 144
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 13.272727272727273,
|
| 628 |
+
"grad_norm": 0.7456735372543335,
|
| 629 |
+
"learning_rate": 8.84848484848485e-06,
|
| 630 |
+
"loss": 1.2148,
|
| 631 |
+
"step": 146
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 13.454545454545455,
|
| 635 |
+
"grad_norm": 0.8296701908111572,
|
| 636 |
+
"learning_rate": 8.969696969696971e-06,
|
| 637 |
+
"loss": 1.2372,
|
| 638 |
+
"step": 148
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 13.636363636363637,
|
| 642 |
+
"grad_norm": 0.8604351282119751,
|
| 643 |
+
"learning_rate": 9.090909090909091e-06,
|
| 644 |
+
"loss": 1.1917,
|
| 645 |
+
"step": 150
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 13.818181818181818,
|
| 649 |
+
"grad_norm": 0.8084425330162048,
|
| 650 |
+
"learning_rate": 9.212121212121213e-06,
|
| 651 |
+
"loss": 1.2257,
|
| 652 |
+
"step": 152
|
| 653 |
+
},
|
| 654 |
+
{
|
| 655 |
+
"epoch": 14.0,
|
| 656 |
+
"grad_norm": 0.8843783140182495,
|
| 657 |
+
"learning_rate": 9.333333333333334e-06,
|
| 658 |
+
"loss": 1.2537,
|
| 659 |
+
"step": 154
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 14.0,
|
| 663 |
+
"eval_loss": 1.3097882270812988,
|
| 664 |
+
"eval_runtime": 9.642,
|
| 665 |
+
"eval_samples_per_second": 2.489,
|
| 666 |
+
"eval_steps_per_second": 2.489,
|
| 667 |
+
"step": 154
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 14.181818181818182,
|
| 671 |
+
"grad_norm": 0.9855999946594238,
|
| 672 |
+
"learning_rate": 9.454545454545456e-06,
|
| 673 |
+
"loss": 1.1807,
|
| 674 |
+
"step": 156
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 14.363636363636363,
|
| 678 |
+
"grad_norm": 0.7823004722595215,
|
| 679 |
+
"learning_rate": 9.575757575757576e-06,
|
| 680 |
+
"loss": 1.1481,
|
| 681 |
+
"step": 158
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 14.545454545454545,
|
| 685 |
+
"grad_norm": 0.8486412167549133,
|
| 686 |
+
"learning_rate": 9.696969696969698e-06,
|
| 687 |
+
"loss": 1.1524,
|
| 688 |
+
"step": 160
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 14.727272727272727,
|
| 692 |
+
"grad_norm": 0.9296090006828308,
|
| 693 |
+
"learning_rate": 9.81818181818182e-06,
|
| 694 |
+
"loss": 1.223,
|
| 695 |
+
"step": 162
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 14.909090909090908,
|
| 699 |
+
"grad_norm": 0.962130069732666,
|
| 700 |
+
"learning_rate": 9.939393939393939e-06,
|
| 701 |
+
"loss": 1.1994,
|
| 702 |
+
"step": 164
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 15.0,
|
| 706 |
+
"eval_loss": 1.2874382734298706,
|
| 707 |
+
"eval_runtime": 9.6369,
|
| 708 |
+
"eval_samples_per_second": 2.49,
|
| 709 |
+
"eval_steps_per_second": 2.49,
|
| 710 |
+
"step": 165
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 15.090909090909092,
|
| 714 |
+
"grad_norm": 1.0040925741195679,
|
| 715 |
+
"learning_rate": 9.999988811118232e-06,
|
| 716 |
+
"loss": 1.0752,
|
| 717 |
+
"step": 166
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 15.272727272727273,
|
| 721 |
+
"grad_norm": 0.8788989782333374,
|
| 722 |
+
"learning_rate": 9.999899300364534e-06,
|
| 723 |
+
"loss": 1.1945,
|
| 724 |
+
"step": 168
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 15.454545454545455,
|
| 728 |
+
"grad_norm": 0.8372966647148132,
|
| 729 |
+
"learning_rate": 9.999720280459576e-06,
|
| 730 |
+
"loss": 1.1612,
|
| 731 |
+
"step": 170
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 15.636363636363637,
|
| 735 |
+
"grad_norm": 0.9981568455696106,
|
| 736 |
+
"learning_rate": 9.999451754608208e-06,
|
| 737 |
+
"loss": 1.0675,
|
| 738 |
+
"step": 172
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 15.818181818181818,
|
| 742 |
+
"grad_norm": 0.989941418170929,
|
| 743 |
+
"learning_rate": 9.99909372761763e-06,
|
| 744 |
+
"loss": 1.1123,
|
| 745 |
+
"step": 174
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 16.0,
|
| 749 |
+
"grad_norm": 1.071035623550415,
|
| 750 |
+
"learning_rate": 9.99864620589731e-06,
|
| 751 |
+
"loss": 1.1054,
|
| 752 |
+
"step": 176
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 16.0,
|
| 756 |
+
"eval_loss": 1.2712817192077637,
|
| 757 |
+
"eval_runtime": 9.6277,
|
| 758 |
+
"eval_samples_per_second": 2.493,
|
| 759 |
+
"eval_steps_per_second": 2.493,
|
| 760 |
+
"step": 176
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 16.181818181818183,
|
| 764 |
+
"grad_norm": 1.0144329071044922,
|
| 765 |
+
"learning_rate": 9.998109197458865e-06,
|
| 766 |
+
"loss": 1.1681,
|
| 767 |
+
"step": 178
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 16.363636363636363,
|
| 771 |
+
"grad_norm": 1.0573251247406006,
|
| 772 |
+
"learning_rate": 9.997482711915926e-06,
|
| 773 |
+
"loss": 1.06,
|
| 774 |
+
"step": 180
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 16.545454545454547,
|
| 778 |
+
"grad_norm": 1.000741720199585,
|
| 779 |
+
"learning_rate": 9.996766760483955e-06,
|
| 780 |
+
"loss": 1.0508,
|
| 781 |
+
"step": 182
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 16.727272727272727,
|
| 785 |
+
"grad_norm": 1.2005733251571655,
|
| 786 |
+
"learning_rate": 9.995961355980052e-06,
|
| 787 |
+
"loss": 1.0129,
|
| 788 |
+
"step": 184
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 16.90909090909091,
|
| 792 |
+
"grad_norm": 1.195275902748108,
|
| 793 |
+
"learning_rate": 9.99506651282272e-06,
|
| 794 |
+
"loss": 1.0452,
|
| 795 |
+
"step": 186
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 17.0,
|
| 799 |
+
"eval_loss": 1.2680319547653198,
|
| 800 |
+
"eval_runtime": 9.6377,
|
| 801 |
+
"eval_samples_per_second": 2.49,
|
| 802 |
+
"eval_steps_per_second": 2.49,
|
| 803 |
+
"step": 187
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 17.09090909090909,
|
| 807 |
+
"grad_norm": 1.2155280113220215,
|
| 808 |
+
"learning_rate": 9.994082247031613e-06,
|
| 809 |
+
"loss": 1.0263,
|
| 810 |
+
"step": 188
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 17.272727272727273,
|
| 814 |
+
"grad_norm": 1.143007516860962,
|
| 815 |
+
"learning_rate": 9.993008576227248e-06,
|
| 816 |
+
"loss": 0.9197,
|
| 817 |
+
"step": 190
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 17.454545454545453,
|
| 821 |
+
"grad_norm": 1.260664939880371,
|
| 822 |
+
"learning_rate": 9.991845519630679e-06,
|
| 823 |
+
"loss": 0.9681,
|
| 824 |
+
"step": 192
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 17.636363636363637,
|
| 828 |
+
"grad_norm": 1.3235067129135132,
|
| 829 |
+
"learning_rate": 9.99059309806317e-06,
|
| 830 |
+
"loss": 1.0343,
|
| 831 |
+
"step": 194
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 17.818181818181817,
|
| 835 |
+
"grad_norm": 1.4046649932861328,
|
| 836 |
+
"learning_rate": 9.989251333945813e-06,
|
| 837 |
+
"loss": 1.0078,
|
| 838 |
+
"step": 196
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 18.0,
|
| 842 |
+
"grad_norm": 1.2338204383850098,
|
| 843 |
+
"learning_rate": 9.987820251299121e-06,
|
| 844 |
+
"loss": 1.0716,
|
| 845 |
+
"step": 198
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 18.0,
|
| 849 |
+
"eval_loss": 1.2658852338790894,
|
| 850 |
+
"eval_runtime": 9.6422,
|
| 851 |
+
"eval_samples_per_second": 2.489,
|
| 852 |
+
"eval_steps_per_second": 2.489,
|
| 853 |
+
"step": 198
|
| 854 |
+
},
|
| 855 |
+
{
|
| 856 |
+
"epoch": 18.181818181818183,
|
| 857 |
+
"grad_norm": 1.3795467615127563,
|
| 858 |
+
"learning_rate": 9.986299875742612e-06,
|
| 859 |
+
"loss": 0.9914,
|
| 860 |
+
"step": 200
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 18.363636363636363,
|
| 864 |
+
"grad_norm": 1.2211111783981323,
|
| 865 |
+
"learning_rate": 9.984690234494338e-06,
|
| 866 |
+
"loss": 0.9788,
|
| 867 |
+
"step": 202
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 18.545454545454547,
|
| 871 |
+
"grad_norm": 1.4873826503753662,
|
| 872 |
+
"learning_rate": 9.982991356370404e-06,
|
| 873 |
+
"loss": 0.9206,
|
| 874 |
+
"step": 204
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 18.727272727272727,
|
| 878 |
+
"grad_norm": 1.1939488649368286,
|
| 879 |
+
"learning_rate": 9.98120327178445e-06,
|
| 880 |
+
"loss": 0.9713,
|
| 881 |
+
"step": 206
|
| 882 |
+
},
|
| 883 |
+
{
|
| 884 |
+
"epoch": 18.90909090909091,
|
| 885 |
+
"grad_norm": 1.4163975715637207,
|
| 886 |
+
"learning_rate": 9.979326012747106e-06,
|
| 887 |
+
"loss": 0.9207,
|
| 888 |
+
"step": 208
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"epoch": 19.0,
|
| 892 |
+
"eval_loss": 1.2754586935043335,
|
| 893 |
+
"eval_runtime": 9.6506,
|
| 894 |
+
"eval_samples_per_second": 2.487,
|
| 895 |
+
"eval_steps_per_second": 2.487,
|
| 896 |
+
"step": 209
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 19.09090909090909,
|
| 900 |
+
"grad_norm": 1.57706880569458,
|
| 901 |
+
"learning_rate": 9.977359612865424e-06,
|
| 902 |
+
"loss": 0.847,
|
| 903 |
+
"step": 210
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 19.272727272727273,
|
| 907 |
+
"grad_norm": 1.3526296615600586,
|
| 908 |
+
"learning_rate": 9.975304107342268e-06,
|
| 909 |
+
"loss": 0.83,
|
| 910 |
+
"step": 212
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 19.454545454545453,
|
| 914 |
+
"grad_norm": 1.3322209119796753,
|
| 915 |
+
"learning_rate": 9.973159532975691e-06,
|
| 916 |
+
"loss": 0.9059,
|
| 917 |
+
"step": 214
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 19.636363636363637,
|
| 921 |
+
"grad_norm": 1.7349506616592407,
|
| 922 |
+
"learning_rate": 9.970925928158275e-06,
|
| 923 |
+
"loss": 0.9101,
|
| 924 |
+
"step": 216
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 19.818181818181817,
|
| 928 |
+
"grad_norm": 1.7136040925979614,
|
| 929 |
+
"learning_rate": 9.968603332876435e-06,
|
| 930 |
+
"loss": 0.9291,
|
| 931 |
+
"step": 218
|
| 932 |
+
},
|
| 933 |
+
{
|
| 934 |
+
"epoch": 20.0,
|
| 935 |
+
"grad_norm": 1.6715441942214966,
|
| 936 |
+
"learning_rate": 9.966191788709716e-06,
|
| 937 |
+
"loss": 0.8712,
|
| 938 |
+
"step": 220
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 20.0,
|
| 942 |
+
"eval_loss": 1.291751503944397,
|
| 943 |
+
"eval_runtime": 9.6384,
|
| 944 |
+
"eval_samples_per_second": 2.49,
|
| 945 |
+
"eval_steps_per_second": 2.49,
|
| 946 |
+
"step": 220
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 20.181818181818183,
|
| 950 |
+
"grad_norm": 1.7461074590682983,
|
| 951 |
+
"learning_rate": 9.963691338830045e-06,
|
| 952 |
+
"loss": 0.8728,
|
| 953 |
+
"step": 222
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 20.363636363636363,
|
| 957 |
+
"grad_norm": 1.5934933423995972,
|
| 958 |
+
"learning_rate": 9.961102028000948e-06,
|
| 959 |
+
"loss": 0.7777,
|
| 960 |
+
"step": 224
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 20.545454545454547,
|
| 964 |
+
"grad_norm": 1.8316841125488281,
|
| 965 |
+
"learning_rate": 9.958423902576764e-06,
|
| 966 |
+
"loss": 0.9123,
|
| 967 |
+
"step": 226
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"epoch": 20.727272727272727,
|
| 971 |
+
"grad_norm": 1.6827653646469116,
|
| 972 |
+
"learning_rate": 9.955657010501807e-06,
|
| 973 |
+
"loss": 0.741,
|
| 974 |
+
"step": 228
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 20.90909090909091,
|
| 978 |
+
"grad_norm": 1.7905974388122559,
|
| 979 |
+
"learning_rate": 9.952801401309504e-06,
|
| 980 |
+
"loss": 0.8179,
|
| 981 |
+
"step": 230
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 21.0,
|
| 985 |
+
"eval_loss": 1.337079644203186,
|
| 986 |
+
"eval_runtime": 9.6484,
|
| 987 |
+
"eval_samples_per_second": 2.487,
|
| 988 |
+
"eval_steps_per_second": 2.487,
|
| 989 |
+
"step": 231
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 21.09090909090909,
|
| 993 |
+
"grad_norm": 1.711150884628296,
|
| 994 |
+
"learning_rate": 9.949857126121519e-06,
|
| 995 |
+
"loss": 0.7859,
|
| 996 |
+
"step": 232
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 21.272727272727273,
|
| 1000 |
+
"grad_norm": 1.8518304824829102,
|
| 1001 |
+
"learning_rate": 9.946824237646823e-06,
|
| 1002 |
+
"loss": 0.7743,
|
| 1003 |
+
"step": 234
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 21.454545454545453,
|
| 1007 |
+
"grad_norm": 2.065861701965332,
|
| 1008 |
+
"learning_rate": 9.94370279018077e-06,
|
| 1009 |
+
"loss": 0.7725,
|
| 1010 |
+
"step": 236
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 21.636363636363637,
|
| 1014 |
+
"grad_norm": 1.9285728931427002,
|
| 1015 |
+
"learning_rate": 9.940492839604103e-06,
|
| 1016 |
+
"loss": 0.7043,
|
| 1017 |
+
"step": 238
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 21.818181818181817,
|
| 1021 |
+
"grad_norm": 1.9804288148880005,
|
| 1022 |
+
"learning_rate": 9.937194443381972e-06,
|
| 1023 |
+
"loss": 0.8355,
|
| 1024 |
+
"step": 240
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 22.0,
|
| 1028 |
+
"grad_norm": 1.9706605672836304,
|
| 1029 |
+
"learning_rate": 9.933807660562898e-06,
|
| 1030 |
+
"loss": 0.6485,
|
| 1031 |
+
"step": 242
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 22.0,
|
| 1035 |
+
"eval_loss": 1.3560718297958374,
|
| 1036 |
+
"eval_runtime": 9.6266,
|
| 1037 |
+
"eval_samples_per_second": 2.493,
|
| 1038 |
+
"eval_steps_per_second": 2.493,
|
| 1039 |
+
"step": 242
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 22.181818181818183,
|
| 1043 |
+
"grad_norm": 1.8734219074249268,
|
| 1044 |
+
"learning_rate": 9.930332551777709e-06,
|
| 1045 |
+
"loss": 0.6863,
|
| 1046 |
+
"step": 244
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 22.363636363636363,
|
| 1050 |
+
"grad_norm": 2.110110282897949,
|
| 1051 |
+
"learning_rate": 9.926769179238467e-06,
|
| 1052 |
+
"loss": 0.6799,
|
| 1053 |
+
"step": 246
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 22.545454545454547,
|
| 1057 |
+
"grad_norm": 2.442317008972168,
|
| 1058 |
+
"learning_rate": 9.923117606737347e-06,
|
| 1059 |
+
"loss": 0.6703,
|
| 1060 |
+
"step": 248
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 22.727272727272727,
|
| 1064 |
+
"grad_norm": 2.216526508331299,
|
| 1065 |
+
"learning_rate": 9.919377899645497e-06,
|
| 1066 |
+
"loss": 0.687,
|
| 1067 |
+
"step": 250
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 22.90909090909091,
|
| 1071 |
+
"grad_norm": 2.3219642639160156,
|
| 1072 |
+
"learning_rate": 9.915550124911866e-06,
|
| 1073 |
+
"loss": 0.6958,
|
| 1074 |
+
"step": 252
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 23.0,
|
| 1078 |
+
"eval_loss": 1.4414390325546265,
|
| 1079 |
+
"eval_runtime": 9.6326,
|
| 1080 |
+
"eval_samples_per_second": 2.492,
|
| 1081 |
+
"eval_steps_per_second": 2.492,
|
| 1082 |
+
"step": 253
|
| 1083 |
+
},
|
| 1084 |
+
{
|
| 1085 |
+
"epoch": 23.09090909090909,
|
| 1086 |
+
"grad_norm": 2.1852304935455322,
|
| 1087 |
+
"learning_rate": 9.91163435106201e-06,
|
| 1088 |
+
"loss": 0.5976,
|
| 1089 |
+
"step": 254
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 23.272727272727273,
|
| 1093 |
+
"grad_norm": 2.0445878505706787,
|
| 1094 |
+
"learning_rate": 9.907630648196857e-06,
|
| 1095 |
+
"loss": 0.687,
|
| 1096 |
+
"step": 256
|
| 1097 |
+
},
|
| 1098 |
+
{
|
| 1099 |
+
"epoch": 23.454545454545453,
|
| 1100 |
+
"grad_norm": 2.2275197505950928,
|
| 1101 |
+
"learning_rate": 9.903539087991462e-06,
|
| 1102 |
+
"loss": 0.62,
|
| 1103 |
+
"step": 258
|
| 1104 |
+
},
|
| 1105 |
+
{
|
| 1106 |
+
"epoch": 23.636363636363637,
|
| 1107 |
+
"grad_norm": 2.462937593460083,
|
| 1108 |
+
"learning_rate": 9.899359743693715e-06,
|
| 1109 |
+
"loss": 0.5359,
|
| 1110 |
+
"step": 260
|
| 1111 |
+
},
|
| 1112 |
+
{
|
| 1113 |
+
"epoch": 23.818181818181817,
|
| 1114 |
+
"grad_norm": 2.7242631912231445,
|
| 1115 |
+
"learning_rate": 9.895092690123036e-06,
|
| 1116 |
+
"loss": 0.6217,
|
| 1117 |
+
"step": 262
|
| 1118 |
+
},
|
| 1119 |
+
{
|
| 1120 |
+
"epoch": 24.0,
|
| 1121 |
+
"grad_norm": 2.585885763168335,
|
| 1122 |
+
"learning_rate": 9.890738003669029e-06,
|
| 1123 |
+
"loss": 0.5845,
|
| 1124 |
+
"step": 264
|
| 1125 |
+
},
|
| 1126 |
+
{
|
| 1127 |
+
"epoch": 24.0,
|
| 1128 |
+
"eval_loss": 1.5147289037704468,
|
| 1129 |
+
"eval_runtime": 9.6323,
|
| 1130 |
+
"eval_samples_per_second": 2.492,
|
| 1131 |
+
"eval_steps_per_second": 2.492,
|
| 1132 |
+
"step": 264
|
| 1133 |
+
},
|
| 1134 |
+
{
|
| 1135 |
+
"epoch": 24.181818181818183,
|
| 1136 |
+
"grad_norm": 2.6411542892456055,
|
| 1137 |
+
"learning_rate": 9.886295762290125e-06,
|
| 1138 |
+
"loss": 0.5457,
|
| 1139 |
+
"step": 266
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"epoch": 24.363636363636363,
|
| 1143 |
+
"grad_norm": 2.4892776012420654,
|
| 1144 |
+
"learning_rate": 9.881766045512176e-06,
|
| 1145 |
+
"loss": 0.5765,
|
| 1146 |
+
"step": 268
|
| 1147 |
+
},
|
| 1148 |
+
{
|
| 1149 |
+
"epoch": 24.545454545454547,
|
| 1150 |
+
"grad_norm": 2.6362385749816895,
|
| 1151 |
+
"learning_rate": 9.877148934427037e-06,
|
| 1152 |
+
"loss": 0.5477,
|
| 1153 |
+
"step": 270
|
| 1154 |
+
},
|
| 1155 |
+
{
|
| 1156 |
+
"epoch": 24.727272727272727,
|
| 1157 |
+
"grad_norm": 2.6221413612365723,
|
| 1158 |
+
"learning_rate": 9.872444511691108e-06,
|
| 1159 |
+
"loss": 0.4876,
|
| 1160 |
+
"step": 272
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"epoch": 24.90909090909091,
|
| 1164 |
+
"grad_norm": 3.3728928565979004,
|
| 1165 |
+
"learning_rate": 9.867652861523866e-06,
|
| 1166 |
+
"loss": 0.5274,
|
| 1167 |
+
"step": 274
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"epoch": 25.0,
|
| 1171 |
+
"eval_loss": 1.5911802053451538,
|
| 1172 |
+
"eval_runtime": 9.6269,
|
| 1173 |
+
"eval_samples_per_second": 2.493,
|
| 1174 |
+
"eval_steps_per_second": 2.493,
|
| 1175 |
+
"step": 275
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 25.0,
|
| 1179 |
+
"step": 275,
|
| 1180 |
+
"total_flos": 3.3769591557586944e+16,
|
| 1181 |
+
"train_loss": 1.3221848821640014,
|
| 1182 |
+
"train_runtime": 2580.936,
|
| 1183 |
+
"train_samples_per_second": 5.114,
|
| 1184 |
+
"train_steps_per_second": 0.639
|
| 1185 |
+
}
|
| 1186 |
+
],
|
| 1187 |
+
"logging_steps": 2,
|
| 1188 |
+
"max_steps": 1650,
|
| 1189 |
+
"num_input_tokens_seen": 0,
|
| 1190 |
+
"num_train_epochs": 150,
|
| 1191 |
+
"save_steps": 25,
|
| 1192 |
+
"stateful_callbacks": {
|
| 1193 |
+
"EarlyStoppingCallback": {
|
| 1194 |
+
"args": {
|
| 1195 |
+
"early_stopping_patience": 7,
|
| 1196 |
+
"early_stopping_threshold": 0.0
|
| 1197 |
+
},
|
| 1198 |
+
"attributes": {
|
| 1199 |
+
"early_stopping_patience_counter": 0
|
| 1200 |
+
}
|
| 1201 |
+
},
|
| 1202 |
+
"TrainerControl": {
|
| 1203 |
+
"args": {
|
| 1204 |
+
"should_epoch_stop": false,
|
| 1205 |
+
"should_evaluate": false,
|
| 1206 |
+
"should_log": false,
|
| 1207 |
+
"should_save": true,
|
| 1208 |
+
"should_training_stop": true
|
| 1209 |
+
},
|
| 1210 |
+
"attributes": {}
|
| 1211 |
+
}
|
| 1212 |
+
},
|
| 1213 |
+
"total_flos": 3.3769591557586944e+16,
|
| 1214 |
+
"train_batch_size": 1,
|
| 1215 |
+
"trial_name": null,
|
| 1216 |
+
"trial_params": null
|
| 1217 |
+
}
|