Model save
Browse files- README.md +61 -0
- all_results.json +9 -0
- train_results.json +9 -0
- trainer_state.json +280 -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-p10-ttt-021125-overnight-final-run-continue2-step1
|
| 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-p10-ttt-021125-overnight-final-run-continue2-step1
|
| 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: 1
|
| 40 |
+
- eval_batch_size: 1
|
| 41 |
+
- seed: 42
|
| 42 |
+
- distributed_type: multi-GPU
|
| 43 |
+
- num_devices: 8
|
| 44 |
+
- total_train_batch_size: 8
|
| 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: 2
|
| 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": 2.0,
|
| 3 |
+
"total_flos": 312828398403584.0,
|
| 4 |
+
"train_loss": 0.11463655378012096,
|
| 5 |
+
"train_runtime": 638.7139,
|
| 6 |
+
"train_samples": 134,
|
| 7 |
+
"train_samples_per_second": 0.42,
|
| 8 |
+
"train_steps_per_second": 0.053
|
| 9 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"total_flos": 312828398403584.0,
|
| 4 |
+
"train_loss": 0.11463655378012096,
|
| 5 |
+
"train_runtime": 638.7139,
|
| 6 |
+
"train_samples": 134,
|
| 7 |
+
"train_samples_per_second": 0.42,
|
| 8 |
+
"train_steps_per_second": 0.053
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,280 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 34,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.058823529411764705,
|
| 13 |
+
"grad_norm": 0.04119938833817372,
|
| 14 |
+
"learning_rate": 1.25e-05,
|
| 15 |
+
"loss": 0.1617,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.11764705882352941,
|
| 20 |
+
"grad_norm": 0.044580310359720134,
|
| 21 |
+
"learning_rate": 2.5e-05,
|
| 22 |
+
"loss": 0.1637,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.17647058823529413,
|
| 27 |
+
"grad_norm": 0.05957459125343682,
|
| 28 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 29 |
+
"loss": 0.1604,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.23529411764705882,
|
| 34 |
+
"grad_norm": 0.03781667288617757,
|
| 35 |
+
"learning_rate": 5e-05,
|
| 36 |
+
"loss": 0.1512,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.29411764705882354,
|
| 41 |
+
"grad_norm": 0.040636654808393624,
|
| 42 |
+
"learning_rate": 4.9863047384206835e-05,
|
| 43 |
+
"loss": 0.1577,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.35294117647058826,
|
| 48 |
+
"grad_norm": 0.049110285117873326,
|
| 49 |
+
"learning_rate": 4.9453690018345144e-05,
|
| 50 |
+
"loss": 0.1512,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.4117647058823529,
|
| 55 |
+
"grad_norm": 0.0465639998513701,
|
| 56 |
+
"learning_rate": 4.877641290737884e-05,
|
| 57 |
+
"loss": 0.1426,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.47058823529411764,
|
| 62 |
+
"grad_norm": 0.036435873417021904,
|
| 63 |
+
"learning_rate": 4.783863644106502e-05,
|
| 64 |
+
"loss": 0.1399,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.5294117647058824,
|
| 69 |
+
"grad_norm": 0.033480220647433744,
|
| 70 |
+
"learning_rate": 4.665063509461097e-05,
|
| 71 |
+
"loss": 0.1294,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.5882352941176471,
|
| 76 |
+
"grad_norm": 0.03192171934202962,
|
| 77 |
+
"learning_rate": 4.522542485937369e-05,
|
| 78 |
+
"loss": 0.1253,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.6470588235294118,
|
| 83 |
+
"grad_norm": 0.04530177214353218,
|
| 84 |
+
"learning_rate": 4.357862063693486e-05,
|
| 85 |
+
"loss": 0.1255,
|
| 86 |
+
"step": 11
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.7058823529411765,
|
| 90 |
+
"grad_norm": 0.04880550652685742,
|
| 91 |
+
"learning_rate": 4.172826515897146e-05,
|
| 92 |
+
"loss": 0.1198,
|
| 93 |
+
"step": 12
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.7647058823529411,
|
| 97 |
+
"grad_norm": 0.041511768419926834,
|
| 98 |
+
"learning_rate": 3.969463130731183e-05,
|
| 99 |
+
"loss": 0.1175,
|
| 100 |
+
"step": 13
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.8235294117647058,
|
| 104 |
+
"grad_norm": 0.0344970307653626,
|
| 105 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 106 |
+
"loss": 0.1122,
|
| 107 |
+
"step": 14
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.8823529411764706,
|
| 111 |
+
"grad_norm": 0.028123434019151898,
|
| 112 |
+
"learning_rate": 3.516841607689501e-05,
|
| 113 |
+
"loss": 0.1128,
|
| 114 |
+
"step": 15
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.9411764705882353,
|
| 118 |
+
"grad_norm": 0.023212294451095815,
|
| 119 |
+
"learning_rate": 3.272542485937369e-05,
|
| 120 |
+
"loss": 0.1025,
|
| 121 |
+
"step": 16
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 1.0,
|
| 125 |
+
"grad_norm": 0.026329550320854524,
|
| 126 |
+
"learning_rate": 3.0197792270443982e-05,
|
| 127 |
+
"loss": 0.1058,
|
| 128 |
+
"step": 17
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.0588235294117647,
|
| 132 |
+
"grad_norm": 0.025282592866642674,
|
| 133 |
+
"learning_rate": 2.761321158169134e-05,
|
| 134 |
+
"loss": 0.1026,
|
| 135 |
+
"step": 18
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 1.1176470588235294,
|
| 139 |
+
"grad_norm": 0.025085561182073654,
|
| 140 |
+
"learning_rate": 2.5e-05,
|
| 141 |
+
"loss": 0.0999,
|
| 142 |
+
"step": 19
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 1.1764705882352942,
|
| 146 |
+
"grad_norm": 0.02563743310804527,
|
| 147 |
+
"learning_rate": 2.238678841830867e-05,
|
| 148 |
+
"loss": 0.1013,
|
| 149 |
+
"step": 20
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.2352941176470589,
|
| 153 |
+
"grad_norm": 0.0257129345184491,
|
| 154 |
+
"learning_rate": 1.980220772955602e-05,
|
| 155 |
+
"loss": 0.1021,
|
| 156 |
+
"step": 21
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 1.2941176470588236,
|
| 160 |
+
"grad_norm": 0.024271582072269274,
|
| 161 |
+
"learning_rate": 1.7274575140626318e-05,
|
| 162 |
+
"loss": 0.1008,
|
| 163 |
+
"step": 22
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 1.3529411764705883,
|
| 167 |
+
"grad_norm": 0.02245818881353105,
|
| 168 |
+
"learning_rate": 1.4831583923104999e-05,
|
| 169 |
+
"loss": 0.0965,
|
| 170 |
+
"step": 23
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 1.4117647058823528,
|
| 174 |
+
"grad_norm": 0.021498728186081145,
|
| 175 |
+
"learning_rate": 1.2500000000000006e-05,
|
| 176 |
+
"loss": 0.0938,
|
| 177 |
+
"step": 24
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 1.4705882352941178,
|
| 181 |
+
"grad_norm": 0.02071609955140359,
|
| 182 |
+
"learning_rate": 1.0305368692688174e-05,
|
| 183 |
+
"loss": 0.0942,
|
| 184 |
+
"step": 25
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 1.5294117647058822,
|
| 188 |
+
"grad_norm": 0.021433099988627618,
|
| 189 |
+
"learning_rate": 8.271734841028553e-06,
|
| 190 |
+
"loss": 0.0939,
|
| 191 |
+
"step": 26
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 1.5882352941176472,
|
| 195 |
+
"grad_norm": 0.021715599852153235,
|
| 196 |
+
"learning_rate": 6.421379363065142e-06,
|
| 197 |
+
"loss": 0.0906,
|
| 198 |
+
"step": 27
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 1.6470588235294117,
|
| 202 |
+
"grad_norm": 0.020442202294777053,
|
| 203 |
+
"learning_rate": 4.7745751406263165e-06,
|
| 204 |
+
"loss": 0.0913,
|
| 205 |
+
"step": 28
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 1.7058823529411766,
|
| 209 |
+
"grad_norm": 0.0218394701395644,
|
| 210 |
+
"learning_rate": 3.3493649053890326e-06,
|
| 211 |
+
"loss": 0.0974,
|
| 212 |
+
"step": 29
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 1.7647058823529411,
|
| 216 |
+
"grad_norm": 0.021109969162255385,
|
| 217 |
+
"learning_rate": 2.1613635589349756e-06,
|
| 218 |
+
"loss": 0.0888,
|
| 219 |
+
"step": 30
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 1.8235294117647058,
|
| 223 |
+
"grad_norm": 0.022207989013227878,
|
| 224 |
+
"learning_rate": 1.2235870926211619e-06,
|
| 225 |
+
"loss": 0.0905,
|
| 226 |
+
"step": 31
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 1.8823529411764706,
|
| 230 |
+
"grad_norm": 0.020468136183607134,
|
| 231 |
+
"learning_rate": 5.463099816548579e-07,
|
| 232 |
+
"loss": 0.0937,
|
| 233 |
+
"step": 32
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 1.9411764705882353,
|
| 237 |
+
"grad_norm": 0.02094523492541685,
|
| 238 |
+
"learning_rate": 1.3695261579316777e-07,
|
| 239 |
+
"loss": 0.088,
|
| 240 |
+
"step": 33
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 2.0,
|
| 244 |
+
"grad_norm": 0.021052288179908476,
|
| 245 |
+
"learning_rate": 0.0,
|
| 246 |
+
"loss": 0.0929,
|
| 247 |
+
"step": 34
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 2.0,
|
| 251 |
+
"step": 34,
|
| 252 |
+
"total_flos": 312828398403584.0,
|
| 253 |
+
"train_loss": 0.11463655378012096,
|
| 254 |
+
"train_runtime": 638.7139,
|
| 255 |
+
"train_samples_per_second": 0.42,
|
| 256 |
+
"train_steps_per_second": 0.053
|
| 257 |
+
}
|
| 258 |
+
],
|
| 259 |
+
"logging_steps": 1,
|
| 260 |
+
"max_steps": 34,
|
| 261 |
+
"num_input_tokens_seen": 0,
|
| 262 |
+
"num_train_epochs": 2,
|
| 263 |
+
"save_steps": 500,
|
| 264 |
+
"stateful_callbacks": {
|
| 265 |
+
"TrainerControl": {
|
| 266 |
+
"args": {
|
| 267 |
+
"should_epoch_stop": false,
|
| 268 |
+
"should_evaluate": false,
|
| 269 |
+
"should_log": false,
|
| 270 |
+
"should_save": true,
|
| 271 |
+
"should_training_stop": true
|
| 272 |
+
},
|
| 273 |
+
"attributes": {}
|
| 274 |
+
}
|
| 275 |
+
},
|
| 276 |
+
"total_flos": 312828398403584.0,
|
| 277 |
+
"train_batch_size": 1,
|
| 278 |
+
"trial_name": null,
|
| 279 |
+
"trial_params": null
|
| 280 |
+
}
|