Model save
Browse files- README.md +61 -0
- all_results.json +9 -0
- train_results.json +9 -0
- trainer_state.json +378 -0
README.md
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
license: mit
|
| 4 |
+
base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
|
| 5 |
+
tags:
|
| 6 |
+
- trl
|
| 7 |
+
- sft
|
| 8 |
+
- generated_from_trainer
|
| 9 |
+
model-index:
|
| 10 |
+
- name: models-ttt-bigestrun-021225-night-step2
|
| 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 |
+
# models-ttt-bigestrun-021225-night-step2
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [deepseek-ai/DeepSeek-R1-Distill-Qwen-32B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B) on an unknown dataset.
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 5e-05
|
| 39 |
+
- train_batch_size: 2
|
| 40 |
+
- eval_batch_size: 1
|
| 41 |
+
- seed: 42
|
| 42 |
+
- distributed_type: multi-GPU
|
| 43 |
+
- num_devices: 8
|
| 44 |
+
- total_train_batch_size: 16
|
| 45 |
+
- total_eval_batch_size: 8
|
| 46 |
+
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 47 |
+
- lr_scheduler_type: cosine
|
| 48 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 49 |
+
- num_epochs: 3
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
|
| 54 |
+
|
| 55 |
+
### Framework versions
|
| 56 |
+
|
| 57 |
+
- PEFT 0.13.2
|
| 58 |
+
- Transformers 4.47.0.dev0
|
| 59 |
+
- Pytorch 2.4.0+cu121
|
| 60 |
+
- Datasets 3.1.0
|
| 61 |
+
- Tokenizers 0.20.3
|
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 882865236606976.0,
|
| 4 |
+
"train_loss": 0.0980342753076305,
|
| 5 |
+
"train_runtime": 1550.4315,
|
| 6 |
+
"train_samples": 250,
|
| 7 |
+
"train_samples_per_second": 0.484,
|
| 8 |
+
"train_steps_per_second": 0.031
|
| 9 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 882865236606976.0,
|
| 4 |
+
"train_loss": 0.0980342753076305,
|
| 5 |
+
"train_runtime": 1550.4315,
|
| 6 |
+
"train_samples": 250,
|
| 7 |
+
"train_samples_per_second": 0.484,
|
| 8 |
+
"train_steps_per_second": 0.031
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,378 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 48,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0625,
|
| 13 |
+
"grad_norm": 0.04137394207755112,
|
| 14 |
+
"learning_rate": 1e-05,
|
| 15 |
+
"loss": 0.1671,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.125,
|
| 20 |
+
"grad_norm": 0.037803193435615265,
|
| 21 |
+
"learning_rate": 2e-05,
|
| 22 |
+
"loss": 0.167,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.1875,
|
| 27 |
+
"grad_norm": 0.04445740088277594,
|
| 28 |
+
"learning_rate": 3e-05,
|
| 29 |
+
"loss": 0.1607,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.25,
|
| 34 |
+
"grad_norm": 0.0380231527607073,
|
| 35 |
+
"learning_rate": 4e-05,
|
| 36 |
+
"loss": 0.1591,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.3125,
|
| 41 |
+
"grad_norm": 0.046362646963448,
|
| 42 |
+
"learning_rate": 5e-05,
|
| 43 |
+
"loss": 0.1597,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.375,
|
| 48 |
+
"grad_norm": 0.05235320825077946,
|
| 49 |
+
"learning_rate": 4.9933307091588796e-05,
|
| 50 |
+
"loss": 0.1616,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.4375,
|
| 55 |
+
"grad_norm": 0.05740591760676448,
|
| 56 |
+
"learning_rate": 4.973358420187776e-05,
|
| 57 |
+
"loss": 0.1459,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.5,
|
| 62 |
+
"grad_norm": 0.04283964782544257,
|
| 63 |
+
"learning_rate": 4.9401896938898185e-05,
|
| 64 |
+
"loss": 0.1332,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.5625,
|
| 69 |
+
"grad_norm": 0.036679242954440874,
|
| 70 |
+
"learning_rate": 4.894001499771015e-05,
|
| 71 |
+
"loss": 0.1293,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.625,
|
| 76 |
+
"grad_norm": 0.033723367633845105,
|
| 77 |
+
"learning_rate": 4.83504027183137e-05,
|
| 78 |
+
"loss": 0.1342,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.6875,
|
| 83 |
+
"grad_norm": 0.037227526954279944,
|
| 84 |
+
"learning_rate": 4.763620593732867e-05,
|
| 85 |
+
"loss": 0.128,
|
| 86 |
+
"step": 11
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.75,
|
| 90 |
+
"grad_norm": 0.044207038446114774,
|
| 91 |
+
"learning_rate": 4.6801235203595195e-05,
|
| 92 |
+
"loss": 0.1275,
|
| 93 |
+
"step": 12
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.8125,
|
| 97 |
+
"grad_norm": 0.04394682449442954,
|
| 98 |
+
"learning_rate": 4.584994544724695e-05,
|
| 99 |
+
"loss": 0.1142,
|
| 100 |
+
"step": 13
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.875,
|
| 104 |
+
"grad_norm": 0.03406265181060845,
|
| 105 |
+
"learning_rate": 4.478741221073136e-05,
|
| 106 |
+
"loss": 0.1161,
|
| 107 |
+
"step": 14
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.9375,
|
| 111 |
+
"grad_norm": 0.030054446617056498,
|
| 112 |
+
"learning_rate": 4.361930456859455e-05,
|
| 113 |
+
"loss": 0.1087,
|
| 114 |
+
"step": 15
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 1.0,
|
| 118 |
+
"grad_norm": 0.028409394434840918,
|
| 119 |
+
"learning_rate": 4.235185488051585e-05,
|
| 120 |
+
"loss": 0.1126,
|
| 121 |
+
"step": 16
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 1.0625,
|
| 125 |
+
"grad_norm": 0.023153227915814832,
|
| 126 |
+
"learning_rate": 4.099182553897229e-05,
|
| 127 |
+
"loss": 0.1054,
|
| 128 |
+
"step": 17
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.125,
|
| 132 |
+
"grad_norm": 0.021598055829915037,
|
| 133 |
+
"learning_rate": 3.954647288894883e-05,
|
| 134 |
+
"loss": 0.1007,
|
| 135 |
+
"step": 18
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 1.1875,
|
| 139 |
+
"grad_norm": 0.02123540151753295,
|
| 140 |
+
"learning_rate": 3.8023508512198256e-05,
|
| 141 |
+
"loss": 0.1001,
|
| 142 |
+
"step": 19
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 1.25,
|
| 146 |
+
"grad_norm": 0.02137306513970009,
|
| 147 |
+
"learning_rate": 3.6431058082615964e-05,
|
| 148 |
+
"loss": 0.0968,
|
| 149 |
+
"step": 20
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.3125,
|
| 153 |
+
"grad_norm": 0.02433397130782817,
|
| 154 |
+
"learning_rate": 3.47776180122539e-05,
|
| 155 |
+
"loss": 0.0983,
|
| 156 |
+
"step": 21
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 1.375,
|
| 160 |
+
"grad_norm": 0.021942525621062504,
|
| 161 |
+
"learning_rate": 3.307201011928616e-05,
|
| 162 |
+
"loss": 0.0935,
|
| 163 |
+
"step": 22
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 1.4375,
|
| 167 |
+
"grad_norm": 0.021261141593508576,
|
| 168 |
+
"learning_rate": 3.132333455979202e-05,
|
| 169 |
+
"loss": 0.0887,
|
| 170 |
+
"step": 23
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 1.5,
|
| 174 |
+
"grad_norm": 0.02142792591828939,
|
| 175 |
+
"learning_rate": 2.954092127448591e-05,
|
| 176 |
+
"loss": 0.0888,
|
| 177 |
+
"step": 24
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 1.5625,
|
| 181 |
+
"grad_norm": 0.020750630946201602,
|
| 182 |
+
"learning_rate": 2.7734280209446865e-05,
|
| 183 |
+
"loss": 0.0891,
|
| 184 |
+
"step": 25
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 1.625,
|
| 188 |
+
"grad_norm": 0.019872557078390127,
|
| 189 |
+
"learning_rate": 2.5913050576441477e-05,
|
| 190 |
+
"loss": 0.0872,
|
| 191 |
+
"step": 26
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 1.6875,
|
| 195 |
+
"grad_norm": 0.019131650653635524,
|
| 196 |
+
"learning_rate": 2.4086949423558526e-05,
|
| 197 |
+
"loss": 0.0835,
|
| 198 |
+
"step": 27
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 1.75,
|
| 202 |
+
"grad_norm": 0.019027351901529727,
|
| 203 |
+
"learning_rate": 2.2265719790553147e-05,
|
| 204 |
+
"loss": 0.0827,
|
| 205 |
+
"step": 28
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 1.8125,
|
| 209 |
+
"grad_norm": 0.019517019388363612,
|
| 210 |
+
"learning_rate": 2.0459078725514092e-05,
|
| 211 |
+
"loss": 0.0769,
|
| 212 |
+
"step": 29
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 1.875,
|
| 216 |
+
"grad_norm": 0.019073963774100196,
|
| 217 |
+
"learning_rate": 1.867666544020798e-05,
|
| 218 |
+
"loss": 0.0768,
|
| 219 |
+
"step": 30
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 1.9375,
|
| 223 |
+
"grad_norm": 0.020535779704439937,
|
| 224 |
+
"learning_rate": 1.692798988071385e-05,
|
| 225 |
+
"loss": 0.0703,
|
| 226 |
+
"step": 31
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 2.0,
|
| 230 |
+
"grad_norm": 0.01735083491599702,
|
| 231 |
+
"learning_rate": 1.5222381987746104e-05,
|
| 232 |
+
"loss": 0.0721,
|
| 233 |
+
"step": 32
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 2.0625,
|
| 237 |
+
"grad_norm": 0.016996572618955864,
|
| 238 |
+
"learning_rate": 1.3568941917384036e-05,
|
| 239 |
+
"loss": 0.0729,
|
| 240 |
+
"step": 33
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 2.125,
|
| 244 |
+
"grad_norm": 0.016947999154191592,
|
| 245 |
+
"learning_rate": 1.1976491487801748e-05,
|
| 246 |
+
"loss": 0.0683,
|
| 247 |
+
"step": 34
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 2.1875,
|
| 251 |
+
"grad_norm": 0.01759855889883996,
|
| 252 |
+
"learning_rate": 1.0453527111051184e-05,
|
| 253 |
+
"loss": 0.0682,
|
| 254 |
+
"step": 35
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 2.25,
|
| 258 |
+
"grad_norm": 0.016563435997106427,
|
| 259 |
+
"learning_rate": 9.008174461027724e-06,
|
| 260 |
+
"loss": 0.0701,
|
| 261 |
+
"step": 36
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 2.3125,
|
| 265 |
+
"grad_norm": 0.0154902825546126,
|
| 266 |
+
"learning_rate": 7.648145119484152e-06,
|
| 267 |
+
"loss": 0.0673,
|
| 268 |
+
"step": 37
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 2.375,
|
| 272 |
+
"grad_norm": 0.01691672911978778,
|
| 273 |
+
"learning_rate": 6.380695431405453e-06,
|
| 274 |
+
"loss": 0.0694,
|
| 275 |
+
"step": 38
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 2.4375,
|
| 279 |
+
"grad_norm": 0.01530029785885113,
|
| 280 |
+
"learning_rate": 5.2125877892686496e-06,
|
| 281 |
+
"loss": 0.0681,
|
| 282 |
+
"step": 39
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 2.5,
|
| 286 |
+
"grad_norm": 0.017885100797614902,
|
| 287 |
+
"learning_rate": 4.150054552753055e-06,
|
| 288 |
+
"loss": 0.0627,
|
| 289 |
+
"step": 40
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 2.5625,
|
| 293 |
+
"grad_norm": 0.016638045960609936,
|
| 294 |
+
"learning_rate": 3.198764796404807e-06,
|
| 295 |
+
"loss": 0.0669,
|
| 296 |
+
"step": 41
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 2.625,
|
| 300 |
+
"grad_norm": 0.016208072151038286,
|
| 301 |
+
"learning_rate": 2.3637940626713346e-06,
|
| 302 |
+
"loss": 0.0678,
|
| 303 |
+
"step": 42
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 2.6875,
|
| 307 |
+
"grad_norm": 0.016401199651084344,
|
| 308 |
+
"learning_rate": 1.649597281686302e-06,
|
| 309 |
+
"loss": 0.0649,
|
| 310 |
+
"step": 43
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 2.75,
|
| 314 |
+
"grad_norm": 0.01598951472231698,
|
| 315 |
+
"learning_rate": 1.0599850022898539e-06,
|
| 316 |
+
"loss": 0.0674,
|
| 317 |
+
"step": 44
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 2.8125,
|
| 321 |
+
"grad_norm": 0.015277414785260311,
|
| 322 |
+
"learning_rate": 5.981030611018234e-07,
|
| 323 |
+
"loss": 0.0634,
|
| 324 |
+
"step": 45
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 2.875,
|
| 328 |
+
"grad_norm": 0.01537912920538106,
|
| 329 |
+
"learning_rate": 2.664157981222437e-07,
|
| 330 |
+
"loss": 0.0637,
|
| 331 |
+
"step": 46
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 2.9375,
|
| 335 |
+
"grad_norm": 0.015282877713047758,
|
| 336 |
+
"learning_rate": 6.66929084112089e-08,
|
| 337 |
+
"loss": 0.0667,
|
| 338 |
+
"step": 47
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 3.0,
|
| 342 |
+
"grad_norm": 0.01629157768683682,
|
| 343 |
+
"learning_rate": 0.0,
|
| 344 |
+
"loss": 0.0622,
|
| 345 |
+
"step": 48
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 3.0,
|
| 349 |
+
"step": 48,
|
| 350 |
+
"total_flos": 882865236606976.0,
|
| 351 |
+
"train_loss": 0.0980342753076305,
|
| 352 |
+
"train_runtime": 1550.4315,
|
| 353 |
+
"train_samples_per_second": 0.484,
|
| 354 |
+
"train_steps_per_second": 0.031
|
| 355 |
+
}
|
| 356 |
+
],
|
| 357 |
+
"logging_steps": 1,
|
| 358 |
+
"max_steps": 48,
|
| 359 |
+
"num_input_tokens_seen": 0,
|
| 360 |
+
"num_train_epochs": 3,
|
| 361 |
+
"save_steps": 500,
|
| 362 |
+
"stateful_callbacks": {
|
| 363 |
+
"TrainerControl": {
|
| 364 |
+
"args": {
|
| 365 |
+
"should_epoch_stop": false,
|
| 366 |
+
"should_evaluate": false,
|
| 367 |
+
"should_log": false,
|
| 368 |
+
"should_save": true,
|
| 369 |
+
"should_training_stop": true
|
| 370 |
+
},
|
| 371 |
+
"attributes": {}
|
| 372 |
+
}
|
| 373 |
+
},
|
| 374 |
+
"total_flos": 882865236606976.0,
|
| 375 |
+
"train_batch_size": 2,
|
| 376 |
+
"trial_name": null,
|
| 377 |
+
"trial_params": null
|
| 378 |
+
}
|