Commit
•
7038762
1
Parent(s):
718791c
Model save
Browse files- README.md +67 -0
- all_results.json +9 -0
- generation_config.json +6 -0
- train_results.json +9 -0
- trainer_state.json +610 -0
README.md
ADDED
|
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
base_model: mistralai/Mistral-7B-v0.1
|
| 5 |
+
tags:
|
| 6 |
+
- trl
|
| 7 |
+
- sft
|
| 8 |
+
- generated_from_trainer
|
| 9 |
+
datasets:
|
| 10 |
+
- generator
|
| 11 |
+
model-index:
|
| 12 |
+
- name: Mistral-7B-v0.1-math-sft
|
| 13 |
+
results: []
|
| 14 |
+
---
|
| 15 |
+
|
| 16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 17 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 18 |
+
|
| 19 |
+
# Mistral-7B-v0.1-math-sft
|
| 20 |
+
|
| 21 |
+
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the generator dataset.
|
| 22 |
+
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 0.1278
|
| 24 |
+
|
| 25 |
+
## Model description
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Intended uses & limitations
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training and evaluation data
|
| 34 |
+
|
| 35 |
+
More information needed
|
| 36 |
+
|
| 37 |
+
## Training procedure
|
| 38 |
+
|
| 39 |
+
### Training hyperparameters
|
| 40 |
+
|
| 41 |
+
The following hyperparameters were used during training:
|
| 42 |
+
- learning_rate: 2e-05
|
| 43 |
+
- train_batch_size: 16
|
| 44 |
+
- eval_batch_size: 8
|
| 45 |
+
- seed: 42
|
| 46 |
+
- distributed_type: multi-GPU
|
| 47 |
+
- num_devices: 8
|
| 48 |
+
- total_train_batch_size: 128
|
| 49 |
+
- total_eval_batch_size: 64
|
| 50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 51 |
+
- lr_scheduler_type: cosine
|
| 52 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 53 |
+
- num_epochs: 1
|
| 54 |
+
|
| 55 |
+
### Training results
|
| 56 |
+
|
| 57 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 58 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 59 |
+
| 0.1711 | 1.0 | 396 | 0.1278 |
|
| 60 |
+
|
| 61 |
+
|
| 62 |
+
### Framework versions
|
| 63 |
+
|
| 64 |
+
- Transformers 4.44.2
|
| 65 |
+
- Pytorch 2.4.1+cu121
|
| 66 |
+
- Datasets 3.0.0
|
| 67 |
+
- Tokenizers 0.19.1
|
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"total_flos": 165828687298560.0,
|
| 4 |
+
"train_loss": 0.24546745942548068,
|
| 5 |
+
"train_runtime": 6726.335,
|
| 6 |
+
"train_samples": 395000,
|
| 7 |
+
"train_samples_per_second": 7.533,
|
| 8 |
+
"train_steps_per_second": 0.059
|
| 9 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"transformers_version": "4.44.2"
|
| 6 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"total_flos": 165828687298560.0,
|
| 4 |
+
"train_loss": 0.24546745942548068,
|
| 5 |
+
"train_runtime": 6726.335,
|
| 6 |
+
"train_samples": 395000,
|
| 7 |
+
"train_samples_per_second": 7.533,
|
| 8 |
+
"train_steps_per_second": 0.059
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,610 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 396,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0025252525252525255,
|
| 13 |
+
"grad_norm": 32.43943786621094,
|
| 14 |
+
"learning_rate": 5.000000000000001e-07,
|
| 15 |
+
"loss": 0.9259,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.012626262626262626,
|
| 20 |
+
"grad_norm": 18.802860260009766,
|
| 21 |
+
"learning_rate": 2.5e-06,
|
| 22 |
+
"loss": 0.8543,
|
| 23 |
+
"step": 5
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.025252525252525252,
|
| 27 |
+
"grad_norm": 11.966745376586914,
|
| 28 |
+
"learning_rate": 5e-06,
|
| 29 |
+
"loss": 0.6558,
|
| 30 |
+
"step": 10
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.03787878787878788,
|
| 34 |
+
"grad_norm": 4.041635990142822,
|
| 35 |
+
"learning_rate": 7.500000000000001e-06,
|
| 36 |
+
"loss": 0.5411,
|
| 37 |
+
"step": 15
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.050505050505050504,
|
| 41 |
+
"grad_norm": 2.9634244441986084,
|
| 42 |
+
"learning_rate": 1e-05,
|
| 43 |
+
"loss": 0.5026,
|
| 44 |
+
"step": 20
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.06313131313131314,
|
| 48 |
+
"grad_norm": 4.437589168548584,
|
| 49 |
+
"learning_rate": 1.25e-05,
|
| 50 |
+
"loss": 0.4873,
|
| 51 |
+
"step": 25
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.07575757575757576,
|
| 55 |
+
"grad_norm": 3.071434497833252,
|
| 56 |
+
"learning_rate": 1.5000000000000002e-05,
|
| 57 |
+
"loss": 0.4655,
|
| 58 |
+
"step": 30
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.08838383838383838,
|
| 62 |
+
"grad_norm": 2.649683713912964,
|
| 63 |
+
"learning_rate": 1.7500000000000002e-05,
|
| 64 |
+
"loss": 0.4277,
|
| 65 |
+
"step": 35
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.10101010101010101,
|
| 69 |
+
"grad_norm": 1.9353753328323364,
|
| 70 |
+
"learning_rate": 2e-05,
|
| 71 |
+
"loss": 0.4123,
|
| 72 |
+
"step": 40
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.11363636363636363,
|
| 76 |
+
"grad_norm": 1.7575881481170654,
|
| 77 |
+
"learning_rate": 1.9990267166335665e-05,
|
| 78 |
+
"loss": 0.3856,
|
| 79 |
+
"step": 45
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.12626262626262627,
|
| 83 |
+
"grad_norm": 1.685341715812683,
|
| 84 |
+
"learning_rate": 1.9961087610952893e-05,
|
| 85 |
+
"loss": 0.3652,
|
| 86 |
+
"step": 50
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.1388888888888889,
|
| 90 |
+
"grad_norm": 1.361409068107605,
|
| 91 |
+
"learning_rate": 1.9912518133803466e-05,
|
| 92 |
+
"loss": 0.3402,
|
| 93 |
+
"step": 55
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.15151515151515152,
|
| 97 |
+
"grad_norm": 1.4926209449768066,
|
| 98 |
+
"learning_rate": 1.9844653278615836e-05,
|
| 99 |
+
"loss": 0.3274,
|
| 100 |
+
"step": 60
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.16414141414141414,
|
| 104 |
+
"grad_norm": 1.358234167098999,
|
| 105 |
+
"learning_rate": 1.9757625148859444e-05,
|
| 106 |
+
"loss": 0.3158,
|
| 107 |
+
"step": 65
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.17676767676767677,
|
| 111 |
+
"grad_norm": 1.3026068210601807,
|
| 112 |
+
"learning_rate": 1.9651603150596497e-05,
|
| 113 |
+
"loss": 0.3039,
|
| 114 |
+
"step": 70
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.1893939393939394,
|
| 118 |
+
"grad_norm": 1.4417624473571777,
|
| 119 |
+
"learning_rate": 1.9526793662721768e-05,
|
| 120 |
+
"loss": 0.2947,
|
| 121 |
+
"step": 75
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.20202020202020202,
|
| 125 |
+
"grad_norm": 1.306173324584961,
|
| 126 |
+
"learning_rate": 1.9383439635232296e-05,
|
| 127 |
+
"loss": 0.2866,
|
| 128 |
+
"step": 80
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.21464646464646464,
|
| 132 |
+
"grad_norm": 1.3218271732330322,
|
| 133 |
+
"learning_rate": 1.922182011630902e-05,
|
| 134 |
+
"loss": 0.2807,
|
| 135 |
+
"step": 85
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.22727272727272727,
|
| 139 |
+
"grad_norm": 1.3361605405807495,
|
| 140 |
+
"learning_rate": 1.904224970913085e-05,
|
| 141 |
+
"loss": 0.2705,
|
| 142 |
+
"step": 90
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.2398989898989899,
|
| 146 |
+
"grad_norm": 1.2049956321716309,
|
| 147 |
+
"learning_rate": 1.8845077959478615e-05,
|
| 148 |
+
"loss": 0.2647,
|
| 149 |
+
"step": 95
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.25252525252525254,
|
| 153 |
+
"grad_norm": 1.0850019454956055,
|
| 154 |
+
"learning_rate": 1.8630688675320844e-05,
|
| 155 |
+
"loss": 0.2558,
|
| 156 |
+
"step": 100
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.26515151515151514,
|
| 160 |
+
"grad_norm": 1.0417327880859375,
|
| 161 |
+
"learning_rate": 1.839949917970596e-05,
|
| 162 |
+
"loss": 0.2519,
|
| 163 |
+
"step": 105
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.2777777777777778,
|
| 167 |
+
"grad_norm": 1.1492786407470703,
|
| 168 |
+
"learning_rate": 1.815195949841512e-05,
|
| 169 |
+
"loss": 0.2491,
|
| 170 |
+
"step": 110
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.2904040404040404,
|
| 174 |
+
"grad_norm": 1.007467269897461,
|
| 175 |
+
"learning_rate": 1.788855148395699e-05,
|
| 176 |
+
"loss": 0.2399,
|
| 177 |
+
"step": 115
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.30303030303030304,
|
| 181 |
+
"grad_norm": 0.9345642924308777,
|
| 182 |
+
"learning_rate": 1.7609787877609678e-05,
|
| 183 |
+
"loss": 0.2389,
|
| 184 |
+
"step": 120
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.31565656565656564,
|
| 188 |
+
"grad_norm": 0.907543957233429,
|
| 189 |
+
"learning_rate": 1.731621131133564e-05,
|
| 190 |
+
"loss": 0.2398,
|
| 191 |
+
"step": 125
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.3282828282828283,
|
| 195 |
+
"grad_norm": 0.9041042923927307,
|
| 196 |
+
"learning_rate": 1.700839325151233e-05,
|
| 197 |
+
"loss": 0.2342,
|
| 198 |
+
"step": 130
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.3409090909090909,
|
| 202 |
+
"grad_norm": 0.9225403070449829,
|
| 203 |
+
"learning_rate": 1.668693288653478e-05,
|
| 204 |
+
"loss": 0.2311,
|
| 205 |
+
"step": 135
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.35353535353535354,
|
| 209 |
+
"grad_norm": 0.8411688208580017,
|
| 210 |
+
"learning_rate": 1.6352455960455385e-05,
|
| 211 |
+
"loss": 0.2281,
|
| 212 |
+
"step": 140
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.3661616161616162,
|
| 216 |
+
"grad_norm": 0.8488685488700867,
|
| 217 |
+
"learning_rate": 1.600561355493137e-05,
|
| 218 |
+
"loss": 0.2218,
|
| 219 |
+
"step": 145
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.3787878787878788,
|
| 223 |
+
"grad_norm": 0.8601275086402893,
|
| 224 |
+
"learning_rate": 1.5647080821850868e-05,
|
| 225 |
+
"loss": 0.2223,
|
| 226 |
+
"step": 150
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.39141414141414144,
|
| 230 |
+
"grad_norm": 0.8070423007011414,
|
| 231 |
+
"learning_rate": 1.5277555669104743e-05,
|
| 232 |
+
"loss": 0.2153,
|
| 233 |
+
"step": 155
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.40404040404040403,
|
| 237 |
+
"grad_norm": 0.8097870945930481,
|
| 238 |
+
"learning_rate": 1.4897757402062285e-05,
|
| 239 |
+
"loss": 0.2162,
|
| 240 |
+
"step": 160
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.4166666666666667,
|
| 244 |
+
"grad_norm": 0.8055990934371948,
|
| 245 |
+
"learning_rate": 1.4508425323395319e-05,
|
| 246 |
+
"loss": 0.2134,
|
| 247 |
+
"step": 165
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.4292929292929293,
|
| 251 |
+
"grad_norm": 0.8727415800094604,
|
| 252 |
+
"learning_rate": 1.411031729397622e-05,
|
| 253 |
+
"loss": 0.2115,
|
| 254 |
+
"step": 170
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.44191919191919193,
|
| 258 |
+
"grad_norm": 0.79546058177948,
|
| 259 |
+
"learning_rate": 1.370420825765114e-05,
|
| 260 |
+
"loss": 0.2123,
|
| 261 |
+
"step": 175
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.45454545454545453,
|
| 265 |
+
"grad_norm": 0.7648718953132629,
|
| 266 |
+
"learning_rate": 1.32908887327601e-05,
|
| 267 |
+
"loss": 0.2101,
|
| 268 |
+
"step": 180
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.4671717171717172,
|
| 272 |
+
"grad_norm": 0.7550036311149597,
|
| 273 |
+
"learning_rate": 1.2871163273340309e-05,
|
| 274 |
+
"loss": 0.2027,
|
| 275 |
+
"step": 185
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.4797979797979798,
|
| 279 |
+
"grad_norm": 0.7257375121116638,
|
| 280 |
+
"learning_rate": 1.2445848903008001e-05,
|
| 281 |
+
"loss": 0.202,
|
| 282 |
+
"step": 190
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.49242424242424243,
|
| 286 |
+
"grad_norm": 0.7294561266899109,
|
| 287 |
+
"learning_rate": 1.201577352456748e-05,
|
| 288 |
+
"loss": 0.2022,
|
| 289 |
+
"step": 195
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.5050505050505051,
|
| 293 |
+
"grad_norm": 0.7660893797874451,
|
| 294 |
+
"learning_rate": 1.1581774308443042e-05,
|
| 295 |
+
"loss": 0.1997,
|
| 296 |
+
"step": 200
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.5176767676767676,
|
| 300 |
+
"grad_norm": 0.7221814393997192,
|
| 301 |
+
"learning_rate": 1.1144696063070884e-05,
|
| 302 |
+
"loss": 0.1963,
|
| 303 |
+
"step": 205
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.5303030303030303,
|
| 307 |
+
"grad_norm": 0.6848293542861938,
|
| 308 |
+
"learning_rate": 1.070538959042311e-05,
|
| 309 |
+
"loss": 0.1957,
|
| 310 |
+
"step": 210
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.5429292929292929,
|
| 314 |
+
"grad_norm": 0.6825312972068787,
|
| 315 |
+
"learning_rate": 1.026471002986491e-05,
|
| 316 |
+
"loss": 0.1951,
|
| 317 |
+
"step": 215
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.5555555555555556,
|
| 321 |
+
"grad_norm": 0.6754021644592285,
|
| 322 |
+
"learning_rate": 9.823515193568715e-06,
|
| 323 |
+
"loss": 0.1902,
|
| 324 |
+
"step": 220
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.5681818181818182,
|
| 328 |
+
"grad_norm": 0.6493006348609924,
|
| 329 |
+
"learning_rate": 9.382663896725578e-06,
|
| 330 |
+
"loss": 0.1892,
|
| 331 |
+
"step": 225
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.5808080808080808,
|
| 335 |
+
"grad_norm": 0.6259664297103882,
|
| 336 |
+
"learning_rate": 8.943014285804072e-06,
|
| 337 |
+
"loss": 0.1919,
|
| 338 |
+
"step": 230
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.5934343434343434,
|
| 342 |
+
"grad_norm": 0.6426423192024231,
|
| 343 |
+
"learning_rate": 8.505422168110936e-06,
|
| 344 |
+
"loss": 0.1871,
|
| 345 |
+
"step": 235
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.6060606060606061,
|
| 349 |
+
"grad_norm": 0.6354442834854126,
|
| 350 |
+
"learning_rate": 8.070739345905032e-06,
|
| 351 |
+
"loss": 0.1852,
|
| 352 |
+
"step": 240
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.6186868686868687,
|
| 356 |
+
"grad_norm": 0.6016388535499573,
|
| 357 |
+
"learning_rate": 7.639811958307421e-06,
|
| 358 |
+
"loss": 0.1856,
|
| 359 |
+
"step": 245
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.6313131313131313,
|
| 363 |
+
"grad_norm": 0.6031273007392883,
|
| 364 |
+
"learning_rate": 7.213478834235079e-06,
|
| 365 |
+
"loss": 0.1854,
|
| 366 |
+
"step": 250
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.6439393939393939,
|
| 370 |
+
"grad_norm": 0.6175743937492371,
|
| 371 |
+
"learning_rate": 6.792569859564445e-06,
|
| 372 |
+
"loss": 0.183,
|
| 373 |
+
"step": 255
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.6565656565656566,
|
| 377 |
+
"grad_norm": 0.6094260215759277,
|
| 378 |
+
"learning_rate": 6.3779043617031775e-06,
|
| 379 |
+
"loss": 0.1829,
|
| 380 |
+
"step": 260
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.6691919191919192,
|
| 384 |
+
"grad_norm": 0.5978714227676392,
|
| 385 |
+
"learning_rate": 5.9702895147146765e-06,
|
| 386 |
+
"loss": 0.1824,
|
| 387 |
+
"step": 265
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.6818181818181818,
|
| 391 |
+
"grad_norm": 0.5708032846450806,
|
| 392 |
+
"learning_rate": 5.570518768099918e-06,
|
| 393 |
+
"loss": 0.1785,
|
| 394 |
+
"step": 270
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.6944444444444444,
|
| 398 |
+
"grad_norm": 0.5738463401794434,
|
| 399 |
+
"learning_rate": 5.179370302295037e-06,
|
| 400 |
+
"loss": 0.1816,
|
| 401 |
+
"step": 275
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.7070707070707071,
|
| 405 |
+
"grad_norm": 0.5719105005264282,
|
| 406 |
+
"learning_rate": 4.797605513891179e-06,
|
| 407 |
+
"loss": 0.1758,
|
| 408 |
+
"step": 280
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.7196969696969697,
|
| 412 |
+
"grad_norm": 0.5968112945556641,
|
| 413 |
+
"learning_rate": 4.425967533525229e-06,
|
| 414 |
+
"loss": 0.1779,
|
| 415 |
+
"step": 285
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.7323232323232324,
|
| 419 |
+
"grad_norm": 0.5471134781837463,
|
| 420 |
+
"learning_rate": 4.0651797793264356e-06,
|
| 421 |
+
"loss": 0.1751,
|
| 422 |
+
"step": 290
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.7449494949494949,
|
| 426 |
+
"grad_norm": 0.5474812984466553,
|
| 427 |
+
"learning_rate": 3.7159445487347546e-06,
|
| 428 |
+
"loss": 0.1769,
|
| 429 |
+
"step": 295
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.7575757575757576,
|
| 433 |
+
"grad_norm": 0.5562990307807922,
|
| 434 |
+
"learning_rate": 3.378941651431996e-06,
|
| 435 |
+
"loss": 0.1744,
|
| 436 |
+
"step": 300
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.7702020202020202,
|
| 440 |
+
"grad_norm": 0.5516139268875122,
|
| 441 |
+
"learning_rate": 3.054827086046931e-06,
|
| 442 |
+
"loss": 0.1718,
|
| 443 |
+
"step": 305
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.7828282828282829,
|
| 447 |
+
"grad_norm": 0.5370557308197021,
|
| 448 |
+
"learning_rate": 2.7442317632101743e-06,
|
| 449 |
+
"loss": 0.171,
|
| 450 |
+
"step": 310
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.7954545454545454,
|
| 454 |
+
"grad_norm": 0.5318647623062134,
|
| 455 |
+
"learning_rate": 2.447760277444543e-06,
|
| 456 |
+
"loss": 0.1714,
|
| 457 |
+
"step": 315
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.8080808080808081,
|
| 461 |
+
"grad_norm": 0.5430074334144592,
|
| 462 |
+
"learning_rate": 2.165989730281475e-06,
|
| 463 |
+
"loss": 0.1727,
|
| 464 |
+
"step": 320
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.8207070707070707,
|
| 468 |
+
"grad_norm": 0.575107216835022,
|
| 469 |
+
"learning_rate": 1.8994686068943792e-06,
|
| 470 |
+
"loss": 0.1695,
|
| 471 |
+
"step": 325
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.8333333333333334,
|
| 475 |
+
"grad_norm": 0.566429615020752,
|
| 476 |
+
"learning_rate": 1.6487157084356454e-06,
|
| 477 |
+
"loss": 0.1718,
|
| 478 |
+
"step": 330
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.8459595959595959,
|
| 482 |
+
"grad_norm": 0.5522480607032776,
|
| 483 |
+
"learning_rate": 1.414219142155585e-06,
|
| 484 |
+
"loss": 0.1694,
|
| 485 |
+
"step": 335
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.8585858585858586,
|
| 489 |
+
"grad_norm": 0.5301287174224854,
|
| 490 |
+
"learning_rate": 1.196435371269089e-06,
|
| 491 |
+
"loss": 0.1695,
|
| 492 |
+
"step": 340
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.8712121212121212,
|
| 496 |
+
"grad_norm": 0.5381254553794861,
|
| 497 |
+
"learning_rate": 9.957883264195224e-07,
|
| 498 |
+
"loss": 0.1709,
|
| 499 |
+
"step": 345
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.8838383838383839,
|
| 503 |
+
"grad_norm": 0.52545166015625,
|
| 504 |
+
"learning_rate": 8.126685804694401e-07,
|
| 505 |
+
"loss": 0.1686,
|
| 506 |
+
"step": 350
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.8964646464646465,
|
| 510 |
+
"grad_norm": 0.5226617455482483,
|
| 511 |
+
"learning_rate": 6.47432588224437e-07,
|
| 512 |
+
"loss": 0.1674,
|
| 513 |
+
"step": 355
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.9090909090909091,
|
| 517 |
+
"grad_norm": 0.5346973538398743,
|
| 518 |
+
"learning_rate": 5.004019925700921e-07,
|
| 519 |
+
"loss": 0.1692,
|
| 520 |
+
"step": 360
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.9217171717171717,
|
| 524 |
+
"grad_norm": 0.5276767015457153,
|
| 525 |
+
"learning_rate": 3.7186299837261855e-07,
|
| 526 |
+
"loss": 0.1699,
|
| 527 |
+
"step": 365
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.9343434343434344,
|
| 531 |
+
"grad_norm": 0.5401973128318787,
|
| 532 |
+
"learning_rate": 2.620658153619959e-07,
|
| 533 |
+
"loss": 0.1684,
|
| 534 |
+
"step": 370
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.946969696969697,
|
| 538 |
+
"grad_norm": 0.5313433408737183,
|
| 539 |
+
"learning_rate": 1.7122417108203727e-07,
|
| 540 |
+
"loss": 0.1691,
|
| 541 |
+
"step": 375
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.9595959595959596,
|
| 545 |
+
"grad_norm": 0.5390282273292542,
|
| 546 |
+
"learning_rate": 9.951489485545696e-08,
|
| 547 |
+
"loss": 0.169,
|
| 548 |
+
"step": 380
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.9722222222222222,
|
| 552 |
+
"grad_norm": 0.5103330016136169,
|
| 553 |
+
"learning_rate": 4.7077573573793836e-08,
|
| 554 |
+
"loss": 0.1653,
|
| 555 |
+
"step": 385
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.9848484848484849,
|
| 559 |
+
"grad_norm": 0.5155799388885498,
|
| 560 |
+
"learning_rate": 1.4014279982216272e-08,
|
| 561 |
+
"loss": 0.1668,
|
| 562 |
+
"step": 390
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.9974747474747475,
|
| 566 |
+
"grad_norm": 0.5293468832969666,
|
| 567 |
+
"learning_rate": 3.893739881088987e-10,
|
| 568 |
+
"loss": 0.1711,
|
| 569 |
+
"step": 395
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 1.0,
|
| 573 |
+
"eval_loss": 0.12780985236167908,
|
| 574 |
+
"eval_runtime": 1.3224,
|
| 575 |
+
"eval_samples_per_second": 0.756,
|
| 576 |
+
"eval_steps_per_second": 0.756,
|
| 577 |
+
"step": 396
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 1.0,
|
| 581 |
+
"step": 396,
|
| 582 |
+
"total_flos": 165828687298560.0,
|
| 583 |
+
"train_loss": 0.24546745942548068,
|
| 584 |
+
"train_runtime": 6726.335,
|
| 585 |
+
"train_samples_per_second": 7.533,
|
| 586 |
+
"train_steps_per_second": 0.059
|
| 587 |
+
}
|
| 588 |
+
],
|
| 589 |
+
"logging_steps": 5,
|
| 590 |
+
"max_steps": 396,
|
| 591 |
+
"num_input_tokens_seen": 0,
|
| 592 |
+
"num_train_epochs": 1,
|
| 593 |
+
"save_steps": 100,
|
| 594 |
+
"stateful_callbacks": {
|
| 595 |
+
"TrainerControl": {
|
| 596 |
+
"args": {
|
| 597 |
+
"should_epoch_stop": false,
|
| 598 |
+
"should_evaluate": false,
|
| 599 |
+
"should_log": false,
|
| 600 |
+
"should_save": true,
|
| 601 |
+
"should_training_stop": true
|
| 602 |
+
},
|
| 603 |
+
"attributes": {}
|
| 604 |
+
}
|
| 605 |
+
},
|
| 606 |
+
"total_flos": 165828687298560.0,
|
| 607 |
+
"train_batch_size": 16,
|
| 608 |
+
"trial_name": null,
|
| 609 |
+
"trial_params": null
|
| 610 |
+
}
|