Model save
Browse files- README.md +66 -0
- all_results.json +9 -0
- train_results.json +9 -0
- trainer_state.json +408 -0
README.md
ADDED
|
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: barc0/Llama-3.1-ARC-Potpourri-Transduction-8B
|
| 3 |
+
library_name: peft
|
| 4 |
+
license: llama3.1
|
| 5 |
+
tags:
|
| 6 |
+
- trl
|
| 7 |
+
- sft
|
| 8 |
+
- generated_from_trainer
|
| 9 |
+
model-index:
|
| 10 |
+
- name: problem0_model_aug_10
|
| 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 |
+
# problem0_model_aug_10
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [barc0/Llama-3.1-ARC-Potpourri-Transduction-8B](https://huggingface.co/barc0/Llama-3.1-ARC-Potpourri-Transduction-8B) on an unknown dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.1473
|
| 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: 2
|
| 46 |
+
- total_train_batch_size: 2
|
| 47 |
+
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 48 |
+
- lr_scheduler_type: cosine
|
| 49 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 50 |
+
- num_epochs: 2
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 55 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 56 |
+
| 0.2436 | 1.0 | 25 | 0.1446 |
|
| 57 |
+
| 0.12 | 2.0 | 50 | 0.1473 |
|
| 58 |
+
|
| 59 |
+
|
| 60 |
+
### Framework versions
|
| 61 |
+
|
| 62 |
+
- PEFT 0.13.2
|
| 63 |
+
- Transformers 4.47.0.dev0
|
| 64 |
+
- Pytorch 2.4.0+cu121
|
| 65 |
+
- Datasets 3.1.0
|
| 66 |
+
- Tokenizers 0.20.3
|
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"total_flos": 643887562752.0,
|
| 4 |
+
"train_loss": 0.10991490356624127,
|
| 5 |
+
"train_runtime": 185.8623,
|
| 6 |
+
"train_samples": 50,
|
| 7 |
+
"train_samples_per_second": 0.538,
|
| 8 |
+
"train_steps_per_second": 0.269
|
| 9 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"total_flos": 643887562752.0,
|
| 4 |
+
"train_loss": 0.10991490356624127,
|
| 5 |
+
"train_runtime": 185.8623,
|
| 6 |
+
"train_samples": 50,
|
| 7 |
+
"train_samples_per_second": 0.538,
|
| 8 |
+
"train_steps_per_second": 0.269
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,408 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 50,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.04,
|
| 13 |
+
"grad_norm": 0.1475104469860361,
|
| 14 |
+
"learning_rate": 2e-05,
|
| 15 |
+
"loss": 0.0999,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.08,
|
| 20 |
+
"grad_norm": 0.17336762271557374,
|
| 21 |
+
"learning_rate": 4e-05,
|
| 22 |
+
"loss": 0.1105,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.12,
|
| 27 |
+
"grad_norm": 0.1625647711677745,
|
| 28 |
+
"learning_rate": 6e-05,
|
| 29 |
+
"loss": 0.1518,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.16,
|
| 34 |
+
"grad_norm": 0.2835973362154201,
|
| 35 |
+
"learning_rate": 8e-05,
|
| 36 |
+
"loss": 0.412,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.2,
|
| 41 |
+
"grad_norm": 0.102899700816259,
|
| 42 |
+
"learning_rate": 0.0001,
|
| 43 |
+
"loss": 0.1253,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.24,
|
| 48 |
+
"grad_norm": 0.10525052737112932,
|
| 49 |
+
"learning_rate": 9.987820251299122e-05,
|
| 50 |
+
"loss": 0.1777,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.28,
|
| 55 |
+
"grad_norm": 0.0841421968850327,
|
| 56 |
+
"learning_rate": 9.951340343707852e-05,
|
| 57 |
+
"loss": 0.1138,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.32,
|
| 62 |
+
"grad_norm": 0.21097849799520993,
|
| 63 |
+
"learning_rate": 9.890738003669029e-05,
|
| 64 |
+
"loss": 0.3093,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.36,
|
| 69 |
+
"grad_norm": 0.13129190430279525,
|
| 70 |
+
"learning_rate": 9.806308479691595e-05,
|
| 71 |
+
"loss": 0.1067,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.4,
|
| 76 |
+
"grad_norm": 0.22029292639589196,
|
| 77 |
+
"learning_rate": 9.698463103929542e-05,
|
| 78 |
+
"loss": 0.2229,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.44,
|
| 83 |
+
"grad_norm": 0.2605739248411656,
|
| 84 |
+
"learning_rate": 9.567727288213005e-05,
|
| 85 |
+
"loss": 0.3048,
|
| 86 |
+
"step": 11
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.48,
|
| 90 |
+
"grad_norm": 0.09516786744052268,
|
| 91 |
+
"learning_rate": 9.414737964294636e-05,
|
| 92 |
+
"loss": 0.0444,
|
| 93 |
+
"step": 12
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.52,
|
| 97 |
+
"grad_norm": 0.11035350979508174,
|
| 98 |
+
"learning_rate": 9.24024048078213e-05,
|
| 99 |
+
"loss": 0.0919,
|
| 100 |
+
"step": 13
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.56,
|
| 104 |
+
"grad_norm": 0.1860366786152161,
|
| 105 |
+
"learning_rate": 9.045084971874738e-05,
|
| 106 |
+
"loss": 0.1798,
|
| 107 |
+
"step": 14
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.6,
|
| 111 |
+
"grad_norm": 0.2051102247541834,
|
| 112 |
+
"learning_rate": 8.83022221559489e-05,
|
| 113 |
+
"loss": 0.1682,
|
| 114 |
+
"step": 15
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.64,
|
| 118 |
+
"grad_norm": 0.2120620056755024,
|
| 119 |
+
"learning_rate": 8.596699001693255e-05,
|
| 120 |
+
"loss": 0.2017,
|
| 121 |
+
"step": 16
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.68,
|
| 125 |
+
"grad_norm": 0.12492795843072409,
|
| 126 |
+
"learning_rate": 8.345653031794292e-05,
|
| 127 |
+
"loss": 0.0715,
|
| 128 |
+
"step": 17
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.72,
|
| 132 |
+
"grad_norm": 0.09372961310287645,
|
| 133 |
+
"learning_rate": 8.07830737662829e-05,
|
| 134 |
+
"loss": 0.063,
|
| 135 |
+
"step": 18
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.76,
|
| 139 |
+
"grad_norm": 0.09404028728202063,
|
| 140 |
+
"learning_rate": 7.795964517353735e-05,
|
| 141 |
+
"loss": 0.1209,
|
| 142 |
+
"step": 19
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.8,
|
| 146 |
+
"grad_norm": 0.11155850164626473,
|
| 147 |
+
"learning_rate": 7.500000000000001e-05,
|
| 148 |
+
"loss": 0.048,
|
| 149 |
+
"step": 20
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.84,
|
| 153 |
+
"grad_norm": 0.14193160043170325,
|
| 154 |
+
"learning_rate": 7.191855733945387e-05,
|
| 155 |
+
"loss": 0.1016,
|
| 156 |
+
"step": 21
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.88,
|
| 160 |
+
"grad_norm": 0.12622860771717062,
|
| 161 |
+
"learning_rate": 6.873032967079561e-05,
|
| 162 |
+
"loss": 0.0836,
|
| 163 |
+
"step": 22
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.92,
|
| 167 |
+
"grad_norm": 0.19822006343379234,
|
| 168 |
+
"learning_rate": 6.545084971874738e-05,
|
| 169 |
+
"loss": 0.1943,
|
| 170 |
+
"step": 23
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.96,
|
| 174 |
+
"grad_norm": 0.17907254526794228,
|
| 175 |
+
"learning_rate": 6.209609477998338e-05,
|
| 176 |
+
"loss": 0.1258,
|
| 177 |
+
"step": 24
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 1.0,
|
| 181 |
+
"grad_norm": 0.35070363993403475,
|
| 182 |
+
"learning_rate": 5.868240888334653e-05,
|
| 183 |
+
"loss": 0.2436,
|
| 184 |
+
"step": 25
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 1.0,
|
| 188 |
+
"eval_loss": 0.1445501148700714,
|
| 189 |
+
"eval_runtime": 0.4011,
|
| 190 |
+
"eval_samples_per_second": 2.493,
|
| 191 |
+
"eval_steps_per_second": 2.493,
|
| 192 |
+
"step": 25
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 1.04,
|
| 196 |
+
"grad_norm": 0.331374058760647,
|
| 197 |
+
"learning_rate": 5.522642316338268e-05,
|
| 198 |
+
"loss": 0.1818,
|
| 199 |
+
"step": 26
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 1.08,
|
| 203 |
+
"grad_norm": 0.10212151784996519,
|
| 204 |
+
"learning_rate": 5.174497483512506e-05,
|
| 205 |
+
"loss": 0.0545,
|
| 206 |
+
"step": 27
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 1.12,
|
| 210 |
+
"grad_norm": 0.12127508733134722,
|
| 211 |
+
"learning_rate": 4.825502516487497e-05,
|
| 212 |
+
"loss": 0.0662,
|
| 213 |
+
"step": 28
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 1.16,
|
| 217 |
+
"grad_norm": 0.10472782126959304,
|
| 218 |
+
"learning_rate": 4.477357683661734e-05,
|
| 219 |
+
"loss": 0.0712,
|
| 220 |
+
"step": 29
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 1.2,
|
| 224 |
+
"grad_norm": 0.09739912535877197,
|
| 225 |
+
"learning_rate": 4.131759111665349e-05,
|
| 226 |
+
"loss": 0.0716,
|
| 227 |
+
"step": 30
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 1.24,
|
| 231 |
+
"grad_norm": 0.07818016052332849,
|
| 232 |
+
"learning_rate": 3.790390522001662e-05,
|
| 233 |
+
"loss": 0.0428,
|
| 234 |
+
"step": 31
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 1.28,
|
| 238 |
+
"grad_norm": 0.1309525888712825,
|
| 239 |
+
"learning_rate": 3.4549150281252636e-05,
|
| 240 |
+
"loss": 0.0632,
|
| 241 |
+
"step": 32
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 1.32,
|
| 245 |
+
"grad_norm": 0.05268163632164765,
|
| 246 |
+
"learning_rate": 3.12696703292044e-05,
|
| 247 |
+
"loss": 0.0308,
|
| 248 |
+
"step": 33
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 1.3599999999999999,
|
| 252 |
+
"grad_norm": 0.07825640200592207,
|
| 253 |
+
"learning_rate": 2.8081442660546125e-05,
|
| 254 |
+
"loss": 0.0439,
|
| 255 |
+
"step": 34
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 1.4,
|
| 259 |
+
"grad_norm": 0.0654461820686998,
|
| 260 |
+
"learning_rate": 2.500000000000001e-05,
|
| 261 |
+
"loss": 0.0337,
|
| 262 |
+
"step": 35
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 1.44,
|
| 266 |
+
"grad_norm": 0.11019625858497928,
|
| 267 |
+
"learning_rate": 2.2040354826462668e-05,
|
| 268 |
+
"loss": 0.0732,
|
| 269 |
+
"step": 36
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 1.48,
|
| 273 |
+
"grad_norm": 0.0589572493253463,
|
| 274 |
+
"learning_rate": 1.9216926233717085e-05,
|
| 275 |
+
"loss": 0.0342,
|
| 276 |
+
"step": 37
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 1.52,
|
| 280 |
+
"grad_norm": 0.06589353609148312,
|
| 281 |
+
"learning_rate": 1.6543469682057106e-05,
|
| 282 |
+
"loss": 0.0325,
|
| 283 |
+
"step": 38
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 1.56,
|
| 287 |
+
"grad_norm": 0.14358958467272426,
|
| 288 |
+
"learning_rate": 1.4033009983067452e-05,
|
| 289 |
+
"loss": 0.0941,
|
| 290 |
+
"step": 39
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 1.6,
|
| 294 |
+
"grad_norm": 0.10816135111790075,
|
| 295 |
+
"learning_rate": 1.1697777844051105e-05,
|
| 296 |
+
"loss": 0.0577,
|
| 297 |
+
"step": 40
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 1.6400000000000001,
|
| 301 |
+
"grad_norm": 0.06366691648082863,
|
| 302 |
+
"learning_rate": 9.549150281252633e-06,
|
| 303 |
+
"loss": 0.0333,
|
| 304 |
+
"step": 41
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 1.6800000000000002,
|
| 308 |
+
"grad_norm": 0.15879304612419673,
|
| 309 |
+
"learning_rate": 7.597595192178702e-06,
|
| 310 |
+
"loss": 0.0666,
|
| 311 |
+
"step": 42
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 1.72,
|
| 315 |
+
"grad_norm": 0.0765495019619371,
|
| 316 |
+
"learning_rate": 5.852620357053651e-06,
|
| 317 |
+
"loss": 0.029,
|
| 318 |
+
"step": 43
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 1.76,
|
| 322 |
+
"grad_norm": 0.1515518653937463,
|
| 323 |
+
"learning_rate": 4.322727117869951e-06,
|
| 324 |
+
"loss": 0.1331,
|
| 325 |
+
"step": 44
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 1.8,
|
| 329 |
+
"grad_norm": 0.08525038364295008,
|
| 330 |
+
"learning_rate": 3.0153689607045845e-06,
|
| 331 |
+
"loss": 0.0489,
|
| 332 |
+
"step": 45
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.8399999999999999,
|
| 336 |
+
"grad_norm": 0.09069389566818667,
|
| 337 |
+
"learning_rate": 1.9369152030840556e-06,
|
| 338 |
+
"loss": 0.0417,
|
| 339 |
+
"step": 46
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.88,
|
| 343 |
+
"grad_norm": 0.15581325970621174,
|
| 344 |
+
"learning_rate": 1.0926199633097157e-06,
|
| 345 |
+
"loss": 0.1167,
|
| 346 |
+
"step": 47
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 1.92,
|
| 350 |
+
"grad_norm": 0.07551809989198507,
|
| 351 |
+
"learning_rate": 4.865965629214819e-07,
|
| 352 |
+
"loss": 0.0324,
|
| 353 |
+
"step": 48
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.96,
|
| 357 |
+
"grad_norm": 0.06320999636101195,
|
| 358 |
+
"learning_rate": 1.2179748700879012e-07,
|
| 359 |
+
"loss": 0.0494,
|
| 360 |
+
"step": 49
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 2.0,
|
| 364 |
+
"grad_norm": 0.13783812798955924,
|
| 365 |
+
"learning_rate": 0.0,
|
| 366 |
+
"loss": 0.12,
|
| 367 |
+
"step": 50
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 2.0,
|
| 371 |
+
"eval_loss": 0.14731274545192719,
|
| 372 |
+
"eval_runtime": 1.4061,
|
| 373 |
+
"eval_samples_per_second": 0.711,
|
| 374 |
+
"eval_steps_per_second": 0.711,
|
| 375 |
+
"step": 50
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 2.0,
|
| 379 |
+
"step": 50,
|
| 380 |
+
"total_flos": 643887562752.0,
|
| 381 |
+
"train_loss": 0.10991490356624127,
|
| 382 |
+
"train_runtime": 185.8623,
|
| 383 |
+
"train_samples_per_second": 0.538,
|
| 384 |
+
"train_steps_per_second": 0.269
|
| 385 |
+
}
|
| 386 |
+
],
|
| 387 |
+
"logging_steps": 1,
|
| 388 |
+
"max_steps": 50,
|
| 389 |
+
"num_input_tokens_seen": 0,
|
| 390 |
+
"num_train_epochs": 2,
|
| 391 |
+
"save_steps": 500,
|
| 392 |
+
"stateful_callbacks": {
|
| 393 |
+
"TrainerControl": {
|
| 394 |
+
"args": {
|
| 395 |
+
"should_epoch_stop": false,
|
| 396 |
+
"should_evaluate": false,
|
| 397 |
+
"should_log": false,
|
| 398 |
+
"should_save": true,
|
| 399 |
+
"should_training_stop": true
|
| 400 |
+
},
|
| 401 |
+
"attributes": {}
|
| 402 |
+
}
|
| 403 |
+
},
|
| 404 |
+
"total_flos": 643887562752.0,
|
| 405 |
+
"train_batch_size": 1,
|
| 406 |
+
"trial_name": null,
|
| 407 |
+
"trial_params": null
|
| 408 |
+
}
|