End of training
Browse files- README.md +2 -1
- all_results.json +12 -0
- eval_results.json +7 -0
- train_results.json +8 -0
- trainer_state.json +486 -0
- training_eval_loss.png +0 -0
- training_loss.png +0 -0
README.md
CHANGED
|
@@ -4,6 +4,7 @@ license: llama3.1
|
|
| 4 |
base_model: meta-llama/Meta-Llama-3.1-8B
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
|
|
|
| 7 |
- generated_from_trainer
|
| 8 |
model-index:
|
| 9 |
- name: top_5_ranking_stackexchange
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# top_5_ranking_stackexchange
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) on
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
- Loss: 0.7860
|
| 21 |
|
|
|
|
| 4 |
base_model: meta-llama/Meta-Llama-3.1-8B
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
| 7 |
+
- full
|
| 8 |
- generated_from_trainer
|
| 9 |
model-index:
|
| 10 |
- name: top_5_ranking_stackexchange
|
|
|
|
| 16 |
|
| 17 |
# top_5_ranking_stackexchange
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) on the mlfoundations-dev/top_5_ranking_stackexchange dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
- Loss: 0.7860
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.9962546816479403,
|
| 3 |
+
"eval_loss": 0.7859531044960022,
|
| 4 |
+
"eval_runtime": 214.0804,
|
| 5 |
+
"eval_samples_per_second": 25.21,
|
| 6 |
+
"eval_steps_per_second": 0.397,
|
| 7 |
+
"total_flos": 1004812967608320.0,
|
| 8 |
+
"train_loss": 0.773849273522695,
|
| 9 |
+
"train_runtime": 35442.7976,
|
| 10 |
+
"train_samples_per_second": 8.678,
|
| 11 |
+
"train_steps_per_second": 0.017
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.9962546816479403,
|
| 3 |
+
"eval_loss": 0.7859531044960022,
|
| 4 |
+
"eval_runtime": 214.0804,
|
| 5 |
+
"eval_samples_per_second": 25.21,
|
| 6 |
+
"eval_steps_per_second": 0.397
|
| 7 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.9962546816479403,
|
| 3 |
+
"total_flos": 1004812967608320.0,
|
| 4 |
+
"train_loss": 0.773849273522695,
|
| 5 |
+
"train_runtime": 35442.7976,
|
| 6 |
+
"train_samples_per_second": 8.678,
|
| 7 |
+
"train_steps_per_second": 0.017
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,486 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.9962546816479403,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 600,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.049937578027465665,
|
| 13 |
+
"grad_norm": 29.759422123901825,
|
| 14 |
+
"learning_rate": 5e-06,
|
| 15 |
+
"loss": 1.0298,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.09987515605493133,
|
| 20 |
+
"grad_norm": 1.659620518169597,
|
| 21 |
+
"learning_rate": 5e-06,
|
| 22 |
+
"loss": 0.9418,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.149812734082397,
|
| 27 |
+
"grad_norm": 1.6655817038532692,
|
| 28 |
+
"learning_rate": 5e-06,
|
| 29 |
+
"loss": 0.9067,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.19975031210986266,
|
| 34 |
+
"grad_norm": 3.758532618440977,
|
| 35 |
+
"learning_rate": 5e-06,
|
| 36 |
+
"loss": 0.8837,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.24968789013732834,
|
| 41 |
+
"grad_norm": 1.0914089528556838,
|
| 42 |
+
"learning_rate": 5e-06,
|
| 43 |
+
"loss": 0.8683,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.299625468164794,
|
| 48 |
+
"grad_norm": 0.8217188574851603,
|
| 49 |
+
"learning_rate": 5e-06,
|
| 50 |
+
"loss": 0.8554,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.3495630461922597,
|
| 55 |
+
"grad_norm": 2.6152137256768913,
|
| 56 |
+
"learning_rate": 5e-06,
|
| 57 |
+
"loss": 0.8501,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.3995006242197253,
|
| 62 |
+
"grad_norm": 0.6790645381435163,
|
| 63 |
+
"learning_rate": 5e-06,
|
| 64 |
+
"loss": 0.8376,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.449438202247191,
|
| 69 |
+
"grad_norm": 1.050547891408586,
|
| 70 |
+
"learning_rate": 5e-06,
|
| 71 |
+
"loss": 0.8389,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.4993757802746567,
|
| 76 |
+
"grad_norm": 0.61531936130051,
|
| 77 |
+
"learning_rate": 5e-06,
|
| 78 |
+
"loss": 0.8283,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.5493133583021224,
|
| 83 |
+
"grad_norm": 0.7158756598167714,
|
| 84 |
+
"learning_rate": 5e-06,
|
| 85 |
+
"loss": 0.8285,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.599250936329588,
|
| 90 |
+
"grad_norm": 0.6741740850175894,
|
| 91 |
+
"learning_rate": 5e-06,
|
| 92 |
+
"loss": 0.8208,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.6491885143570537,
|
| 97 |
+
"grad_norm": 0.727395321147856,
|
| 98 |
+
"learning_rate": 5e-06,
|
| 99 |
+
"loss": 0.8226,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.6991260923845194,
|
| 104 |
+
"grad_norm": 0.5979029940330495,
|
| 105 |
+
"learning_rate": 5e-06,
|
| 106 |
+
"loss": 0.8218,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.7490636704119851,
|
| 111 |
+
"grad_norm": 0.7354628133399658,
|
| 112 |
+
"learning_rate": 5e-06,
|
| 113 |
+
"loss": 0.8146,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.7990012484394506,
|
| 118 |
+
"grad_norm": 1.0797869029852383,
|
| 119 |
+
"learning_rate": 5e-06,
|
| 120 |
+
"loss": 0.811,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.8489388264669163,
|
| 125 |
+
"grad_norm": 0.5732338176348897,
|
| 126 |
+
"learning_rate": 5e-06,
|
| 127 |
+
"loss": 0.8117,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.898876404494382,
|
| 132 |
+
"grad_norm": 0.516647597175339,
|
| 133 |
+
"learning_rate": 5e-06,
|
| 134 |
+
"loss": 0.8099,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.9488139825218477,
|
| 139 |
+
"grad_norm": 0.595235164677505,
|
| 140 |
+
"learning_rate": 5e-06,
|
| 141 |
+
"loss": 0.8062,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.9987515605493134,
|
| 146 |
+
"grad_norm": 0.5491264032653016,
|
| 147 |
+
"learning_rate": 5e-06,
|
| 148 |
+
"loss": 0.7992,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.9987515605493134,
|
| 153 |
+
"eval_loss": 0.8015628457069397,
|
| 154 |
+
"eval_runtime": 212.5855,
|
| 155 |
+
"eval_samples_per_second": 25.387,
|
| 156 |
+
"eval_steps_per_second": 0.4,
|
| 157 |
+
"step": 200
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 1.048689138576779,
|
| 161 |
+
"grad_norm": 1.1815779977106664,
|
| 162 |
+
"learning_rate": 5e-06,
|
| 163 |
+
"loss": 0.8245,
|
| 164 |
+
"step": 210
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 1.0986267166042447,
|
| 168 |
+
"grad_norm": 0.8607004375758024,
|
| 169 |
+
"learning_rate": 5e-06,
|
| 170 |
+
"loss": 0.7537,
|
| 171 |
+
"step": 220
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 1.1485642946317103,
|
| 175 |
+
"grad_norm": 0.6382531480247193,
|
| 176 |
+
"learning_rate": 5e-06,
|
| 177 |
+
"loss": 0.7617,
|
| 178 |
+
"step": 230
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 1.198501872659176,
|
| 182 |
+
"grad_norm": 0.5848998545511357,
|
| 183 |
+
"learning_rate": 5e-06,
|
| 184 |
+
"loss": 0.7635,
|
| 185 |
+
"step": 240
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 1.2484394506866416,
|
| 189 |
+
"grad_norm": 0.6856479277932508,
|
| 190 |
+
"learning_rate": 5e-06,
|
| 191 |
+
"loss": 0.7623,
|
| 192 |
+
"step": 250
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 1.2983770287141074,
|
| 196 |
+
"grad_norm": 0.7819524787327043,
|
| 197 |
+
"learning_rate": 5e-06,
|
| 198 |
+
"loss": 0.7567,
|
| 199 |
+
"step": 260
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 1.348314606741573,
|
| 203 |
+
"grad_norm": 0.6831313099201878,
|
| 204 |
+
"learning_rate": 5e-06,
|
| 205 |
+
"loss": 0.7606,
|
| 206 |
+
"step": 270
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 1.3982521847690386,
|
| 210 |
+
"grad_norm": 0.6700856388131974,
|
| 211 |
+
"learning_rate": 5e-06,
|
| 212 |
+
"loss": 0.7553,
|
| 213 |
+
"step": 280
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 1.4481897627965044,
|
| 217 |
+
"grad_norm": 0.5874295240823044,
|
| 218 |
+
"learning_rate": 5e-06,
|
| 219 |
+
"loss": 0.7575,
|
| 220 |
+
"step": 290
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 1.4981273408239701,
|
| 224 |
+
"grad_norm": 0.6100148315517313,
|
| 225 |
+
"learning_rate": 5e-06,
|
| 226 |
+
"loss": 0.7523,
|
| 227 |
+
"step": 300
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 1.5480649188514357,
|
| 231 |
+
"grad_norm": 0.6291672713518774,
|
| 232 |
+
"learning_rate": 5e-06,
|
| 233 |
+
"loss": 0.759,
|
| 234 |
+
"step": 310
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 1.5980024968789013,
|
| 238 |
+
"grad_norm": 0.7275448418797654,
|
| 239 |
+
"learning_rate": 5e-06,
|
| 240 |
+
"loss": 0.7532,
|
| 241 |
+
"step": 320
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 1.647940074906367,
|
| 245 |
+
"grad_norm": 0.6798292981346045,
|
| 246 |
+
"learning_rate": 5e-06,
|
| 247 |
+
"loss": 0.7652,
|
| 248 |
+
"step": 330
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 1.6978776529338329,
|
| 252 |
+
"grad_norm": 0.7320780258400261,
|
| 253 |
+
"learning_rate": 5e-06,
|
| 254 |
+
"loss": 0.7554,
|
| 255 |
+
"step": 340
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 1.7478152309612984,
|
| 259 |
+
"grad_norm": 0.6107676047027211,
|
| 260 |
+
"learning_rate": 5e-06,
|
| 261 |
+
"loss": 0.757,
|
| 262 |
+
"step": 350
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 1.797752808988764,
|
| 266 |
+
"grad_norm": 0.5083613384732135,
|
| 267 |
+
"learning_rate": 5e-06,
|
| 268 |
+
"loss": 0.7576,
|
| 269 |
+
"step": 360
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 1.8476903870162298,
|
| 273 |
+
"grad_norm": 0.5021025632111004,
|
| 274 |
+
"learning_rate": 5e-06,
|
| 275 |
+
"loss": 0.7584,
|
| 276 |
+
"step": 370
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 1.8976279650436954,
|
| 280 |
+
"grad_norm": 0.6593302140861815,
|
| 281 |
+
"learning_rate": 5e-06,
|
| 282 |
+
"loss": 0.755,
|
| 283 |
+
"step": 380
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 1.947565543071161,
|
| 287 |
+
"grad_norm": 0.5669868340257436,
|
| 288 |
+
"learning_rate": 5e-06,
|
| 289 |
+
"loss": 0.7478,
|
| 290 |
+
"step": 390
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 1.9975031210986267,
|
| 294 |
+
"grad_norm": 0.5745040341281294,
|
| 295 |
+
"learning_rate": 5e-06,
|
| 296 |
+
"loss": 0.7538,
|
| 297 |
+
"step": 400
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 1.9975031210986267,
|
| 301 |
+
"eval_loss": 0.7874204516410828,
|
| 302 |
+
"eval_runtime": 212.6782,
|
| 303 |
+
"eval_samples_per_second": 25.376,
|
| 304 |
+
"eval_steps_per_second": 0.4,
|
| 305 |
+
"step": 400
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 2.0474406991260925,
|
| 309 |
+
"grad_norm": 0.6952347883899184,
|
| 310 |
+
"learning_rate": 5e-06,
|
| 311 |
+
"loss": 0.7611,
|
| 312 |
+
"step": 410
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 2.097378277153558,
|
| 316 |
+
"grad_norm": 0.6000479994459602,
|
| 317 |
+
"learning_rate": 5e-06,
|
| 318 |
+
"loss": 0.7037,
|
| 319 |
+
"step": 420
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 2.1473158551810236,
|
| 323 |
+
"grad_norm": 0.6575266096005482,
|
| 324 |
+
"learning_rate": 5e-06,
|
| 325 |
+
"loss": 0.7089,
|
| 326 |
+
"step": 430
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 2.1972534332084894,
|
| 330 |
+
"grad_norm": 0.7384159721059136,
|
| 331 |
+
"learning_rate": 5e-06,
|
| 332 |
+
"loss": 0.7057,
|
| 333 |
+
"step": 440
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 2.247191011235955,
|
| 337 |
+
"grad_norm": 0.6735840214535883,
|
| 338 |
+
"learning_rate": 5e-06,
|
| 339 |
+
"loss": 0.706,
|
| 340 |
+
"step": 450
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 2.2971285892634206,
|
| 344 |
+
"grad_norm": 0.7153617513297972,
|
| 345 |
+
"learning_rate": 5e-06,
|
| 346 |
+
"loss": 0.7064,
|
| 347 |
+
"step": 460
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 2.3470661672908864,
|
| 351 |
+
"grad_norm": 0.7396133098853745,
|
| 352 |
+
"learning_rate": 5e-06,
|
| 353 |
+
"loss": 0.7049,
|
| 354 |
+
"step": 470
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 2.397003745318352,
|
| 358 |
+
"grad_norm": 0.6440383221784979,
|
| 359 |
+
"learning_rate": 5e-06,
|
| 360 |
+
"loss": 0.705,
|
| 361 |
+
"step": 480
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 2.4469413233458175,
|
| 365 |
+
"grad_norm": 0.5481603423583875,
|
| 366 |
+
"learning_rate": 5e-06,
|
| 367 |
+
"loss": 0.709,
|
| 368 |
+
"step": 490
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 2.4968789013732833,
|
| 372 |
+
"grad_norm": 0.6611697985224058,
|
| 373 |
+
"learning_rate": 5e-06,
|
| 374 |
+
"loss": 0.71,
|
| 375 |
+
"step": 500
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 2.546816479400749,
|
| 379 |
+
"grad_norm": 0.6252639550455323,
|
| 380 |
+
"learning_rate": 5e-06,
|
| 381 |
+
"loss": 0.7128,
|
| 382 |
+
"step": 510
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 2.596754057428215,
|
| 386 |
+
"grad_norm": 0.578764019014536,
|
| 387 |
+
"learning_rate": 5e-06,
|
| 388 |
+
"loss": 0.7116,
|
| 389 |
+
"step": 520
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 2.6466916354556806,
|
| 393 |
+
"grad_norm": 0.5718219886250622,
|
| 394 |
+
"learning_rate": 5e-06,
|
| 395 |
+
"loss": 0.711,
|
| 396 |
+
"step": 530
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 2.696629213483146,
|
| 400 |
+
"grad_norm": 0.6480951015929783,
|
| 401 |
+
"learning_rate": 5e-06,
|
| 402 |
+
"loss": 0.706,
|
| 403 |
+
"step": 540
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 2.746566791510612,
|
| 407 |
+
"grad_norm": 0.568128147930456,
|
| 408 |
+
"learning_rate": 5e-06,
|
| 409 |
+
"loss": 0.7144,
|
| 410 |
+
"step": 550
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 2.796504369538077,
|
| 414 |
+
"grad_norm": 0.7016907742592169,
|
| 415 |
+
"learning_rate": 5e-06,
|
| 416 |
+
"loss": 0.708,
|
| 417 |
+
"step": 560
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 2.846441947565543,
|
| 421 |
+
"grad_norm": 0.6718047517989062,
|
| 422 |
+
"learning_rate": 5e-06,
|
| 423 |
+
"loss": 0.7147,
|
| 424 |
+
"step": 570
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 2.8963795255930087,
|
| 428 |
+
"grad_norm": 0.7869266984488797,
|
| 429 |
+
"learning_rate": 5e-06,
|
| 430 |
+
"loss": 0.7114,
|
| 431 |
+
"step": 580
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 2.9463171036204745,
|
| 435 |
+
"grad_norm": 0.6070316014377024,
|
| 436 |
+
"learning_rate": 5e-06,
|
| 437 |
+
"loss": 0.7072,
|
| 438 |
+
"step": 590
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 2.9962546816479403,
|
| 442 |
+
"grad_norm": 0.5662761836861052,
|
| 443 |
+
"learning_rate": 5e-06,
|
| 444 |
+
"loss": 0.7158,
|
| 445 |
+
"step": 600
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 2.9962546816479403,
|
| 449 |
+
"eval_loss": 0.7859531044960022,
|
| 450 |
+
"eval_runtime": 213.866,
|
| 451 |
+
"eval_samples_per_second": 25.235,
|
| 452 |
+
"eval_steps_per_second": 0.397,
|
| 453 |
+
"step": 600
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 2.9962546816479403,
|
| 457 |
+
"step": 600,
|
| 458 |
+
"total_flos": 1004812967608320.0,
|
| 459 |
+
"train_loss": 0.773849273522695,
|
| 460 |
+
"train_runtime": 35442.7976,
|
| 461 |
+
"train_samples_per_second": 8.678,
|
| 462 |
+
"train_steps_per_second": 0.017
|
| 463 |
+
}
|
| 464 |
+
],
|
| 465 |
+
"logging_steps": 10,
|
| 466 |
+
"max_steps": 600,
|
| 467 |
+
"num_input_tokens_seen": 0,
|
| 468 |
+
"num_train_epochs": 3,
|
| 469 |
+
"save_steps": 500,
|
| 470 |
+
"stateful_callbacks": {
|
| 471 |
+
"TrainerControl": {
|
| 472 |
+
"args": {
|
| 473 |
+
"should_epoch_stop": false,
|
| 474 |
+
"should_evaluate": false,
|
| 475 |
+
"should_log": false,
|
| 476 |
+
"should_save": true,
|
| 477 |
+
"should_training_stop": true
|
| 478 |
+
},
|
| 479 |
+
"attributes": {}
|
| 480 |
+
}
|
| 481 |
+
},
|
| 482 |
+
"total_flos": 1004812967608320.0,
|
| 483 |
+
"train_batch_size": 8,
|
| 484 |
+
"trial_name": null,
|
| 485 |
+
"trial_params": null
|
| 486 |
+
}
|
training_eval_loss.png
ADDED
|
training_loss.png
ADDED
|