Model save
Browse files- README.md +104 -0
- all_results.json +9 -0
- train_results.json +9 -0
- trainer_state.json +649 -0
README.md
ADDED
|
@@ -0,0 +1,104 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: meta-llama/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_3_gsm8k_midset_cot_simplest
|
| 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_3_gsm8k_midset_cot_simplest
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct) on the None dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.5414
|
| 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: 0.0002
|
| 41 |
+
- train_batch_size: 4
|
| 42 |
+
- eval_batch_size: 4
|
| 43 |
+
- seed: 42
|
| 44 |
+
- distributed_type: multi-GPU
|
| 45 |
+
- gradient_accumulation_steps: 2
|
| 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 |
+
- training_steps: 200
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 55 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 56 |
+
| 1.121 | 0.04 | 5 | 1.0499 |
|
| 57 |
+
| 0.7969 | 0.08 | 10 | 0.7587 |
|
| 58 |
+
| 0.7177 | 0.12 | 15 | 0.6761 |
|
| 59 |
+
| 0.6315 | 0.16 | 20 | 0.6275 |
|
| 60 |
+
| 0.5984 | 0.2 | 25 | 0.5965 |
|
| 61 |
+
| 0.5678 | 0.24 | 30 | 0.5893 |
|
| 62 |
+
| 0.6067 | 0.28 | 35 | 0.5732 |
|
| 63 |
+
| 0.6306 | 0.32 | 40 | 0.5717 |
|
| 64 |
+
| 0.6134 | 0.36 | 45 | 0.5688 |
|
| 65 |
+
| 0.5396 | 0.4 | 50 | 0.5616 |
|
| 66 |
+
| 0.5796 | 0.44 | 55 | 0.5596 |
|
| 67 |
+
| 0.582 | 0.48 | 60 | 0.5543 |
|
| 68 |
+
| 0.5793 | 0.52 | 65 | 0.5518 |
|
| 69 |
+
| 0.4974 | 0.56 | 70 | 0.5556 |
|
| 70 |
+
| 0.5791 | 0.6 | 75 | 0.5544 |
|
| 71 |
+
| 0.5484 | 0.64 | 80 | 0.5518 |
|
| 72 |
+
| 0.5611 | 0.68 | 85 | 0.5500 |
|
| 73 |
+
| 0.5736 | 0.72 | 90 | 0.5474 |
|
| 74 |
+
| 0.5269 | 0.76 | 95 | 0.5490 |
|
| 75 |
+
| 0.58 | 0.8 | 100 | 0.5485 |
|
| 76 |
+
| 0.5295 | 0.84 | 105 | 0.5476 |
|
| 77 |
+
| 0.5124 | 0.88 | 110 | 0.5447 |
|
| 78 |
+
| 0.5368 | 0.92 | 115 | 0.5409 |
|
| 79 |
+
| 0.5705 | 0.96 | 120 | 0.5408 |
|
| 80 |
+
| 0.5244 | 1.0 | 125 | 0.5394 |
|
| 81 |
+
| 0.4334 | 1.04 | 130 | 0.5402 |
|
| 82 |
+
| 0.5256 | 1.08 | 135 | 0.5425 |
|
| 83 |
+
| 0.4398 | 1.12 | 140 | 0.5464 |
|
| 84 |
+
| 0.4843 | 1.16 | 145 | 0.5472 |
|
| 85 |
+
| 0.4437 | 1.2 | 150 | 0.5457 |
|
| 86 |
+
| 0.5133 | 1.24 | 155 | 0.5449 |
|
| 87 |
+
| 0.497 | 1.28 | 160 | 0.5427 |
|
| 88 |
+
| 0.4682 | 1.32 | 165 | 0.5420 |
|
| 89 |
+
| 0.4872 | 1.3600 | 170 | 0.5415 |
|
| 90 |
+
| 0.4763 | 1.4 | 175 | 0.5413 |
|
| 91 |
+
| 0.4647 | 1.44 | 180 | 0.5417 |
|
| 92 |
+
| 0.4679 | 1.48 | 185 | 0.5417 |
|
| 93 |
+
| 0.476 | 1.52 | 190 | 0.5414 |
|
| 94 |
+
| 0.462 | 1.56 | 195 | 0.5414 |
|
| 95 |
+
| 0.4665 | 1.6 | 200 | 0.5414 |
|
| 96 |
+
|
| 97 |
+
|
| 98 |
+
### Framework versions
|
| 99 |
+
|
| 100 |
+
- PEFT 0.12.0
|
| 101 |
+
- Transformers 4.44.2
|
| 102 |
+
- Pytorch 2.4.1+cu121
|
| 103 |
+
- Datasets 3.0.0
|
| 104 |
+
- Tokenizers 0.19.1
|
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.6,
|
| 3 |
+
"total_flos": 11601719820288.0,
|
| 4 |
+
"train_loss": 0.5555729389190673,
|
| 5 |
+
"train_runtime": 622.2423,
|
| 6 |
+
"train_samples": 1000,
|
| 7 |
+
"train_samples_per_second": 2.571,
|
| 8 |
+
"train_steps_per_second": 0.321
|
| 9 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.6,
|
| 3 |
+
"total_flos": 11601719820288.0,
|
| 4 |
+
"train_loss": 0.5555729389190673,
|
| 5 |
+
"train_runtime": 622.2423,
|
| 6 |
+
"train_samples": 1000,
|
| 7 |
+
"train_samples_per_second": 2.571,
|
| 8 |
+
"train_steps_per_second": 0.321
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,649 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.6,
|
| 5 |
+
"eval_steps": 5,
|
| 6 |
+
"global_step": 200,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.008,
|
| 13 |
+
"grad_norm": 1.2240601700710738,
|
| 14 |
+
"learning_rate": 1e-05,
|
| 15 |
+
"loss": 1.1829,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.04,
|
| 20 |
+
"grad_norm": 1.3328787157467732,
|
| 21 |
+
"learning_rate": 5e-05,
|
| 22 |
+
"loss": 1.121,
|
| 23 |
+
"step": 5
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.04,
|
| 27 |
+
"eval_loss": 1.049928903579712,
|
| 28 |
+
"eval_runtime": 3.2684,
|
| 29 |
+
"eval_samples_per_second": 6.119,
|
| 30 |
+
"eval_steps_per_second": 1.53,
|
| 31 |
+
"step": 5
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.08,
|
| 35 |
+
"grad_norm": 0.36829974889205147,
|
| 36 |
+
"learning_rate": 0.0001,
|
| 37 |
+
"loss": 0.7969,
|
| 38 |
+
"step": 10
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.08,
|
| 42 |
+
"eval_loss": 0.7586944103240967,
|
| 43 |
+
"eval_runtime": 1.8887,
|
| 44 |
+
"eval_samples_per_second": 10.589,
|
| 45 |
+
"eval_steps_per_second": 2.647,
|
| 46 |
+
"step": 10
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 0.12,
|
| 50 |
+
"grad_norm": 0.3157342201428062,
|
| 51 |
+
"learning_rate": 0.00015000000000000001,
|
| 52 |
+
"loss": 0.7177,
|
| 53 |
+
"step": 15
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.12,
|
| 57 |
+
"eval_loss": 0.6760886907577515,
|
| 58 |
+
"eval_runtime": 1.8819,
|
| 59 |
+
"eval_samples_per_second": 10.628,
|
| 60 |
+
"eval_steps_per_second": 2.657,
|
| 61 |
+
"step": 15
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 0.16,
|
| 65 |
+
"grad_norm": 0.3375491833564291,
|
| 66 |
+
"learning_rate": 0.0002,
|
| 67 |
+
"loss": 0.6315,
|
| 68 |
+
"step": 20
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.16,
|
| 72 |
+
"eval_loss": 0.6274805068969727,
|
| 73 |
+
"eval_runtime": 1.8861,
|
| 74 |
+
"eval_samples_per_second": 10.604,
|
| 75 |
+
"eval_steps_per_second": 2.651,
|
| 76 |
+
"step": 20
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.2,
|
| 80 |
+
"grad_norm": 0.4288885913090479,
|
| 81 |
+
"learning_rate": 0.00019961946980917456,
|
| 82 |
+
"loss": 0.5984,
|
| 83 |
+
"step": 25
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 0.2,
|
| 87 |
+
"eval_loss": 0.5965251922607422,
|
| 88 |
+
"eval_runtime": 1.8879,
|
| 89 |
+
"eval_samples_per_second": 10.594,
|
| 90 |
+
"eval_steps_per_second": 2.648,
|
| 91 |
+
"step": 25
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 0.24,
|
| 95 |
+
"grad_norm": 0.48479731407705157,
|
| 96 |
+
"learning_rate": 0.00019848077530122083,
|
| 97 |
+
"loss": 0.5678,
|
| 98 |
+
"step": 30
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.24,
|
| 102 |
+
"eval_loss": 0.5893207788467407,
|
| 103 |
+
"eval_runtime": 1.8836,
|
| 104 |
+
"eval_samples_per_second": 10.618,
|
| 105 |
+
"eval_steps_per_second": 2.655,
|
| 106 |
+
"step": 30
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.28,
|
| 110 |
+
"grad_norm": 0.40920359366877707,
|
| 111 |
+
"learning_rate": 0.00019659258262890683,
|
| 112 |
+
"loss": 0.6067,
|
| 113 |
+
"step": 35
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 0.28,
|
| 117 |
+
"eval_loss": 0.5732331275939941,
|
| 118 |
+
"eval_runtime": 1.8852,
|
| 119 |
+
"eval_samples_per_second": 10.609,
|
| 120 |
+
"eval_steps_per_second": 2.652,
|
| 121 |
+
"step": 35
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.32,
|
| 125 |
+
"grad_norm": 0.32156555533030146,
|
| 126 |
+
"learning_rate": 0.00019396926207859084,
|
| 127 |
+
"loss": 0.6306,
|
| 128 |
+
"step": 40
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.32,
|
| 132 |
+
"eval_loss": 0.5717456340789795,
|
| 133 |
+
"eval_runtime": 1.8847,
|
| 134 |
+
"eval_samples_per_second": 10.612,
|
| 135 |
+
"eval_steps_per_second": 2.653,
|
| 136 |
+
"step": 40
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.36,
|
| 140 |
+
"grad_norm": 0.25427281234716914,
|
| 141 |
+
"learning_rate": 0.000190630778703665,
|
| 142 |
+
"loss": 0.6134,
|
| 143 |
+
"step": 45
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.36,
|
| 147 |
+
"eval_loss": 0.5688132047653198,
|
| 148 |
+
"eval_runtime": 1.8863,
|
| 149 |
+
"eval_samples_per_second": 10.603,
|
| 150 |
+
"eval_steps_per_second": 2.651,
|
| 151 |
+
"step": 45
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.4,
|
| 155 |
+
"grad_norm": 0.31350926451796496,
|
| 156 |
+
"learning_rate": 0.00018660254037844388,
|
| 157 |
+
"loss": 0.5396,
|
| 158 |
+
"step": 50
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.4,
|
| 162 |
+
"eval_loss": 0.5616275072097778,
|
| 163 |
+
"eval_runtime": 1.8868,
|
| 164 |
+
"eval_samples_per_second": 10.6,
|
| 165 |
+
"eval_steps_per_second": 2.65,
|
| 166 |
+
"step": 50
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 0.44,
|
| 170 |
+
"grad_norm": 0.23818876822125845,
|
| 171 |
+
"learning_rate": 0.0001819152044288992,
|
| 172 |
+
"loss": 0.5796,
|
| 173 |
+
"step": 55
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 0.44,
|
| 177 |
+
"eval_loss": 0.5595570206642151,
|
| 178 |
+
"eval_runtime": 1.8863,
|
| 179 |
+
"eval_samples_per_second": 10.603,
|
| 180 |
+
"eval_steps_per_second": 2.651,
|
| 181 |
+
"step": 55
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.48,
|
| 185 |
+
"grad_norm": 0.23628589389483673,
|
| 186 |
+
"learning_rate": 0.0001766044443118978,
|
| 187 |
+
"loss": 0.582,
|
| 188 |
+
"step": 60
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.48,
|
| 192 |
+
"eval_loss": 0.5542594194412231,
|
| 193 |
+
"eval_runtime": 1.8854,
|
| 194 |
+
"eval_samples_per_second": 10.608,
|
| 195 |
+
"eval_steps_per_second": 2.652,
|
| 196 |
+
"step": 60
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 0.52,
|
| 200 |
+
"grad_norm": 0.23056898031828738,
|
| 201 |
+
"learning_rate": 0.00017071067811865476,
|
| 202 |
+
"loss": 0.5793,
|
| 203 |
+
"step": 65
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 0.52,
|
| 207 |
+
"eval_loss": 0.5517722964286804,
|
| 208 |
+
"eval_runtime": 1.8887,
|
| 209 |
+
"eval_samples_per_second": 10.589,
|
| 210 |
+
"eval_steps_per_second": 2.647,
|
| 211 |
+
"step": 65
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 0.56,
|
| 215 |
+
"grad_norm": 0.28466424696078446,
|
| 216 |
+
"learning_rate": 0.00016427876096865394,
|
| 217 |
+
"loss": 0.4974,
|
| 218 |
+
"step": 70
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.56,
|
| 222 |
+
"eval_loss": 0.555589497089386,
|
| 223 |
+
"eval_runtime": 1.8931,
|
| 224 |
+
"eval_samples_per_second": 10.564,
|
| 225 |
+
"eval_steps_per_second": 2.641,
|
| 226 |
+
"step": 70
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.6,
|
| 230 |
+
"grad_norm": 0.23423380737967384,
|
| 231 |
+
"learning_rate": 0.0001573576436351046,
|
| 232 |
+
"loss": 0.5791,
|
| 233 |
+
"step": 75
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.6,
|
| 237 |
+
"eval_loss": 0.5543732643127441,
|
| 238 |
+
"eval_runtime": 1.8851,
|
| 239 |
+
"eval_samples_per_second": 10.61,
|
| 240 |
+
"eval_steps_per_second": 2.652,
|
| 241 |
+
"step": 75
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.64,
|
| 245 |
+
"grad_norm": 0.21845424948025258,
|
| 246 |
+
"learning_rate": 0.00015000000000000001,
|
| 247 |
+
"loss": 0.5484,
|
| 248 |
+
"step": 80
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.64,
|
| 252 |
+
"eval_loss": 0.5517922639846802,
|
| 253 |
+
"eval_runtime": 1.8903,
|
| 254 |
+
"eval_samples_per_second": 10.581,
|
| 255 |
+
"eval_steps_per_second": 2.645,
|
| 256 |
+
"step": 80
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 0.68,
|
| 260 |
+
"grad_norm": 0.21666619387725577,
|
| 261 |
+
"learning_rate": 0.00014226182617406996,
|
| 262 |
+
"loss": 0.5611,
|
| 263 |
+
"step": 85
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 0.68,
|
| 267 |
+
"eval_loss": 0.550040602684021,
|
| 268 |
+
"eval_runtime": 1.8866,
|
| 269 |
+
"eval_samples_per_second": 10.601,
|
| 270 |
+
"eval_steps_per_second": 2.65,
|
| 271 |
+
"step": 85
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 0.72,
|
| 275 |
+
"grad_norm": 0.23843457677303798,
|
| 276 |
+
"learning_rate": 0.00013420201433256689,
|
| 277 |
+
"loss": 0.5736,
|
| 278 |
+
"step": 90
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 0.72,
|
| 282 |
+
"eval_loss": 0.5473921895027161,
|
| 283 |
+
"eval_runtime": 1.8892,
|
| 284 |
+
"eval_samples_per_second": 10.587,
|
| 285 |
+
"eval_steps_per_second": 2.647,
|
| 286 |
+
"step": 90
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 0.76,
|
| 290 |
+
"grad_norm": 0.24501294645887348,
|
| 291 |
+
"learning_rate": 0.00012588190451025207,
|
| 292 |
+
"loss": 0.5269,
|
| 293 |
+
"step": 95
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 0.76,
|
| 297 |
+
"eval_loss": 0.5490081906318665,
|
| 298 |
+
"eval_runtime": 1.8873,
|
| 299 |
+
"eval_samples_per_second": 10.597,
|
| 300 |
+
"eval_steps_per_second": 2.649,
|
| 301 |
+
"step": 95
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 0.8,
|
| 305 |
+
"grad_norm": 0.22278557053233525,
|
| 306 |
+
"learning_rate": 0.00011736481776669306,
|
| 307 |
+
"loss": 0.58,
|
| 308 |
+
"step": 100
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 0.8,
|
| 312 |
+
"eval_loss": 0.5484501123428345,
|
| 313 |
+
"eval_runtime": 1.8854,
|
| 314 |
+
"eval_samples_per_second": 10.608,
|
| 315 |
+
"eval_steps_per_second": 2.652,
|
| 316 |
+
"step": 100
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 0.84,
|
| 320 |
+
"grad_norm": 0.23174799050411005,
|
| 321 |
+
"learning_rate": 0.00010871557427476583,
|
| 322 |
+
"loss": 0.5295,
|
| 323 |
+
"step": 105
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 0.84,
|
| 327 |
+
"eval_loss": 0.5476487874984741,
|
| 328 |
+
"eval_runtime": 1.8895,
|
| 329 |
+
"eval_samples_per_second": 10.585,
|
| 330 |
+
"eval_steps_per_second": 2.646,
|
| 331 |
+
"step": 105
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.88,
|
| 335 |
+
"grad_norm": 0.2376662083429967,
|
| 336 |
+
"learning_rate": 0.0001,
|
| 337 |
+
"loss": 0.5124,
|
| 338 |
+
"step": 110
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.88,
|
| 342 |
+
"eval_loss": 0.5447433590888977,
|
| 343 |
+
"eval_runtime": 1.8818,
|
| 344 |
+
"eval_samples_per_second": 10.628,
|
| 345 |
+
"eval_steps_per_second": 2.657,
|
| 346 |
+
"step": 110
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.92,
|
| 350 |
+
"grad_norm": 0.24948598862935448,
|
| 351 |
+
"learning_rate": 9.128442572523417e-05,
|
| 352 |
+
"loss": 0.5368,
|
| 353 |
+
"step": 115
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.92,
|
| 357 |
+
"eval_loss": 0.5408658385276794,
|
| 358 |
+
"eval_runtime": 1.8862,
|
| 359 |
+
"eval_samples_per_second": 10.604,
|
| 360 |
+
"eval_steps_per_second": 2.651,
|
| 361 |
+
"step": 115
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 0.96,
|
| 365 |
+
"grad_norm": 0.2285562749319789,
|
| 366 |
+
"learning_rate": 8.263518223330697e-05,
|
| 367 |
+
"loss": 0.5705,
|
| 368 |
+
"step": 120
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 0.96,
|
| 372 |
+
"eval_loss": 0.5408440232276917,
|
| 373 |
+
"eval_runtime": 1.8858,
|
| 374 |
+
"eval_samples_per_second": 10.606,
|
| 375 |
+
"eval_steps_per_second": 2.651,
|
| 376 |
+
"step": 120
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 1.0,
|
| 380 |
+
"grad_norm": 0.27136795405571645,
|
| 381 |
+
"learning_rate": 7.411809548974792e-05,
|
| 382 |
+
"loss": 0.5244,
|
| 383 |
+
"step": 125
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 1.0,
|
| 387 |
+
"eval_loss": 0.5394060015678406,
|
| 388 |
+
"eval_runtime": 1.8816,
|
| 389 |
+
"eval_samples_per_second": 10.629,
|
| 390 |
+
"eval_steps_per_second": 2.657,
|
| 391 |
+
"step": 125
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 1.04,
|
| 395 |
+
"grad_norm": 0.19917020746884295,
|
| 396 |
+
"learning_rate": 6.579798566743314e-05,
|
| 397 |
+
"loss": 0.4334,
|
| 398 |
+
"step": 130
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 1.04,
|
| 402 |
+
"eval_loss": 0.5401565432548523,
|
| 403 |
+
"eval_runtime": 1.8887,
|
| 404 |
+
"eval_samples_per_second": 10.589,
|
| 405 |
+
"eval_steps_per_second": 2.647,
|
| 406 |
+
"step": 130
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 1.08,
|
| 410 |
+
"grad_norm": 0.21927162891543134,
|
| 411 |
+
"learning_rate": 5.773817382593008e-05,
|
| 412 |
+
"loss": 0.5256,
|
| 413 |
+
"step": 135
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 1.08,
|
| 417 |
+
"eval_loss": 0.5424562692642212,
|
| 418 |
+
"eval_runtime": 1.8888,
|
| 419 |
+
"eval_samples_per_second": 10.589,
|
| 420 |
+
"eval_steps_per_second": 2.647,
|
| 421 |
+
"step": 135
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 1.12,
|
| 425 |
+
"grad_norm": 0.20576619497891951,
|
| 426 |
+
"learning_rate": 5.000000000000002e-05,
|
| 427 |
+
"loss": 0.4398,
|
| 428 |
+
"step": 140
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 1.12,
|
| 432 |
+
"eval_loss": 0.5464188456535339,
|
| 433 |
+
"eval_runtime": 1.8869,
|
| 434 |
+
"eval_samples_per_second": 10.6,
|
| 435 |
+
"eval_steps_per_second": 2.65,
|
| 436 |
+
"step": 140
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 1.16,
|
| 440 |
+
"grad_norm": 0.26759310868105435,
|
| 441 |
+
"learning_rate": 4.264235636489542e-05,
|
| 442 |
+
"loss": 0.4843,
|
| 443 |
+
"step": 145
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 1.16,
|
| 447 |
+
"eval_loss": 0.5471861362457275,
|
| 448 |
+
"eval_runtime": 1.9257,
|
| 449 |
+
"eval_samples_per_second": 10.386,
|
| 450 |
+
"eval_steps_per_second": 2.596,
|
| 451 |
+
"step": 145
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 1.2,
|
| 455 |
+
"grad_norm": 0.2211439036624294,
|
| 456 |
+
"learning_rate": 3.5721239031346066e-05,
|
| 457 |
+
"loss": 0.4437,
|
| 458 |
+
"step": 150
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 1.2,
|
| 462 |
+
"eval_loss": 0.5457112193107605,
|
| 463 |
+
"eval_runtime": 1.891,
|
| 464 |
+
"eval_samples_per_second": 10.576,
|
| 465 |
+
"eval_steps_per_second": 2.644,
|
| 466 |
+
"step": 150
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 1.24,
|
| 470 |
+
"grad_norm": 0.23481942059415437,
|
| 471 |
+
"learning_rate": 2.9289321881345254e-05,
|
| 472 |
+
"loss": 0.5133,
|
| 473 |
+
"step": 155
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 1.24,
|
| 477 |
+
"eval_loss": 0.5448678135871887,
|
| 478 |
+
"eval_runtime": 1.8917,
|
| 479 |
+
"eval_samples_per_second": 10.573,
|
| 480 |
+
"eval_steps_per_second": 2.643,
|
| 481 |
+
"step": 155
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 1.28,
|
| 485 |
+
"grad_norm": 0.2678076401010754,
|
| 486 |
+
"learning_rate": 2.339555568810221e-05,
|
| 487 |
+
"loss": 0.497,
|
| 488 |
+
"step": 160
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 1.28,
|
| 492 |
+
"eval_loss": 0.5427194833755493,
|
| 493 |
+
"eval_runtime": 1.8926,
|
| 494 |
+
"eval_samples_per_second": 10.567,
|
| 495 |
+
"eval_steps_per_second": 2.642,
|
| 496 |
+
"step": 160
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 1.32,
|
| 500 |
+
"grad_norm": 0.2796679737048467,
|
| 501 |
+
"learning_rate": 1.808479557110081e-05,
|
| 502 |
+
"loss": 0.4682,
|
| 503 |
+
"step": 165
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 1.32,
|
| 507 |
+
"eval_loss": 0.5419761538505554,
|
| 508 |
+
"eval_runtime": 1.8898,
|
| 509 |
+
"eval_samples_per_second": 10.583,
|
| 510 |
+
"eval_steps_per_second": 2.646,
|
| 511 |
+
"step": 165
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 1.3599999999999999,
|
| 515 |
+
"grad_norm": 0.2306569559526473,
|
| 516 |
+
"learning_rate": 1.339745962155613e-05,
|
| 517 |
+
"loss": 0.4872,
|
| 518 |
+
"step": 170
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 1.3599999999999999,
|
| 522 |
+
"eval_loss": 0.5414702296257019,
|
| 523 |
+
"eval_runtime": 1.8927,
|
| 524 |
+
"eval_samples_per_second": 10.567,
|
| 525 |
+
"eval_steps_per_second": 2.642,
|
| 526 |
+
"step": 170
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 1.4,
|
| 530 |
+
"grad_norm": 0.24703640202499294,
|
| 531 |
+
"learning_rate": 9.369221296335006e-06,
|
| 532 |
+
"loss": 0.4763,
|
| 533 |
+
"step": 175
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 1.4,
|
| 537 |
+
"eval_loss": 0.5412562489509583,
|
| 538 |
+
"eval_runtime": 1.8941,
|
| 539 |
+
"eval_samples_per_second": 10.559,
|
| 540 |
+
"eval_steps_per_second": 2.64,
|
| 541 |
+
"step": 175
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 1.44,
|
| 545 |
+
"grad_norm": 0.20649027994314437,
|
| 546 |
+
"learning_rate": 6.030737921409169e-06,
|
| 547 |
+
"loss": 0.4647,
|
| 548 |
+
"step": 180
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 1.44,
|
| 552 |
+
"eval_loss": 0.541702926158905,
|
| 553 |
+
"eval_runtime": 1.8843,
|
| 554 |
+
"eval_samples_per_second": 10.614,
|
| 555 |
+
"eval_steps_per_second": 2.654,
|
| 556 |
+
"step": 180
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 1.48,
|
| 560 |
+
"grad_norm": 0.2674278078306123,
|
| 561 |
+
"learning_rate": 3.40741737109318e-06,
|
| 562 |
+
"loss": 0.4679,
|
| 563 |
+
"step": 185
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 1.48,
|
| 567 |
+
"eval_loss": 0.541742205619812,
|
| 568 |
+
"eval_runtime": 1.8898,
|
| 569 |
+
"eval_samples_per_second": 10.583,
|
| 570 |
+
"eval_steps_per_second": 2.646,
|
| 571 |
+
"step": 185
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 1.52,
|
| 575 |
+
"grad_norm": 0.25453255319861695,
|
| 576 |
+
"learning_rate": 1.5192246987791981e-06,
|
| 577 |
+
"loss": 0.476,
|
| 578 |
+
"step": 190
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 1.52,
|
| 582 |
+
"eval_loss": 0.5414270162582397,
|
| 583 |
+
"eval_runtime": 1.8892,
|
| 584 |
+
"eval_samples_per_second": 10.586,
|
| 585 |
+
"eval_steps_per_second": 2.647,
|
| 586 |
+
"step": 190
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 1.56,
|
| 590 |
+
"grad_norm": 0.26036244527725116,
|
| 591 |
+
"learning_rate": 3.805301908254455e-07,
|
| 592 |
+
"loss": 0.462,
|
| 593 |
+
"step": 195
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 1.56,
|
| 597 |
+
"eval_loss": 0.5414429903030396,
|
| 598 |
+
"eval_runtime": 1.8932,
|
| 599 |
+
"eval_samples_per_second": 10.564,
|
| 600 |
+
"eval_steps_per_second": 2.641,
|
| 601 |
+
"step": 195
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 1.6,
|
| 605 |
+
"grad_norm": 0.23115347129847905,
|
| 606 |
+
"learning_rate": 0.0,
|
| 607 |
+
"loss": 0.4665,
|
| 608 |
+
"step": 200
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 1.6,
|
| 612 |
+
"eval_loss": 0.5413893461227417,
|
| 613 |
+
"eval_runtime": 1.8908,
|
| 614 |
+
"eval_samples_per_second": 10.577,
|
| 615 |
+
"eval_steps_per_second": 2.644,
|
| 616 |
+
"step": 200
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 1.6,
|
| 620 |
+
"step": 200,
|
| 621 |
+
"total_flos": 11601719820288.0,
|
| 622 |
+
"train_loss": 0.5555729389190673,
|
| 623 |
+
"train_runtime": 622.2423,
|
| 624 |
+
"train_samples_per_second": 2.571,
|
| 625 |
+
"train_steps_per_second": 0.321
|
| 626 |
+
}
|
| 627 |
+
],
|
| 628 |
+
"logging_steps": 5,
|
| 629 |
+
"max_steps": 200,
|
| 630 |
+
"num_input_tokens_seen": 0,
|
| 631 |
+
"num_train_epochs": 2,
|
| 632 |
+
"save_steps": 1000,
|
| 633 |
+
"stateful_callbacks": {
|
| 634 |
+
"TrainerControl": {
|
| 635 |
+
"args": {
|
| 636 |
+
"should_epoch_stop": false,
|
| 637 |
+
"should_evaluate": false,
|
| 638 |
+
"should_log": false,
|
| 639 |
+
"should_save": true,
|
| 640 |
+
"should_training_stop": true
|
| 641 |
+
},
|
| 642 |
+
"attributes": {}
|
| 643 |
+
}
|
| 644 |
+
},
|
| 645 |
+
"total_flos": 11601719820288.0,
|
| 646 |
+
"train_batch_size": 4,
|
| 647 |
+
"trial_name": null,
|
| 648 |
+
"trial_params": null
|
| 649 |
+
}
|