Training completed
Browse files- README.md +60 -0
- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +742 -0
README.md
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: llama3.2
|
| 3 |
+
base_model: meta-llama/Llama-3.2-3B-Instruct
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
library_name: peft
|
| 7 |
+
model-index:
|
| 8 |
+
- name: model
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
# model
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [meta-llama/Llama-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct) on an unknown dataset.
|
| 18 |
+
|
| 19 |
+
## Model description
|
| 20 |
+
|
| 21 |
+
More information needed
|
| 22 |
+
|
| 23 |
+
## Intended uses & limitations
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Training and evaluation data
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training procedure
|
| 32 |
+
|
| 33 |
+
### Training hyperparameters
|
| 34 |
+
|
| 35 |
+
The following hyperparameters were used during training:
|
| 36 |
+
- learning_rate: 0.0001
|
| 37 |
+
- train_batch_size: 2
|
| 38 |
+
- eval_batch_size: 8
|
| 39 |
+
- seed: 42
|
| 40 |
+
- distributed_type: multi-GPU
|
| 41 |
+
- num_devices: 8
|
| 42 |
+
- gradient_accumulation_steps: 10
|
| 43 |
+
- total_train_batch_size: 160
|
| 44 |
+
- total_eval_batch_size: 64
|
| 45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
+
- lr_scheduler_type: linear
|
| 47 |
+
- lr_scheduler_warmup_ratio: 0.03
|
| 48 |
+
- training_steps: 1000
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
|
| 53 |
+
|
| 54 |
+
### Framework versions
|
| 55 |
+
|
| 56 |
+
- PEFT 0.14.0
|
| 57 |
+
- Transformers 4.43.3
|
| 58 |
+
- Pytorch 2.3.0+cu121
|
| 59 |
+
- Datasets 3.2.0
|
| 60 |
+
- Tokenizers 0.19.1
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.82648401826484,
|
| 3 |
+
"total_flos": 2.7828922766852096e+18,
|
| 4 |
+
"train_loss": 0.1416516397893429,
|
| 5 |
+
"train_runtime": 13741.8812,
|
| 6 |
+
"train_samples_per_second": 11.643,
|
| 7 |
+
"train_steps_per_second": 0.073
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.82648401826484,
|
| 3 |
+
"total_flos": 2.7828922766852096e+18,
|
| 4 |
+
"train_loss": 0.1416516397893429,
|
| 5 |
+
"train_runtime": 13741.8812,
|
| 6 |
+
"train_samples_per_second": 11.643,
|
| 7 |
+
"train_steps_per_second": 0.073
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,742 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.82648401826484,
|
| 5 |
+
"eval_steps": 0,
|
| 6 |
+
"global_step": 1000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0182648401826484,
|
| 13 |
+
"grad_norm": 3.1544902324676514,
|
| 14 |
+
"learning_rate": 8.384962462644227e-05,
|
| 15 |
+
"loss": 6.5825,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.0365296803652968,
|
| 20 |
+
"grad_norm": 4.691030025482178,
|
| 21 |
+
"learning_rate": 9.403937698096759e-05,
|
| 22 |
+
"loss": 2.2258,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.0547945205479452,
|
| 27 |
+
"grad_norm": 0.15685631334781647,
|
| 28 |
+
"learning_rate": 0.0001,
|
| 29 |
+
"loss": 0.7147,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.0730593607305936,
|
| 34 |
+
"grad_norm": 0.2332121729850769,
|
| 35 |
+
"learning_rate": 0.0001,
|
| 36 |
+
"loss": 0.0805,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.091324200913242,
|
| 41 |
+
"grad_norm": 0.16184434294700623,
|
| 42 |
+
"learning_rate": 0.0001,
|
| 43 |
+
"loss": 0.0756,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.1095890410958904,
|
| 48 |
+
"grad_norm": 0.12418559938669205,
|
| 49 |
+
"learning_rate": 0.0001,
|
| 50 |
+
"loss": 0.0689,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.1278538812785388,
|
| 55 |
+
"grad_norm": 0.07869353890419006,
|
| 56 |
+
"learning_rate": 0.0001,
|
| 57 |
+
"loss": 0.0613,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.1461187214611872,
|
| 62 |
+
"grad_norm": 0.08317060768604279,
|
| 63 |
+
"learning_rate": 0.0001,
|
| 64 |
+
"loss": 0.0588,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.1643835616438356,
|
| 69 |
+
"grad_norm": 0.03102727420628071,
|
| 70 |
+
"learning_rate": 0.0001,
|
| 71 |
+
"loss": 0.0558,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.182648401826484,
|
| 76 |
+
"grad_norm": 0.03055960312485695,
|
| 77 |
+
"learning_rate": 0.0001,
|
| 78 |
+
"loss": 0.0524,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.2009132420091324,
|
| 83 |
+
"grad_norm": 0.044805943965911865,
|
| 84 |
+
"learning_rate": 0.0001,
|
| 85 |
+
"loss": 0.053,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.2191780821917808,
|
| 90 |
+
"grad_norm": 0.022071639075875282,
|
| 91 |
+
"learning_rate": 0.0001,
|
| 92 |
+
"loss": 0.0514,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.2374429223744292,
|
| 97 |
+
"grad_norm": 0.02765820547938347,
|
| 98 |
+
"learning_rate": 0.0001,
|
| 99 |
+
"loss": 0.0539,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.2557077625570776,
|
| 104 |
+
"grad_norm": 0.07519228011369705,
|
| 105 |
+
"learning_rate": 0.0001,
|
| 106 |
+
"loss": 0.0521,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.273972602739726,
|
| 111 |
+
"grad_norm": 0.03463088348507881,
|
| 112 |
+
"learning_rate": 0.0001,
|
| 113 |
+
"loss": 0.0506,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.2922374429223744,
|
| 118 |
+
"grad_norm": 0.02032029815018177,
|
| 119 |
+
"learning_rate": 0.0001,
|
| 120 |
+
"loss": 0.0505,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.3105022831050228,
|
| 125 |
+
"grad_norm": 0.02619280107319355,
|
| 126 |
+
"learning_rate": 0.0001,
|
| 127 |
+
"loss": 0.0502,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.3287671232876712,
|
| 132 |
+
"grad_norm": 0.0779644325375557,
|
| 133 |
+
"learning_rate": 0.0001,
|
| 134 |
+
"loss": 0.0508,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.3470319634703196,
|
| 139 |
+
"grad_norm": 0.020659184083342552,
|
| 140 |
+
"learning_rate": 0.0001,
|
| 141 |
+
"loss": 0.0498,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.365296803652968,
|
| 146 |
+
"grad_norm": 0.037233296781778336,
|
| 147 |
+
"learning_rate": 0.0001,
|
| 148 |
+
"loss": 0.0522,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.3835616438356164,
|
| 153 |
+
"grad_norm": 0.024209504947066307,
|
| 154 |
+
"learning_rate": 0.0001,
|
| 155 |
+
"loss": 0.0496,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.4018264840182648,
|
| 160 |
+
"grad_norm": 0.04244047403335571,
|
| 161 |
+
"learning_rate": 0.0001,
|
| 162 |
+
"loss": 0.051,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.4200913242009132,
|
| 167 |
+
"grad_norm": 0.048180386424064636,
|
| 168 |
+
"learning_rate": 0.0001,
|
| 169 |
+
"loss": 0.0488,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.4383561643835616,
|
| 174 |
+
"grad_norm": 0.08031062036752701,
|
| 175 |
+
"learning_rate": 0.0001,
|
| 176 |
+
"loss": 0.0501,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.45662100456621,
|
| 181 |
+
"grad_norm": 0.03865548223257065,
|
| 182 |
+
"learning_rate": 0.0001,
|
| 183 |
+
"loss": 0.0486,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.4748858447488584,
|
| 188 |
+
"grad_norm": 0.02194119803607464,
|
| 189 |
+
"learning_rate": 0.0001,
|
| 190 |
+
"loss": 0.0482,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.4931506849315068,
|
| 195 |
+
"grad_norm": 0.02352655865252018,
|
| 196 |
+
"learning_rate": 0.0001,
|
| 197 |
+
"loss": 0.0498,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.5114155251141552,
|
| 202 |
+
"grad_norm": 0.038341544568538666,
|
| 203 |
+
"learning_rate": 0.0001,
|
| 204 |
+
"loss": 0.0495,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.5296803652968036,
|
| 209 |
+
"grad_norm": 0.025721246376633644,
|
| 210 |
+
"learning_rate": 0.0001,
|
| 211 |
+
"loss": 0.048,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.547945205479452,
|
| 216 |
+
"grad_norm": 0.09147298336029053,
|
| 217 |
+
"learning_rate": 0.0001,
|
| 218 |
+
"loss": 0.0482,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.5662100456621004,
|
| 223 |
+
"grad_norm": 0.06810816377401352,
|
| 224 |
+
"learning_rate": 0.0001,
|
| 225 |
+
"loss": 0.0451,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.5844748858447488,
|
| 230 |
+
"grad_norm": 0.040888071060180664,
|
| 231 |
+
"learning_rate": 0.0001,
|
| 232 |
+
"loss": 0.0451,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.6027397260273972,
|
| 237 |
+
"grad_norm": 0.019504548981785774,
|
| 238 |
+
"learning_rate": 0.0001,
|
| 239 |
+
"loss": 0.0504,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.6210045662100456,
|
| 244 |
+
"grad_norm": 0.03003929927945137,
|
| 245 |
+
"learning_rate": 0.0001,
|
| 246 |
+
"loss": 0.0462,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.639269406392694,
|
| 251 |
+
"grad_norm": 0.04315442591905594,
|
| 252 |
+
"learning_rate": 0.0001,
|
| 253 |
+
"loss": 0.0472,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.6575342465753424,
|
| 258 |
+
"grad_norm": 0.06795976310968399,
|
| 259 |
+
"learning_rate": 0.0001,
|
| 260 |
+
"loss": 0.0486,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.6757990867579908,
|
| 265 |
+
"grad_norm": 0.022645803168416023,
|
| 266 |
+
"learning_rate": 0.0001,
|
| 267 |
+
"loss": 0.0474,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.6940639269406392,
|
| 272 |
+
"grad_norm": 0.02328133024275303,
|
| 273 |
+
"learning_rate": 0.0001,
|
| 274 |
+
"loss": 0.046,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.7123287671232876,
|
| 279 |
+
"grad_norm": 0.020323406904935837,
|
| 280 |
+
"learning_rate": 0.0001,
|
| 281 |
+
"loss": 0.0474,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.730593607305936,
|
| 286 |
+
"grad_norm": 0.07395225018262863,
|
| 287 |
+
"learning_rate": 0.0001,
|
| 288 |
+
"loss": 0.0465,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.7488584474885844,
|
| 293 |
+
"grad_norm": 0.024821775034070015,
|
| 294 |
+
"learning_rate": 0.0001,
|
| 295 |
+
"loss": 0.0469,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.7671232876712328,
|
| 300 |
+
"grad_norm": 0.0158799197524786,
|
| 301 |
+
"learning_rate": 0.0001,
|
| 302 |
+
"loss": 0.0469,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.7853881278538812,
|
| 307 |
+
"grad_norm": 0.05058496072888374,
|
| 308 |
+
"learning_rate": 0.0001,
|
| 309 |
+
"loss": 0.0483,
|
| 310 |
+
"step": 430
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.8036529680365296,
|
| 314 |
+
"grad_norm": 0.045970965176820755,
|
| 315 |
+
"learning_rate": 0.0001,
|
| 316 |
+
"loss": 0.048,
|
| 317 |
+
"step": 440
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.821917808219178,
|
| 321 |
+
"grad_norm": 0.08588553965091705,
|
| 322 |
+
"learning_rate": 0.0001,
|
| 323 |
+
"loss": 0.0464,
|
| 324 |
+
"step": 450
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.8401826484018264,
|
| 328 |
+
"grad_norm": 0.03549494966864586,
|
| 329 |
+
"learning_rate": 0.0001,
|
| 330 |
+
"loss": 0.0463,
|
| 331 |
+
"step": 460
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.8584474885844748,
|
| 335 |
+
"grad_norm": 0.015155879780650139,
|
| 336 |
+
"learning_rate": 0.0001,
|
| 337 |
+
"loss": 0.0438,
|
| 338 |
+
"step": 470
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.8767123287671232,
|
| 342 |
+
"grad_norm": 0.04356207326054573,
|
| 343 |
+
"learning_rate": 0.0001,
|
| 344 |
+
"loss": 0.0459,
|
| 345 |
+
"step": 480
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.8949771689497716,
|
| 349 |
+
"grad_norm": 0.07264907658100128,
|
| 350 |
+
"learning_rate": 0.0001,
|
| 351 |
+
"loss": 0.0455,
|
| 352 |
+
"step": 490
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.91324200913242,
|
| 356 |
+
"grad_norm": 0.0752376988530159,
|
| 357 |
+
"learning_rate": 0.0001,
|
| 358 |
+
"loss": 0.0471,
|
| 359 |
+
"step": 500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.9315068493150684,
|
| 363 |
+
"grad_norm": 0.028345758095383644,
|
| 364 |
+
"learning_rate": 0.0001,
|
| 365 |
+
"loss": 0.0462,
|
| 366 |
+
"step": 510
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.9497716894977168,
|
| 370 |
+
"grad_norm": 0.038208525627851486,
|
| 371 |
+
"learning_rate": 0.0001,
|
| 372 |
+
"loss": 0.0453,
|
| 373 |
+
"step": 520
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.9680365296803652,
|
| 377 |
+
"grad_norm": 0.06613120436668396,
|
| 378 |
+
"learning_rate": 0.0001,
|
| 379 |
+
"loss": 0.0478,
|
| 380 |
+
"step": 530
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.9863013698630136,
|
| 384 |
+
"grad_norm": 0.01847919635474682,
|
| 385 |
+
"learning_rate": 0.0001,
|
| 386 |
+
"loss": 0.0461,
|
| 387 |
+
"step": 540
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 1.004566210045662,
|
| 391 |
+
"grad_norm": 0.05972537770867348,
|
| 392 |
+
"learning_rate": 0.0001,
|
| 393 |
+
"loss": 0.0464,
|
| 394 |
+
"step": 550
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 1.0228310502283104,
|
| 398 |
+
"grad_norm": 0.015237771905958652,
|
| 399 |
+
"learning_rate": 0.0001,
|
| 400 |
+
"loss": 0.0469,
|
| 401 |
+
"step": 560
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 1.0410958904109588,
|
| 405 |
+
"grad_norm": 0.040945298969745636,
|
| 406 |
+
"learning_rate": 0.0001,
|
| 407 |
+
"loss": 0.043,
|
| 408 |
+
"step": 570
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 1.0593607305936072,
|
| 412 |
+
"grad_norm": 0.0319833904504776,
|
| 413 |
+
"learning_rate": 0.0001,
|
| 414 |
+
"loss": 0.0457,
|
| 415 |
+
"step": 580
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 1.0776255707762556,
|
| 419 |
+
"grad_norm": 0.04091507941484451,
|
| 420 |
+
"learning_rate": 0.0001,
|
| 421 |
+
"loss": 0.0476,
|
| 422 |
+
"step": 590
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 1.095890410958904,
|
| 426 |
+
"grad_norm": 0.02997482568025589,
|
| 427 |
+
"learning_rate": 0.0001,
|
| 428 |
+
"loss": 0.0452,
|
| 429 |
+
"step": 600
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 1.1141552511415524,
|
| 433 |
+
"grad_norm": 0.03648979961872101,
|
| 434 |
+
"learning_rate": 0.0001,
|
| 435 |
+
"loss": 0.0477,
|
| 436 |
+
"step": 610
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 1.1324200913242009,
|
| 440 |
+
"grad_norm": 0.07507160305976868,
|
| 441 |
+
"learning_rate": 0.0001,
|
| 442 |
+
"loss": 0.0455,
|
| 443 |
+
"step": 620
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 1.1506849315068493,
|
| 447 |
+
"grad_norm": 0.04007234051823616,
|
| 448 |
+
"learning_rate": 0.0001,
|
| 449 |
+
"loss": 0.0437,
|
| 450 |
+
"step": 630
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 1.1689497716894977,
|
| 454 |
+
"grad_norm": 0.02057138830423355,
|
| 455 |
+
"learning_rate": 0.0001,
|
| 456 |
+
"loss": 0.0449,
|
| 457 |
+
"step": 640
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 1.187214611872146,
|
| 461 |
+
"grad_norm": 0.0629994347691536,
|
| 462 |
+
"learning_rate": 0.0001,
|
| 463 |
+
"loss": 0.0455,
|
| 464 |
+
"step": 650
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 1.2054794520547945,
|
| 468 |
+
"grad_norm": 0.01666969247162342,
|
| 469 |
+
"learning_rate": 0.0001,
|
| 470 |
+
"loss": 0.0445,
|
| 471 |
+
"step": 660
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 1.2237442922374429,
|
| 475 |
+
"grad_norm": 0.030777623876929283,
|
| 476 |
+
"learning_rate": 0.0001,
|
| 477 |
+
"loss": 0.0451,
|
| 478 |
+
"step": 670
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 1.2420091324200913,
|
| 482 |
+
"grad_norm": 0.03577893599867821,
|
| 483 |
+
"learning_rate": 0.0001,
|
| 484 |
+
"loss": 0.0452,
|
| 485 |
+
"step": 680
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 1.2602739726027397,
|
| 489 |
+
"grad_norm": 0.029062671586871147,
|
| 490 |
+
"learning_rate": 0.0001,
|
| 491 |
+
"loss": 0.0446,
|
| 492 |
+
"step": 690
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 1.278538812785388,
|
| 496 |
+
"grad_norm": 0.05249248445034027,
|
| 497 |
+
"learning_rate": 0.0001,
|
| 498 |
+
"loss": 0.0455,
|
| 499 |
+
"step": 700
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 1.2968036529680365,
|
| 503 |
+
"grad_norm": 0.041040170937776566,
|
| 504 |
+
"learning_rate": 0.0001,
|
| 505 |
+
"loss": 0.0448,
|
| 506 |
+
"step": 710
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 1.3150684931506849,
|
| 510 |
+
"grad_norm": 0.021207276731729507,
|
| 511 |
+
"learning_rate": 0.0001,
|
| 512 |
+
"loss": 0.0431,
|
| 513 |
+
"step": 720
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 1.3333333333333333,
|
| 517 |
+
"grad_norm": 0.01565389707684517,
|
| 518 |
+
"learning_rate": 0.0001,
|
| 519 |
+
"loss": 0.0446,
|
| 520 |
+
"step": 730
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 1.3515981735159817,
|
| 524 |
+
"grad_norm": 0.025387732312083244,
|
| 525 |
+
"learning_rate": 0.0001,
|
| 526 |
+
"loss": 0.0456,
|
| 527 |
+
"step": 740
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 1.36986301369863,
|
| 531 |
+
"grad_norm": 0.038002725690603256,
|
| 532 |
+
"learning_rate": 0.0001,
|
| 533 |
+
"loss": 0.045,
|
| 534 |
+
"step": 750
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 1.3881278538812785,
|
| 538 |
+
"grad_norm": 0.04078778624534607,
|
| 539 |
+
"learning_rate": 0.0001,
|
| 540 |
+
"loss": 0.0444,
|
| 541 |
+
"step": 760
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 1.4063926940639269,
|
| 545 |
+
"grad_norm": 0.022022055462002754,
|
| 546 |
+
"learning_rate": 0.0001,
|
| 547 |
+
"loss": 0.0456,
|
| 548 |
+
"step": 770
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 1.4246575342465753,
|
| 552 |
+
"grad_norm": 0.049356043338775635,
|
| 553 |
+
"learning_rate": 0.0001,
|
| 554 |
+
"loss": 0.0437,
|
| 555 |
+
"step": 780
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 1.4429223744292237,
|
| 559 |
+
"grad_norm": 0.020526748150587082,
|
| 560 |
+
"learning_rate": 0.0001,
|
| 561 |
+
"loss": 0.0441,
|
| 562 |
+
"step": 790
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 1.461187214611872,
|
| 566 |
+
"grad_norm": 0.024564441293478012,
|
| 567 |
+
"learning_rate": 0.0001,
|
| 568 |
+
"loss": 0.0432,
|
| 569 |
+
"step": 800
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 1.4794520547945205,
|
| 573 |
+
"grad_norm": 0.024945318698883057,
|
| 574 |
+
"learning_rate": 0.0001,
|
| 575 |
+
"loss": 0.0449,
|
| 576 |
+
"step": 810
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 1.4977168949771689,
|
| 580 |
+
"grad_norm": 0.02930104173719883,
|
| 581 |
+
"learning_rate": 0.0001,
|
| 582 |
+
"loss": 0.046,
|
| 583 |
+
"step": 820
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 1.5159817351598175,
|
| 587 |
+
"grad_norm": 0.013758889399468899,
|
| 588 |
+
"learning_rate": 0.0001,
|
| 589 |
+
"loss": 0.0452,
|
| 590 |
+
"step": 830
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 1.5342465753424657,
|
| 594 |
+
"grad_norm": 0.026020096614956856,
|
| 595 |
+
"learning_rate": 0.0001,
|
| 596 |
+
"loss": 0.0425,
|
| 597 |
+
"step": 840
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 1.5525114155251143,
|
| 601 |
+
"grad_norm": 0.015805073082447052,
|
| 602 |
+
"learning_rate": 0.0001,
|
| 603 |
+
"loss": 0.0436,
|
| 604 |
+
"step": 850
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 1.5707762557077625,
|
| 608 |
+
"grad_norm": 0.045076530426740646,
|
| 609 |
+
"learning_rate": 0.0001,
|
| 610 |
+
"loss": 0.0463,
|
| 611 |
+
"step": 860
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 1.589041095890411,
|
| 615 |
+
"grad_norm": 0.0530586875975132,
|
| 616 |
+
"learning_rate": 0.0001,
|
| 617 |
+
"loss": 0.044,
|
| 618 |
+
"step": 870
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 1.6073059360730593,
|
| 622 |
+
"grad_norm": 0.02274339646100998,
|
| 623 |
+
"learning_rate": 0.0001,
|
| 624 |
+
"loss": 0.0453,
|
| 625 |
+
"step": 880
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 1.625570776255708,
|
| 629 |
+
"grad_norm": 0.03770416975021362,
|
| 630 |
+
"learning_rate": 0.0001,
|
| 631 |
+
"loss": 0.0448,
|
| 632 |
+
"step": 890
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 1.643835616438356,
|
| 636 |
+
"grad_norm": 0.03844894468784332,
|
| 637 |
+
"learning_rate": 0.0001,
|
| 638 |
+
"loss": 0.0459,
|
| 639 |
+
"step": 900
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 1.6621004566210047,
|
| 643 |
+
"grad_norm": 0.04359343647956848,
|
| 644 |
+
"learning_rate": 0.0001,
|
| 645 |
+
"loss": 0.0428,
|
| 646 |
+
"step": 910
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 1.6803652968036529,
|
| 650 |
+
"grad_norm": 0.01994573511183262,
|
| 651 |
+
"learning_rate": 0.0001,
|
| 652 |
+
"loss": 0.0442,
|
| 653 |
+
"step": 920
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 1.6986301369863015,
|
| 657 |
+
"grad_norm": 0.015456647612154484,
|
| 658 |
+
"learning_rate": 0.0001,
|
| 659 |
+
"loss": 0.0439,
|
| 660 |
+
"step": 930
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 1.7168949771689497,
|
| 664 |
+
"grad_norm": 0.02144942246377468,
|
| 665 |
+
"learning_rate": 0.0001,
|
| 666 |
+
"loss": 0.0447,
|
| 667 |
+
"step": 940
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 1.7351598173515983,
|
| 671 |
+
"grad_norm": 0.03585704043507576,
|
| 672 |
+
"learning_rate": 0.0001,
|
| 673 |
+
"loss": 0.0462,
|
| 674 |
+
"step": 950
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 1.7534246575342465,
|
| 678 |
+
"grad_norm": 0.0445864275097847,
|
| 679 |
+
"learning_rate": 0.0001,
|
| 680 |
+
"loss": 0.0437,
|
| 681 |
+
"step": 960
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 1.771689497716895,
|
| 685 |
+
"grad_norm": 0.045315828174352646,
|
| 686 |
+
"learning_rate": 0.0001,
|
| 687 |
+
"loss": 0.0427,
|
| 688 |
+
"step": 970
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 1.7899543378995433,
|
| 692 |
+
"grad_norm": 0.025775112211704254,
|
| 693 |
+
"learning_rate": 0.0001,
|
| 694 |
+
"loss": 0.0459,
|
| 695 |
+
"step": 980
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 1.808219178082192,
|
| 699 |
+
"grad_norm": 0.02963119000196457,
|
| 700 |
+
"learning_rate": 0.0001,
|
| 701 |
+
"loss": 0.0445,
|
| 702 |
+
"step": 990
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 1.82648401826484,
|
| 706 |
+
"grad_norm": 0.04461943730711937,
|
| 707 |
+
"learning_rate": 0.0001,
|
| 708 |
+
"loss": 0.0437,
|
| 709 |
+
"step": 1000
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 1.82648401826484,
|
| 713 |
+
"step": 1000,
|
| 714 |
+
"total_flos": 2.7828922766852096e+18,
|
| 715 |
+
"train_loss": 0.1416516397893429,
|
| 716 |
+
"train_runtime": 13741.8812,
|
| 717 |
+
"train_samples_per_second": 11.643,
|
| 718 |
+
"train_steps_per_second": 0.073
|
| 719 |
+
}
|
| 720 |
+
],
|
| 721 |
+
"logging_steps": 10,
|
| 722 |
+
"max_steps": 1000,
|
| 723 |
+
"num_input_tokens_seen": 0,
|
| 724 |
+
"num_train_epochs": 2,
|
| 725 |
+
"save_steps": 300,
|
| 726 |
+
"stateful_callbacks": {
|
| 727 |
+
"TrainerControl": {
|
| 728 |
+
"args": {
|
| 729 |
+
"should_epoch_stop": false,
|
| 730 |
+
"should_evaluate": false,
|
| 731 |
+
"should_log": false,
|
| 732 |
+
"should_save": true,
|
| 733 |
+
"should_training_stop": true
|
| 734 |
+
},
|
| 735 |
+
"attributes": {}
|
| 736 |
+
}
|
| 737 |
+
},
|
| 738 |
+
"total_flos": 2.7828922766852096e+18,
|
| 739 |
+
"train_batch_size": 2,
|
| 740 |
+
"trial_name": null,
|
| 741 |
+
"trial_params": null
|
| 742 |
+
}
|