Commit
•
97692cd
1
Parent(s):
afaca68
Model save
Browse files- README.md +76 -0
- adapter_model.safetensors +1 -1
- all_results.json +9 -0
- train_results.json +9 -0
- trainer_state.json +616 -0
README.md
ADDED
|
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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-1
|
| 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-1
|
| 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: 2.9299
|
| 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: 0.0001
|
| 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: 50
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 55 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 56 |
+
| 1.8587 | 1.0 | 11 | 1.8962 |
|
| 57 |
+
| 1.5582 | 2.0 | 22 | 1.5353 |
|
| 58 |
+
| 1.3116 | 3.0 | 33 | 1.3440 |
|
| 59 |
+
| 1.1103 | 4.0 | 44 | 1.2486 |
|
| 60 |
+
| 0.9015 | 5.0 | 55 | 1.2432 |
|
| 61 |
+
| 0.6339 | 6.0 | 66 | 1.3448 |
|
| 62 |
+
| 0.2953 | 7.0 | 77 | 1.6649 |
|
| 63 |
+
| 0.2611 | 8.0 | 88 | 1.9195 |
|
| 64 |
+
| 0.107 | 9.0 | 99 | 2.4669 |
|
| 65 |
+
| 0.0592 | 10.0 | 110 | 2.5539 |
|
| 66 |
+
| 0.06 | 11.0 | 121 | 2.4769 |
|
| 67 |
+
| 0.0548 | 12.0 | 132 | 2.9299 |
|
| 68 |
+
|
| 69 |
+
|
| 70 |
+
### Framework versions
|
| 71 |
+
|
| 72 |
+
- PEFT 0.12.0
|
| 73 |
+
- Transformers 4.44.0
|
| 74 |
+
- Pytorch 2.1.2+cu121
|
| 75 |
+
- Datasets 2.20.0
|
| 76 |
+
- 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:e9136d8d48f90fa92bbc063cbfc4166fa742d645cd6a4ca011dde0b9150f1bc6
|
| 3 |
size 167832240
|
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 12.0,
|
| 3 |
+
"total_flos": 1.6209403933884416e+16,
|
| 4 |
+
"train_loss": 0.7309455393926438,
|
| 5 |
+
"train_runtime": 1236.3069,
|
| 6 |
+
"train_samples": 88,
|
| 7 |
+
"train_samples_per_second": 3.559,
|
| 8 |
+
"train_steps_per_second": 0.445
|
| 9 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 12.0,
|
| 3 |
+
"total_flos": 1.6209403933884416e+16,
|
| 4 |
+
"train_loss": 0.7309455393926438,
|
| 5 |
+
"train_runtime": 1236.3069,
|
| 6 |
+
"train_samples": 88,
|
| 7 |
+
"train_samples_per_second": 3.559,
|
| 8 |
+
"train_steps_per_second": 0.445
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,616 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.24324631690979,
|
| 3 |
+
"best_model_checkpoint": "data/Llama-31-8B_task-1_120-samples_config-1/checkpoint-55",
|
| 4 |
+
"epoch": 12.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 132,
|
| 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": 1.947190523147583,
|
| 14 |
+
"learning_rate": 1.818181818181818e-06,
|
| 15 |
+
"loss": 2.2569,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.18181818181818182,
|
| 20 |
+
"grad_norm": 1.950323462486267,
|
| 21 |
+
"learning_rate": 3.636363636363636e-06,
|
| 22 |
+
"loss": 2.3228,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.36363636363636365,
|
| 27 |
+
"grad_norm": 1.7120546102523804,
|
| 28 |
+
"learning_rate": 7.272727272727272e-06,
|
| 29 |
+
"loss": 2.076,
|
| 30 |
+
"step": 4
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.5454545454545454,
|
| 34 |
+
"grad_norm": 1.5879558324813843,
|
| 35 |
+
"learning_rate": 1.0909090909090909e-05,
|
| 36 |
+
"loss": 2.0525,
|
| 37 |
+
"step": 6
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.7272727272727273,
|
| 41 |
+
"grad_norm": 1.8351306915283203,
|
| 42 |
+
"learning_rate": 1.4545454545454545e-05,
|
| 43 |
+
"loss": 2.1059,
|
| 44 |
+
"step": 8
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.9090909090909091,
|
| 48 |
+
"grad_norm": 1.7258864641189575,
|
| 49 |
+
"learning_rate": 1.8181818181818182e-05,
|
| 50 |
+
"loss": 1.8587,
|
| 51 |
+
"step": 10
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 1.0,
|
| 55 |
+
"eval_loss": 1.8961697816848755,
|
| 56 |
+
"eval_runtime": 9.6373,
|
| 57 |
+
"eval_samples_per_second": 2.49,
|
| 58 |
+
"eval_steps_per_second": 2.49,
|
| 59 |
+
"step": 11
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 1.0909090909090908,
|
| 63 |
+
"grad_norm": 1.5399166345596313,
|
| 64 |
+
"learning_rate": 2.1818181818181818e-05,
|
| 65 |
+
"loss": 1.7527,
|
| 66 |
+
"step": 12
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 1.2727272727272727,
|
| 70 |
+
"grad_norm": 1.6511270999908447,
|
| 71 |
+
"learning_rate": 2.5454545454545454e-05,
|
| 72 |
+
"loss": 1.8337,
|
| 73 |
+
"step": 14
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 1.4545454545454546,
|
| 77 |
+
"grad_norm": 1.104617714881897,
|
| 78 |
+
"learning_rate": 2.909090909090909e-05,
|
| 79 |
+
"loss": 1.7403,
|
| 80 |
+
"step": 16
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 1.6363636363636362,
|
| 84 |
+
"grad_norm": 0.8533787131309509,
|
| 85 |
+
"learning_rate": 3.272727272727273e-05,
|
| 86 |
+
"loss": 1.5971,
|
| 87 |
+
"step": 18
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 1.8181818181818183,
|
| 91 |
+
"grad_norm": 0.8006373047828674,
|
| 92 |
+
"learning_rate": 3.6363636363636364e-05,
|
| 93 |
+
"loss": 1.503,
|
| 94 |
+
"step": 20
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 2.0,
|
| 98 |
+
"grad_norm": 0.7819918394088745,
|
| 99 |
+
"learning_rate": 4e-05,
|
| 100 |
+
"loss": 1.5582,
|
| 101 |
+
"step": 22
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 2.0,
|
| 105 |
+
"eval_loss": 1.5353227853775024,
|
| 106 |
+
"eval_runtime": 9.6335,
|
| 107 |
+
"eval_samples_per_second": 2.491,
|
| 108 |
+
"eval_steps_per_second": 2.491,
|
| 109 |
+
"step": 22
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 2.1818181818181817,
|
| 113 |
+
"grad_norm": 0.713280200958252,
|
| 114 |
+
"learning_rate": 4.3636363636363636e-05,
|
| 115 |
+
"loss": 1.5487,
|
| 116 |
+
"step": 24
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 2.3636363636363638,
|
| 120 |
+
"grad_norm": 0.6750282645225525,
|
| 121 |
+
"learning_rate": 4.7272727272727275e-05,
|
| 122 |
+
"loss": 1.4773,
|
| 123 |
+
"step": 26
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 2.5454545454545454,
|
| 127 |
+
"grad_norm": 0.7663286924362183,
|
| 128 |
+
"learning_rate": 5.090909090909091e-05,
|
| 129 |
+
"loss": 1.3698,
|
| 130 |
+
"step": 28
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 2.7272727272727275,
|
| 134 |
+
"grad_norm": 0.6964442133903503,
|
| 135 |
+
"learning_rate": 5.4545454545454546e-05,
|
| 136 |
+
"loss": 1.2677,
|
| 137 |
+
"step": 30
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 2.909090909090909,
|
| 141 |
+
"grad_norm": 0.7686213850975037,
|
| 142 |
+
"learning_rate": 5.818181818181818e-05,
|
| 143 |
+
"loss": 1.3116,
|
| 144 |
+
"step": 32
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 3.0,
|
| 148 |
+
"eval_loss": 1.3440297842025757,
|
| 149 |
+
"eval_runtime": 9.6307,
|
| 150 |
+
"eval_samples_per_second": 2.492,
|
| 151 |
+
"eval_steps_per_second": 2.492,
|
| 152 |
+
"step": 33
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 3.090909090909091,
|
| 156 |
+
"grad_norm": 0.7271563410758972,
|
| 157 |
+
"learning_rate": 6.181818181818182e-05,
|
| 158 |
+
"loss": 1.3272,
|
| 159 |
+
"step": 34
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 3.2727272727272725,
|
| 163 |
+
"grad_norm": 0.7131862640380859,
|
| 164 |
+
"learning_rate": 6.545454545454546e-05,
|
| 165 |
+
"loss": 1.2423,
|
| 166 |
+
"step": 36
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 3.4545454545454546,
|
| 170 |
+
"grad_norm": 0.8657882809638977,
|
| 171 |
+
"learning_rate": 6.90909090909091e-05,
|
| 172 |
+
"loss": 1.2197,
|
| 173 |
+
"step": 38
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 3.6363636363636362,
|
| 177 |
+
"grad_norm": 0.8501375317573547,
|
| 178 |
+
"learning_rate": 7.272727272727273e-05,
|
| 179 |
+
"loss": 1.1791,
|
| 180 |
+
"step": 40
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 3.8181818181818183,
|
| 184 |
+
"grad_norm": 0.8458476662635803,
|
| 185 |
+
"learning_rate": 7.636363636363637e-05,
|
| 186 |
+
"loss": 1.1082,
|
| 187 |
+
"step": 42
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 4.0,
|
| 191 |
+
"grad_norm": 0.8599070906639099,
|
| 192 |
+
"learning_rate": 8e-05,
|
| 193 |
+
"loss": 1.1103,
|
| 194 |
+
"step": 44
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 4.0,
|
| 198 |
+
"eval_loss": 1.248623251914978,
|
| 199 |
+
"eval_runtime": 9.6225,
|
| 200 |
+
"eval_samples_per_second": 2.494,
|
| 201 |
+
"eval_steps_per_second": 2.494,
|
| 202 |
+
"step": 44
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 4.181818181818182,
|
| 206 |
+
"grad_norm": 0.9287438988685608,
|
| 207 |
+
"learning_rate": 8.363636363636364e-05,
|
| 208 |
+
"loss": 0.991,
|
| 209 |
+
"step": 46
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 4.363636363636363,
|
| 213 |
+
"grad_norm": 1.0513927936553955,
|
| 214 |
+
"learning_rate": 8.727272727272727e-05,
|
| 215 |
+
"loss": 0.9697,
|
| 216 |
+
"step": 48
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 4.545454545454545,
|
| 220 |
+
"grad_norm": 1.1929577589035034,
|
| 221 |
+
"learning_rate": 9.090909090909092e-05,
|
| 222 |
+
"loss": 1.0229,
|
| 223 |
+
"step": 50
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 4.7272727272727275,
|
| 227 |
+
"grad_norm": 1.1892277002334595,
|
| 228 |
+
"learning_rate": 9.454545454545455e-05,
|
| 229 |
+
"loss": 0.9632,
|
| 230 |
+
"step": 52
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 4.909090909090909,
|
| 234 |
+
"grad_norm": 1.2755712270736694,
|
| 235 |
+
"learning_rate": 9.818181818181818e-05,
|
| 236 |
+
"loss": 0.9015,
|
| 237 |
+
"step": 54
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 5.0,
|
| 241 |
+
"eval_loss": 1.24324631690979,
|
| 242 |
+
"eval_runtime": 9.6237,
|
| 243 |
+
"eval_samples_per_second": 2.494,
|
| 244 |
+
"eval_steps_per_second": 2.494,
|
| 245 |
+
"step": 55
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 5.090909090909091,
|
| 249 |
+
"grad_norm": 1.26650071144104,
|
| 250 |
+
"learning_rate": 9.999899300364532e-05,
|
| 251 |
+
"loss": 0.871,
|
| 252 |
+
"step": 56
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 5.2727272727272725,
|
| 256 |
+
"grad_norm": 1.2812609672546387,
|
| 257 |
+
"learning_rate": 9.99909372761763e-05,
|
| 258 |
+
"loss": 0.7046,
|
| 259 |
+
"step": 58
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 5.454545454545454,
|
| 263 |
+
"grad_norm": 1.5597699880599976,
|
| 264 |
+
"learning_rate": 9.997482711915927e-05,
|
| 265 |
+
"loss": 0.6681,
|
| 266 |
+
"step": 60
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 5.636363636363637,
|
| 270 |
+
"grad_norm": 1.8858792781829834,
|
| 271 |
+
"learning_rate": 9.99506651282272e-05,
|
| 272 |
+
"loss": 0.7369,
|
| 273 |
+
"step": 62
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 5.818181818181818,
|
| 277 |
+
"grad_norm": 1.7140628099441528,
|
| 278 |
+
"learning_rate": 9.991845519630678e-05,
|
| 279 |
+
"loss": 0.6761,
|
| 280 |
+
"step": 64
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 6.0,
|
| 284 |
+
"grad_norm": 1.500331163406372,
|
| 285 |
+
"learning_rate": 9.987820251299122e-05,
|
| 286 |
+
"loss": 0.6339,
|
| 287 |
+
"step": 66
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 6.0,
|
| 291 |
+
"eval_loss": 1.3448349237442017,
|
| 292 |
+
"eval_runtime": 9.633,
|
| 293 |
+
"eval_samples_per_second": 2.491,
|
| 294 |
+
"eval_steps_per_second": 2.491,
|
| 295 |
+
"step": 66
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 6.181818181818182,
|
| 299 |
+
"grad_norm": 1.3713549375534058,
|
| 300 |
+
"learning_rate": 9.982991356370404e-05,
|
| 301 |
+
"loss": 0.527,
|
| 302 |
+
"step": 68
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 6.363636363636363,
|
| 306 |
+
"grad_norm": 1.5518769025802612,
|
| 307 |
+
"learning_rate": 9.977359612865423e-05,
|
| 308 |
+
"loss": 0.4046,
|
| 309 |
+
"step": 70
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 6.545454545454545,
|
| 313 |
+
"grad_norm": 2.7726385593414307,
|
| 314 |
+
"learning_rate": 9.970925928158274e-05,
|
| 315 |
+
"loss": 0.3872,
|
| 316 |
+
"step": 72
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 6.7272727272727275,
|
| 320 |
+
"grad_norm": 3.0638201236724854,
|
| 321 |
+
"learning_rate": 9.963691338830044e-05,
|
| 322 |
+
"loss": 0.4758,
|
| 323 |
+
"step": 74
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 6.909090909090909,
|
| 327 |
+
"grad_norm": 1.8400838375091553,
|
| 328 |
+
"learning_rate": 9.955657010501806e-05,
|
| 329 |
+
"loss": 0.2953,
|
| 330 |
+
"step": 76
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 7.0,
|
| 334 |
+
"eval_loss": 1.664857268333435,
|
| 335 |
+
"eval_runtime": 9.6249,
|
| 336 |
+
"eval_samples_per_second": 2.494,
|
| 337 |
+
"eval_steps_per_second": 2.494,
|
| 338 |
+
"step": 77
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 7.090909090909091,
|
| 342 |
+
"grad_norm": 1.4201287031173706,
|
| 343 |
+
"learning_rate": 9.946824237646824e-05,
|
| 344 |
+
"loss": 0.2398,
|
| 345 |
+
"step": 78
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 7.2727272727272725,
|
| 349 |
+
"grad_norm": 1.569122314453125,
|
| 350 |
+
"learning_rate": 9.937194443381972e-05,
|
| 351 |
+
"loss": 0.2232,
|
| 352 |
+
"step": 80
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 7.454545454545454,
|
| 356 |
+
"grad_norm": 2.7534537315368652,
|
| 357 |
+
"learning_rate": 9.926769179238466e-05,
|
| 358 |
+
"loss": 0.1809,
|
| 359 |
+
"step": 82
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 7.636363636363637,
|
| 363 |
+
"grad_norm": 3.2907912731170654,
|
| 364 |
+
"learning_rate": 9.915550124911866e-05,
|
| 365 |
+
"loss": 0.2009,
|
| 366 |
+
"step": 84
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 7.818181818181818,
|
| 370 |
+
"grad_norm": 2.7623965740203857,
|
| 371 |
+
"learning_rate": 9.903539087991462e-05,
|
| 372 |
+
"loss": 0.2162,
|
| 373 |
+
"step": 86
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 8.0,
|
| 377 |
+
"grad_norm": 2.723360776901245,
|
| 378 |
+
"learning_rate": 9.890738003669029e-05,
|
| 379 |
+
"loss": 0.2611,
|
| 380 |
+
"step": 88
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 8.0,
|
| 384 |
+
"eval_loss": 1.9194618463516235,
|
| 385 |
+
"eval_runtime": 9.6254,
|
| 386 |
+
"eval_samples_per_second": 2.493,
|
| 387 |
+
"eval_steps_per_second": 2.493,
|
| 388 |
+
"step": 88
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 8.181818181818182,
|
| 392 |
+
"grad_norm": 1.1859649419784546,
|
| 393 |
+
"learning_rate": 9.877148934427037e-05,
|
| 394 |
+
"loss": 0.13,
|
| 395 |
+
"step": 90
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 8.363636363636363,
|
| 399 |
+
"grad_norm": 1.631119966506958,
|
| 400 |
+
"learning_rate": 9.862774069706346e-05,
|
| 401 |
+
"loss": 0.0969,
|
| 402 |
+
"step": 92
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 8.545454545454545,
|
| 406 |
+
"grad_norm": 1.6909385919570923,
|
| 407 |
+
"learning_rate": 9.847615725553456e-05,
|
| 408 |
+
"loss": 0.0749,
|
| 409 |
+
"step": 94
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 8.727272727272727,
|
| 413 |
+
"grad_norm": 2.5971972942352295,
|
| 414 |
+
"learning_rate": 9.831676344247342e-05,
|
| 415 |
+
"loss": 0.0947,
|
| 416 |
+
"step": 96
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 8.909090909090908,
|
| 420 |
+
"grad_norm": 2.3750057220458984,
|
| 421 |
+
"learning_rate": 9.814958493905963e-05,
|
| 422 |
+
"loss": 0.107,
|
| 423 |
+
"step": 98
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 9.0,
|
| 427 |
+
"eval_loss": 2.4669106006622314,
|
| 428 |
+
"eval_runtime": 9.6325,
|
| 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": 1.5737000703811646,
|
| 436 |
+
"learning_rate": 9.797464868072488e-05,
|
| 437 |
+
"loss": 0.0641,
|
| 438 |
+
"step": 100
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 9.272727272727273,
|
| 442 |
+
"grad_norm": 1.2060961723327637,
|
| 443 |
+
"learning_rate": 9.779198285281325e-05,
|
| 444 |
+
"loss": 0.0515,
|
| 445 |
+
"step": 102
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 9.454545454545455,
|
| 449 |
+
"grad_norm": 0.8381581902503967,
|
| 450 |
+
"learning_rate": 9.760161688604008e-05,
|
| 451 |
+
"loss": 0.04,
|
| 452 |
+
"step": 104
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 9.636363636363637,
|
| 456 |
+
"grad_norm": 2.207648754119873,
|
| 457 |
+
"learning_rate": 9.740358145174998e-05,
|
| 458 |
+
"loss": 0.0481,
|
| 459 |
+
"step": 106
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 9.818181818181818,
|
| 463 |
+
"grad_norm": 2.044506311416626,
|
| 464 |
+
"learning_rate": 9.719790845697533e-05,
|
| 465 |
+
"loss": 0.0573,
|
| 466 |
+
"step": 108
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 10.0,
|
| 470 |
+
"grad_norm": 2.117966413497925,
|
| 471 |
+
"learning_rate": 9.698463103929542e-05,
|
| 472 |
+
"loss": 0.0592,
|
| 473 |
+
"step": 110
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 10.0,
|
| 477 |
+
"eval_loss": 2.5538697242736816,
|
| 478 |
+
"eval_runtime": 9.6217,
|
| 479 |
+
"eval_samples_per_second": 2.494,
|
| 480 |
+
"eval_steps_per_second": 2.494,
|
| 481 |
+
"step": 110
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 10.181818181818182,
|
| 485 |
+
"grad_norm": 1.4448171854019165,
|
| 486 |
+
"learning_rate": 9.676378356149734e-05,
|
| 487 |
+
"loss": 0.021,
|
| 488 |
+
"step": 112
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 10.363636363636363,
|
| 492 |
+
"grad_norm": 1.2305335998535156,
|
| 493 |
+
"learning_rate": 9.653540160603956e-05,
|
| 494 |
+
"loss": 0.0286,
|
| 495 |
+
"step": 114
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 10.545454545454545,
|
| 499 |
+
"grad_norm": 1.0550709962844849,
|
| 500 |
+
"learning_rate": 9.629952196931901e-05,
|
| 501 |
+
"loss": 0.0274,
|
| 502 |
+
"step": 116
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 10.727272727272727,
|
| 506 |
+
"grad_norm": 1.6463170051574707,
|
| 507 |
+
"learning_rate": 9.60561826557425e-05,
|
| 508 |
+
"loss": 0.0486,
|
| 509 |
+
"step": 118
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 10.909090909090908,
|
| 513 |
+
"grad_norm": 1.7919278144836426,
|
| 514 |
+
"learning_rate": 9.580542287160348e-05,
|
| 515 |
+
"loss": 0.06,
|
| 516 |
+
"step": 120
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 11.0,
|
| 520 |
+
"eval_loss": 2.47693133354187,
|
| 521 |
+
"eval_runtime": 9.6239,
|
| 522 |
+
"eval_samples_per_second": 2.494,
|
| 523 |
+
"eval_steps_per_second": 2.494,
|
| 524 |
+
"step": 121
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 11.090909090909092,
|
| 528 |
+
"grad_norm": 0.7210983037948608,
|
| 529 |
+
"learning_rate": 9.554728301876526e-05,
|
| 530 |
+
"loss": 0.0226,
|
| 531 |
+
"step": 122
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 11.272727272727273,
|
| 535 |
+
"grad_norm": 0.9753442406654358,
|
| 536 |
+
"learning_rate": 9.528180468815155e-05,
|
| 537 |
+
"loss": 0.0168,
|
| 538 |
+
"step": 124
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 11.454545454545455,
|
| 542 |
+
"grad_norm": 1.1973837614059448,
|
| 543 |
+
"learning_rate": 9.50090306530454e-05,
|
| 544 |
+
"loss": 0.0248,
|
| 545 |
+
"step": 126
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 11.636363636363637,
|
| 549 |
+
"grad_norm": 0.9973687529563904,
|
| 550 |
+
"learning_rate": 9.472900486219769e-05,
|
| 551 |
+
"loss": 0.0107,
|
| 552 |
+
"step": 128
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 11.818181818181818,
|
| 556 |
+
"grad_norm": 1.4094384908676147,
|
| 557 |
+
"learning_rate": 9.444177243274618e-05,
|
| 558 |
+
"loss": 0.0223,
|
| 559 |
+
"step": 130
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 12.0,
|
| 563 |
+
"grad_norm": 1.581376552581787,
|
| 564 |
+
"learning_rate": 9.414737964294636e-05,
|
| 565 |
+
"loss": 0.0548,
|
| 566 |
+
"step": 132
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 12.0,
|
| 570 |
+
"eval_loss": 2.9299166202545166,
|
| 571 |
+
"eval_runtime": 9.6267,
|
| 572 |
+
"eval_samples_per_second": 2.493,
|
| 573 |
+
"eval_steps_per_second": 2.493,
|
| 574 |
+
"step": 132
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 12.0,
|
| 578 |
+
"step": 132,
|
| 579 |
+
"total_flos": 1.6209403933884416e+16,
|
| 580 |
+
"train_loss": 0.7309455393926438,
|
| 581 |
+
"train_runtime": 1236.3069,
|
| 582 |
+
"train_samples_per_second": 3.559,
|
| 583 |
+
"train_steps_per_second": 0.445
|
| 584 |
+
}
|
| 585 |
+
],
|
| 586 |
+
"logging_steps": 2,
|
| 587 |
+
"max_steps": 550,
|
| 588 |
+
"num_input_tokens_seen": 0,
|
| 589 |
+
"num_train_epochs": 50,
|
| 590 |
+
"save_steps": 25,
|
| 591 |
+
"stateful_callbacks": {
|
| 592 |
+
"EarlyStoppingCallback": {
|
| 593 |
+
"args": {
|
| 594 |
+
"early_stopping_patience": 7,
|
| 595 |
+
"early_stopping_threshold": 0.0
|
| 596 |
+
},
|
| 597 |
+
"attributes": {
|
| 598 |
+
"early_stopping_patience_counter": 0
|
| 599 |
+
}
|
| 600 |
+
},
|
| 601 |
+
"TrainerControl": {
|
| 602 |
+
"args": {
|
| 603 |
+
"should_epoch_stop": false,
|
| 604 |
+
"should_evaluate": false,
|
| 605 |
+
"should_log": false,
|
| 606 |
+
"should_save": true,
|
| 607 |
+
"should_training_stop": true
|
| 608 |
+
},
|
| 609 |
+
"attributes": {}
|
| 610 |
+
}
|
| 611 |
+
},
|
| 612 |
+
"total_flos": 1.6209403933884416e+16,
|
| 613 |
+
"train_batch_size": 1,
|
| 614 |
+
"trial_name": null,
|
| 615 |
+
"trial_params": null
|
| 616 |
+
}
|