End of training
Browse files- README.md +2 -1
- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +462 -0
- training_loss.png +0 -0
README.md
CHANGED
|
@@ -4,6 +4,7 @@ license: apache-2.0
|
|
| 4 |
base_model: Qwen/Qwen2.5-7B-Instruct
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
|
|
|
| 7 |
- generated_from_trainer
|
| 8 |
model-index:
|
| 9 |
- name: seed_math_multiple_samples_scale_up_scaredy_cat_baseline
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# seed_math_multiple_samples_scale_up_scaredy_cat_baseline
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
|
|
| 4 |
base_model: Qwen/Qwen2.5-7B-Instruct
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
| 7 |
+
- full
|
| 8 |
- generated_from_trainer
|
| 9 |
model-index:
|
| 10 |
- name: seed_math_multiple_samples_scale_up_scaredy_cat_baseline
|
|
|
|
| 16 |
|
| 17 |
# seed_math_multiple_samples_scale_up_scaredy_cat_baseline
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the mlfoundations-dev/seed_math_multiple_samples_scale_up_scaredy_cat_baseline dataset.
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.926829268292683,
|
| 3 |
+
"total_flos": 56084346568704.0,
|
| 4 |
+
"train_loss": 0.8459723273913066,
|
| 5 |
+
"train_runtime": 3353.8656,
|
| 6 |
+
"train_samples_per_second": 1.756,
|
| 7 |
+
"train_steps_per_second": 0.018
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.926829268292683,
|
| 3 |
+
"total_flos": 56084346568704.0,
|
| 4 |
+
"train_loss": 0.8459723273913066,
|
| 5 |
+
"train_runtime": 3353.8656,
|
| 6 |
+
"train_samples_per_second": 1.756,
|
| 7 |
+
"train_steps_per_second": 0.018
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,462 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.926829268292683,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 60,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.04878048780487805,
|
| 13 |
+
"grad_norm": 6.836372375488281,
|
| 14 |
+
"learning_rate": 1.6666666666666667e-06,
|
| 15 |
+
"loss": 1.1182,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.0975609756097561,
|
| 20 |
+
"grad_norm": 6.894412517547607,
|
| 21 |
+
"learning_rate": 3.3333333333333333e-06,
|
| 22 |
+
"loss": 1.1051,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.14634146341463414,
|
| 27 |
+
"grad_norm": 6.724112033843994,
|
| 28 |
+
"learning_rate": 5e-06,
|
| 29 |
+
"loss": 1.1203,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.1951219512195122,
|
| 34 |
+
"grad_norm": 5.394062042236328,
|
| 35 |
+
"learning_rate": 6.666666666666667e-06,
|
| 36 |
+
"loss": 1.0799,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.24390243902439024,
|
| 41 |
+
"grad_norm": 2.9904468059539795,
|
| 42 |
+
"learning_rate": 8.333333333333334e-06,
|
| 43 |
+
"loss": 0.9942,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.2926829268292683,
|
| 48 |
+
"grad_norm": 4.739986896514893,
|
| 49 |
+
"learning_rate": 1e-05,
|
| 50 |
+
"loss": 0.9869,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.34146341463414637,
|
| 55 |
+
"grad_norm": 4.689507961273193,
|
| 56 |
+
"learning_rate": 9.991540791356342e-06,
|
| 57 |
+
"loss": 0.9747,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.3902439024390244,
|
| 62 |
+
"grad_norm": 4.10852575302124,
|
| 63 |
+
"learning_rate": 9.966191788709716e-06,
|
| 64 |
+
"loss": 1.0225,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.43902439024390244,
|
| 69 |
+
"grad_norm": 3.6707763671875,
|
| 70 |
+
"learning_rate": 9.924038765061042e-06,
|
| 71 |
+
"loss": 0.9272,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.4878048780487805,
|
| 76 |
+
"grad_norm": 2.4826507568359375,
|
| 77 |
+
"learning_rate": 9.86522435289912e-06,
|
| 78 |
+
"loss": 0.9513,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.5365853658536586,
|
| 83 |
+
"grad_norm": 2.0593159198760986,
|
| 84 |
+
"learning_rate": 9.789947561577445e-06,
|
| 85 |
+
"loss": 0.8729,
|
| 86 |
+
"step": 11
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.5853658536585366,
|
| 90 |
+
"grad_norm": 2.3102424144744873,
|
| 91 |
+
"learning_rate": 9.698463103929542e-06,
|
| 92 |
+
"loss": 0.9028,
|
| 93 |
+
"step": 12
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.6341463414634146,
|
| 97 |
+
"grad_norm": 1.8726847171783447,
|
| 98 |
+
"learning_rate": 9.591080534401371e-06,
|
| 99 |
+
"loss": 0.8811,
|
| 100 |
+
"step": 13
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.6829268292682927,
|
| 104 |
+
"grad_norm": 1.3534939289093018,
|
| 105 |
+
"learning_rate": 9.468163201617063e-06,
|
| 106 |
+
"loss": 0.9254,
|
| 107 |
+
"step": 14
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.7317073170731707,
|
| 111 |
+
"grad_norm": 1.3493455648422241,
|
| 112 |
+
"learning_rate": 9.330127018922195e-06,
|
| 113 |
+
"loss": 0.8082,
|
| 114 |
+
"step": 15
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.7804878048780488,
|
| 118 |
+
"grad_norm": 1.103345274925232,
|
| 119 |
+
"learning_rate": 9.177439057064684e-06,
|
| 120 |
+
"loss": 0.8552,
|
| 121 |
+
"step": 16
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.8292682926829268,
|
| 125 |
+
"grad_norm": 0.8746293783187866,
|
| 126 |
+
"learning_rate": 9.01061596377522e-06,
|
| 127 |
+
"loss": 0.8405,
|
| 128 |
+
"step": 17
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.8780487804878049,
|
| 132 |
+
"grad_norm": 0.923000156879425,
|
| 133 |
+
"learning_rate": 8.83022221559489e-06,
|
| 134 |
+
"loss": 0.8543,
|
| 135 |
+
"step": 18
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.926829268292683,
|
| 139 |
+
"grad_norm": 0.7458917498588562,
|
| 140 |
+
"learning_rate": 8.636868207865244e-06,
|
| 141 |
+
"loss": 0.9075,
|
| 142 |
+
"step": 19
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.975609756097561,
|
| 146 |
+
"grad_norm": 0.7327495813369751,
|
| 147 |
+
"learning_rate": 8.43120818934367e-06,
|
| 148 |
+
"loss": 0.8463,
|
| 149 |
+
"step": 20
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.024390243902439,
|
| 153 |
+
"grad_norm": 1.1537771224975586,
|
| 154 |
+
"learning_rate": 8.213938048432697e-06,
|
| 155 |
+
"loss": 1.1651,
|
| 156 |
+
"step": 21
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 1.0731707317073171,
|
| 160 |
+
"grad_norm": 0.6341186761856079,
|
| 161 |
+
"learning_rate": 7.985792958513932e-06,
|
| 162 |
+
"loss": 0.7399,
|
| 163 |
+
"step": 22
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 1.1219512195121952,
|
| 167 |
+
"grad_norm": 0.7606744170188904,
|
| 168 |
+
"learning_rate": 7.747544890354031e-06,
|
| 169 |
+
"loss": 0.8688,
|
| 170 |
+
"step": 23
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 1.170731707317073,
|
| 174 |
+
"grad_norm": 0.6201728582382202,
|
| 175 |
+
"learning_rate": 7.500000000000001e-06,
|
| 176 |
+
"loss": 0.7049,
|
| 177 |
+
"step": 24
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 1.2195121951219512,
|
| 181 |
+
"grad_norm": 0.8632344007492065,
|
| 182 |
+
"learning_rate": 7.243995901002312e-06,
|
| 183 |
+
"loss": 0.92,
|
| 184 |
+
"step": 25
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 1.2682926829268293,
|
| 188 |
+
"grad_norm": 0.6163485050201416,
|
| 189 |
+
"learning_rate": 6.980398830195785e-06,
|
| 190 |
+
"loss": 0.6655,
|
| 191 |
+
"step": 26
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 1.3170731707317074,
|
| 195 |
+
"grad_norm": 0.5234319567680359,
|
| 196 |
+
"learning_rate": 6.710100716628345e-06,
|
| 197 |
+
"loss": 0.7905,
|
| 198 |
+
"step": 27
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 1.3658536585365852,
|
| 202 |
+
"grad_norm": 0.5779823660850525,
|
| 203 |
+
"learning_rate": 6.434016163555452e-06,
|
| 204 |
+
"loss": 0.8514,
|
| 205 |
+
"step": 28
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 1.4146341463414633,
|
| 209 |
+
"grad_norm": 0.6601042747497559,
|
| 210 |
+
"learning_rate": 6.153079353712201e-06,
|
| 211 |
+
"loss": 0.88,
|
| 212 |
+
"step": 29
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 1.4634146341463414,
|
| 216 |
+
"grad_norm": 0.5179601311683655,
|
| 217 |
+
"learning_rate": 5.8682408883346535e-06,
|
| 218 |
+
"loss": 0.6719,
|
| 219 |
+
"step": 30
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 1.5121951219512195,
|
| 223 |
+
"grad_norm": 0.5515910983085632,
|
| 224 |
+
"learning_rate": 5.5804645706261515e-06,
|
| 225 |
+
"loss": 0.9152,
|
| 226 |
+
"step": 31
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 1.5609756097560976,
|
| 230 |
+
"grad_norm": 0.49588778614997864,
|
| 231 |
+
"learning_rate": 5.290724144552379e-06,
|
| 232 |
+
"loss": 0.6975,
|
| 233 |
+
"step": 32
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 1.6097560975609757,
|
| 237 |
+
"grad_norm": 0.5540623068809509,
|
| 238 |
+
"learning_rate": 5e-06,
|
| 239 |
+
"loss": 0.8428,
|
| 240 |
+
"step": 33
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 1.6585365853658538,
|
| 244 |
+
"grad_norm": 0.5262721180915833,
|
| 245 |
+
"learning_rate": 4.7092758554476215e-06,
|
| 246 |
+
"loss": 0.7701,
|
| 247 |
+
"step": 34
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 1.7073170731707317,
|
| 251 |
+
"grad_norm": 0.499987930059433,
|
| 252 |
+
"learning_rate": 4.4195354293738484e-06,
|
| 253 |
+
"loss": 0.684,
|
| 254 |
+
"step": 35
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 1.7560975609756098,
|
| 258 |
+
"grad_norm": 0.5329548716545105,
|
| 259 |
+
"learning_rate": 4.131759111665349e-06,
|
| 260 |
+
"loss": 0.811,
|
| 261 |
+
"step": 36
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 1.8048780487804879,
|
| 265 |
+
"grad_norm": 0.516512393951416,
|
| 266 |
+
"learning_rate": 3.8469206462878e-06,
|
| 267 |
+
"loss": 0.8534,
|
| 268 |
+
"step": 37
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 1.8536585365853657,
|
| 272 |
+
"grad_norm": 0.5150623917579651,
|
| 273 |
+
"learning_rate": 3.5659838364445505e-06,
|
| 274 |
+
"loss": 0.7364,
|
| 275 |
+
"step": 38
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 1.9024390243902438,
|
| 279 |
+
"grad_norm": 0.5092661380767822,
|
| 280 |
+
"learning_rate": 3.289899283371657e-06,
|
| 281 |
+
"loss": 0.7937,
|
| 282 |
+
"step": 39
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 1.951219512195122,
|
| 286 |
+
"grad_norm": 0.4906715452671051,
|
| 287 |
+
"learning_rate": 3.019601169804216e-06,
|
| 288 |
+
"loss": 0.7559,
|
| 289 |
+
"step": 40
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 2.0,
|
| 293 |
+
"grad_norm": 0.7150355577468872,
|
| 294 |
+
"learning_rate": 2.7560040989976894e-06,
|
| 295 |
+
"loss": 1.254,
|
| 296 |
+
"step": 41
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 2.048780487804878,
|
| 300 |
+
"grad_norm": 0.4212687015533447,
|
| 301 |
+
"learning_rate": 2.5000000000000015e-06,
|
| 302 |
+
"loss": 0.7906,
|
| 303 |
+
"step": 42
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 2.097560975609756,
|
| 307 |
+
"grad_norm": 0.45231571793556213,
|
| 308 |
+
"learning_rate": 2.2524551096459703e-06,
|
| 309 |
+
"loss": 0.7495,
|
| 310 |
+
"step": 43
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 2.1463414634146343,
|
| 314 |
+
"grad_norm": 0.47202828526496887,
|
| 315 |
+
"learning_rate": 2.0142070414860704e-06,
|
| 316 |
+
"loss": 0.7846,
|
| 317 |
+
"step": 44
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 2.1951219512195124,
|
| 321 |
+
"grad_norm": 0.49245500564575195,
|
| 322 |
+
"learning_rate": 1.7860619515673034e-06,
|
| 323 |
+
"loss": 0.7664,
|
| 324 |
+
"step": 45
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 2.2439024390243905,
|
| 328 |
+
"grad_norm": 0.4255480170249939,
|
| 329 |
+
"learning_rate": 1.5687918106563326e-06,
|
| 330 |
+
"loss": 0.7178,
|
| 331 |
+
"step": 46
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 2.292682926829268,
|
| 335 |
+
"grad_norm": 0.42227357625961304,
|
| 336 |
+
"learning_rate": 1.3631317921347564e-06,
|
| 337 |
+
"loss": 0.7867,
|
| 338 |
+
"step": 47
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 2.341463414634146,
|
| 342 |
+
"grad_norm": 0.4211116135120392,
|
| 343 |
+
"learning_rate": 1.1697777844051105e-06,
|
| 344 |
+
"loss": 0.7419,
|
| 345 |
+
"step": 48
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 2.3902439024390243,
|
| 349 |
+
"grad_norm": 0.38902539014816284,
|
| 350 |
+
"learning_rate": 9.893840362247809e-07,
|
| 351 |
+
"loss": 0.7224,
|
| 352 |
+
"step": 49
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 2.4390243902439024,
|
| 356 |
+
"grad_norm": 0.473481684923172,
|
| 357 |
+
"learning_rate": 8.225609429353187e-07,
|
| 358 |
+
"loss": 0.7914,
|
| 359 |
+
"step": 50
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 2.4878048780487805,
|
| 363 |
+
"grad_norm": 0.40908774733543396,
|
| 364 |
+
"learning_rate": 6.698729810778065e-07,
|
| 365 |
+
"loss": 0.7448,
|
| 366 |
+
"step": 51
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 2.5365853658536586,
|
| 370 |
+
"grad_norm": 0.4036145806312561,
|
| 371 |
+
"learning_rate": 5.318367983829393e-07,
|
| 372 |
+
"loss": 0.7486,
|
| 373 |
+
"step": 52
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 2.5853658536585367,
|
| 377 |
+
"grad_norm": 0.4587302803993225,
|
| 378 |
+
"learning_rate": 4.089194655986306e-07,
|
| 379 |
+
"loss": 0.7421,
|
| 380 |
+
"step": 53
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 2.6341463414634148,
|
| 384 |
+
"grad_norm": 0.42735883593559265,
|
| 385 |
+
"learning_rate": 3.015368960704584e-07,
|
| 386 |
+
"loss": 0.8132,
|
| 387 |
+
"step": 54
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 2.682926829268293,
|
| 391 |
+
"grad_norm": 0.3429286777973175,
|
| 392 |
+
"learning_rate": 2.1005243842255552e-07,
|
| 393 |
+
"loss": 0.7491,
|
| 394 |
+
"step": 55
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 2.7317073170731705,
|
| 398 |
+
"grad_norm": 0.3881649971008301,
|
| 399 |
+
"learning_rate": 1.3477564710088097e-07,
|
| 400 |
+
"loss": 0.7919,
|
| 401 |
+
"step": 56
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 2.7804878048780486,
|
| 405 |
+
"grad_norm": 0.36438366770744324,
|
| 406 |
+
"learning_rate": 7.59612349389599e-08,
|
| 407 |
+
"loss": 0.7485,
|
| 408 |
+
"step": 57
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 2.8292682926829267,
|
| 412 |
+
"grad_norm": 0.4045783579349518,
|
| 413 |
+
"learning_rate": 3.3808211290284886e-08,
|
| 414 |
+
"loss": 0.734,
|
| 415 |
+
"step": 58
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 2.8780487804878048,
|
| 419 |
+
"grad_norm": 0.3840378522872925,
|
| 420 |
+
"learning_rate": 8.459208643659122e-09,
|
| 421 |
+
"loss": 0.7751,
|
| 422 |
+
"step": 59
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 2.926829268292683,
|
| 426 |
+
"grad_norm": 0.41218218207359314,
|
| 427 |
+
"learning_rate": 0.0,
|
| 428 |
+
"loss": 0.7135,
|
| 429 |
+
"step": 60
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 2.926829268292683,
|
| 433 |
+
"step": 60,
|
| 434 |
+
"total_flos": 56084346568704.0,
|
| 435 |
+
"train_loss": 0.8459723273913066,
|
| 436 |
+
"train_runtime": 3353.8656,
|
| 437 |
+
"train_samples_per_second": 1.756,
|
| 438 |
+
"train_steps_per_second": 0.018
|
| 439 |
+
}
|
| 440 |
+
],
|
| 441 |
+
"logging_steps": 1.0,
|
| 442 |
+
"max_steps": 60,
|
| 443 |
+
"num_input_tokens_seen": 0,
|
| 444 |
+
"num_train_epochs": 3,
|
| 445 |
+
"save_steps": 500,
|
| 446 |
+
"stateful_callbacks": {
|
| 447 |
+
"TrainerControl": {
|
| 448 |
+
"args": {
|
| 449 |
+
"should_epoch_stop": false,
|
| 450 |
+
"should_evaluate": false,
|
| 451 |
+
"should_log": false,
|
| 452 |
+
"should_save": true,
|
| 453 |
+
"should_training_stop": true
|
| 454 |
+
},
|
| 455 |
+
"attributes": {}
|
| 456 |
+
}
|
| 457 |
+
},
|
| 458 |
+
"total_flos": 56084346568704.0,
|
| 459 |
+
"train_batch_size": 1,
|
| 460 |
+
"trial_name": null,
|
| 461 |
+
"trial_params": null
|
| 462 |
+
}
|
training_loss.png
ADDED
|