End of training
Browse files- README.md +2 -1
- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +546 -0
- training_loss.png +0 -0
README.md
CHANGED
|
@@ -4,6 +4,7 @@ license: apache-2.0
|
|
| 4 |
base_model: Qwen/Qwen2.5-Coder-14B-Instruct
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
|
|
|
| 7 |
- generated_from_trainer
|
| 8 |
model-index:
|
| 9 |
- name: SWE-BENCH-reproduce-verify-validation_qwen_code_14B_lite_validation
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# SWE-BENCH-reproduce-verify-validation_qwen_code_14B_lite_validation
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [Qwen/Qwen2.5-Coder-14B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-14B-Instruct) on
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
|
|
| 4 |
base_model: Qwen/Qwen2.5-Coder-14B-Instruct
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
| 7 |
+
- full
|
| 8 |
- generated_from_trainer
|
| 9 |
model-index:
|
| 10 |
- name: SWE-BENCH-reproduce-verify-validation_qwen_code_14B_lite_validation
|
|
|
|
| 16 |
|
| 17 |
# SWE-BENCH-reproduce-verify-validation_qwen_code_14B_lite_validation
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [Qwen/Qwen2.5-Coder-14B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-14B-Instruct) on the SWE-BENCH-reproduce-verify-validation dataset.
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.909090909090909,
|
| 3 |
+
"total_flos": 3.5981250321711104e+16,
|
| 4 |
+
"train_loss": 0.4774101939466264,
|
| 5 |
+
"train_runtime": 9083.6349,
|
| 6 |
+
"train_samples_per_second": 0.392,
|
| 7 |
+
"train_steps_per_second": 0.008
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.909090909090909,
|
| 3 |
+
"total_flos": 3.5981250321711104e+16,
|
| 4 |
+
"train_loss": 0.4774101939466264,
|
| 5 |
+
"train_runtime": 9083.6349,
|
| 6 |
+
"train_samples_per_second": 0.392,
|
| 7 |
+
"train_steps_per_second": 0.008
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,546 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.909090909090909,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 72,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.04040404040404041,
|
| 13 |
+
"grad_norm": 1.6406759023666382,
|
| 14 |
+
"learning_rate": 1.25e-06,
|
| 15 |
+
"loss": 0.7384,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.08080808080808081,
|
| 20 |
+
"grad_norm": 1.777174472808838,
|
| 21 |
+
"learning_rate": 2.5e-06,
|
| 22 |
+
"loss": 0.7666,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.12121212121212122,
|
| 27 |
+
"grad_norm": 1.6539289951324463,
|
| 28 |
+
"learning_rate": 3.7500000000000005e-06,
|
| 29 |
+
"loss": 0.7385,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.16161616161616163,
|
| 34 |
+
"grad_norm": 1.5728503465652466,
|
| 35 |
+
"learning_rate": 5e-06,
|
| 36 |
+
"loss": 0.7408,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.20202020202020202,
|
| 41 |
+
"grad_norm": 1.4771438837051392,
|
| 42 |
+
"learning_rate": 6.25e-06,
|
| 43 |
+
"loss": 0.7154,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.24242424242424243,
|
| 48 |
+
"grad_norm": 1.1310724020004272,
|
| 49 |
+
"learning_rate": 7.500000000000001e-06,
|
| 50 |
+
"loss": 0.7054,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.2828282828282828,
|
| 55 |
+
"grad_norm": 0.9647331833839417,
|
| 56 |
+
"learning_rate": 8.750000000000001e-06,
|
| 57 |
+
"loss": 0.6335,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.32323232323232326,
|
| 62 |
+
"grad_norm": 0.8720846772193909,
|
| 63 |
+
"learning_rate": 1e-05,
|
| 64 |
+
"loss": 0.6252,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.36363636363636365,
|
| 69 |
+
"grad_norm": 0.9205116033554077,
|
| 70 |
+
"learning_rate": 9.993977281025862e-06,
|
| 71 |
+
"loss": 0.6279,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.40404040404040403,
|
| 76 |
+
"grad_norm": 0.9854218363761902,
|
| 77 |
+
"learning_rate": 9.975923633360985e-06,
|
| 78 |
+
"loss": 0.6394,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.4444444444444444,
|
| 83 |
+
"grad_norm": 0.9342491030693054,
|
| 84 |
+
"learning_rate": 9.945882549823906e-06,
|
| 85 |
+
"loss": 0.6368,
|
| 86 |
+
"step": 11
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.48484848484848486,
|
| 90 |
+
"grad_norm": 0.7965356111526489,
|
| 91 |
+
"learning_rate": 9.903926402016153e-06,
|
| 92 |
+
"loss": 0.6019,
|
| 93 |
+
"step": 12
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.5252525252525253,
|
| 97 |
+
"grad_norm": 0.6925312876701355,
|
| 98 |
+
"learning_rate": 9.850156265972722e-06,
|
| 99 |
+
"loss": 0.6251,
|
| 100 |
+
"step": 13
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.5656565656565656,
|
| 104 |
+
"grad_norm": 0.7038740515708923,
|
| 105 |
+
"learning_rate": 9.784701678661045e-06,
|
| 106 |
+
"loss": 0.6023,
|
| 107 |
+
"step": 14
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.6060606060606061,
|
| 111 |
+
"grad_norm": 0.5820484161376953,
|
| 112 |
+
"learning_rate": 9.707720325915105e-06,
|
| 113 |
+
"loss": 0.5583,
|
| 114 |
+
"step": 15
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.6464646464646465,
|
| 118 |
+
"grad_norm": 0.6657494306564331,
|
| 119 |
+
"learning_rate": 9.619397662556434e-06,
|
| 120 |
+
"loss": 0.6093,
|
| 121 |
+
"step": 16
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.6868686868686869,
|
| 125 |
+
"grad_norm": 0.5573738813400269,
|
| 126 |
+
"learning_rate": 9.519946465617217e-06,
|
| 127 |
+
"loss": 0.5488,
|
| 128 |
+
"step": 17
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.7272727272727273,
|
| 132 |
+
"grad_norm": 0.5118197202682495,
|
| 133 |
+
"learning_rate": 9.409606321741776e-06,
|
| 134 |
+
"loss": 0.5422,
|
| 135 |
+
"step": 18
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.7676767676767676,
|
| 139 |
+
"grad_norm": 0.53837651014328,
|
| 140 |
+
"learning_rate": 9.288643050001362e-06,
|
| 141 |
+
"loss": 0.5477,
|
| 142 |
+
"step": 19
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.8080808080808081,
|
| 146 |
+
"grad_norm": 0.49398595094680786,
|
| 147 |
+
"learning_rate": 9.157348061512728e-06,
|
| 148 |
+
"loss": 0.5245,
|
| 149 |
+
"step": 20
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.8484848484848485,
|
| 153 |
+
"grad_norm": 0.48072442412376404,
|
| 154 |
+
"learning_rate": 9.016037657403225e-06,
|
| 155 |
+
"loss": 0.5405,
|
| 156 |
+
"step": 21
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.8888888888888888,
|
| 160 |
+
"grad_norm": 0.48007655143737793,
|
| 161 |
+
"learning_rate": 8.865052266813686e-06,
|
| 162 |
+
"loss": 0.5306,
|
| 163 |
+
"step": 22
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.9292929292929293,
|
| 167 |
+
"grad_norm": 0.45421069860458374,
|
| 168 |
+
"learning_rate": 8.704755626774796e-06,
|
| 169 |
+
"loss": 0.4897,
|
| 170 |
+
"step": 23
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.9696969696969697,
|
| 174 |
+
"grad_norm": 0.47499579191207886,
|
| 175 |
+
"learning_rate": 8.535533905932739e-06,
|
| 176 |
+
"loss": 0.4854,
|
| 177 |
+
"step": 24
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 1.0101010101010102,
|
| 181 |
+
"grad_norm": 0.6332795023918152,
|
| 182 |
+
"learning_rate": 8.357794774235094e-06,
|
| 183 |
+
"loss": 0.675,
|
| 184 |
+
"step": 25
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 1.0505050505050506,
|
| 188 |
+
"grad_norm": 0.47866344451904297,
|
| 189 |
+
"learning_rate": 8.171966420818227e-06,
|
| 190 |
+
"loss": 0.4459,
|
| 191 |
+
"step": 26
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 1.0909090909090908,
|
| 195 |
+
"grad_norm": 0.46443578600883484,
|
| 196 |
+
"learning_rate": 7.978496522462167e-06,
|
| 197 |
+
"loss": 0.4561,
|
| 198 |
+
"step": 27
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 1.1313131313131313,
|
| 202 |
+
"grad_norm": 0.4448317885398865,
|
| 203 |
+
"learning_rate": 7.777851165098012e-06,
|
| 204 |
+
"loss": 0.4448,
|
| 205 |
+
"step": 28
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 1.1717171717171717,
|
| 209 |
+
"grad_norm": 0.44462504982948303,
|
| 210 |
+
"learning_rate": 7.570513720966108e-06,
|
| 211 |
+
"loss": 0.4434,
|
| 212 |
+
"step": 29
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 1.2121212121212122,
|
| 216 |
+
"grad_norm": 0.44808101654052734,
|
| 217 |
+
"learning_rate": 7.3569836841299905e-06,
|
| 218 |
+
"loss": 0.4443,
|
| 219 |
+
"step": 30
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 1.2525252525252526,
|
| 223 |
+
"grad_norm": 0.473147988319397,
|
| 224 |
+
"learning_rate": 7.137775467151411e-06,
|
| 225 |
+
"loss": 0.4634,
|
| 226 |
+
"step": 31
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 1.2929292929292928,
|
| 230 |
+
"grad_norm": 0.46904295682907104,
|
| 231 |
+
"learning_rate": 6.913417161825449e-06,
|
| 232 |
+
"loss": 0.4505,
|
| 233 |
+
"step": 32
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 1.3333333333333333,
|
| 237 |
+
"grad_norm": 0.46802252531051636,
|
| 238 |
+
"learning_rate": 6.684449266961101e-06,
|
| 239 |
+
"loss": 0.4489,
|
| 240 |
+
"step": 33
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 1.3737373737373737,
|
| 244 |
+
"grad_norm": 0.43041056394577026,
|
| 245 |
+
"learning_rate": 6.451423386272312e-06,
|
| 246 |
+
"loss": 0.3996,
|
| 247 |
+
"step": 34
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 1.4141414141414141,
|
| 251 |
+
"grad_norm": 0.4580051004886627,
|
| 252 |
+
"learning_rate": 6.21490089951632e-06,
|
| 253 |
+
"loss": 0.4013,
|
| 254 |
+
"step": 35
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 1.4545454545454546,
|
| 258 |
+
"grad_norm": 0.48125723004341125,
|
| 259 |
+
"learning_rate": 5.975451610080643e-06,
|
| 260 |
+
"loss": 0.4606,
|
| 261 |
+
"step": 36
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 1.494949494949495,
|
| 265 |
+
"grad_norm": 0.4803732633590698,
|
| 266 |
+
"learning_rate": 5.733652372276809e-06,
|
| 267 |
+
"loss": 0.4398,
|
| 268 |
+
"step": 37
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 1.5353535353535355,
|
| 272 |
+
"grad_norm": 0.4758044481277466,
|
| 273 |
+
"learning_rate": 5.490085701647805e-06,
|
| 274 |
+
"loss": 0.4314,
|
| 275 |
+
"step": 38
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 1.5757575757575757,
|
| 279 |
+
"grad_norm": 0.43107980489730835,
|
| 280 |
+
"learning_rate": 5.245338371637091e-06,
|
| 281 |
+
"loss": 0.4052,
|
| 282 |
+
"step": 39
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 1.6161616161616161,
|
| 286 |
+
"grad_norm": 0.4567951560020447,
|
| 287 |
+
"learning_rate": 5e-06,
|
| 288 |
+
"loss": 0.4341,
|
| 289 |
+
"step": 40
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 1.6565656565656566,
|
| 293 |
+
"grad_norm": 0.48505422472953796,
|
| 294 |
+
"learning_rate": 4.75466162836291e-06,
|
| 295 |
+
"loss": 0.4169,
|
| 296 |
+
"step": 41
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 1.696969696969697,
|
| 300 |
+
"grad_norm": 0.490830659866333,
|
| 301 |
+
"learning_rate": 4.509914298352197e-06,
|
| 302 |
+
"loss": 0.4441,
|
| 303 |
+
"step": 42
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 1.7373737373737375,
|
| 307 |
+
"grad_norm": 0.4757992923259735,
|
| 308 |
+
"learning_rate": 4.266347627723192e-06,
|
| 309 |
+
"loss": 0.4306,
|
| 310 |
+
"step": 43
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 1.7777777777777777,
|
| 314 |
+
"grad_norm": 0.47538337111473083,
|
| 315 |
+
"learning_rate": 4.02454838991936e-06,
|
| 316 |
+
"loss": 0.4153,
|
| 317 |
+
"step": 44
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 1.8181818181818183,
|
| 321 |
+
"grad_norm": 0.45427966117858887,
|
| 322 |
+
"learning_rate": 3.7850991004836813e-06,
|
| 323 |
+
"loss": 0.4075,
|
| 324 |
+
"step": 45
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 1.8585858585858586,
|
| 328 |
+
"grad_norm": 0.4872586131095886,
|
| 329 |
+
"learning_rate": 3.5485766137276894e-06,
|
| 330 |
+
"loss": 0.44,
|
| 331 |
+
"step": 46
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 1.898989898989899,
|
| 335 |
+
"grad_norm": 0.4346865117549896,
|
| 336 |
+
"learning_rate": 3.3155507330389004e-06,
|
| 337 |
+
"loss": 0.4338,
|
| 338 |
+
"step": 47
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 1.9393939393939394,
|
| 342 |
+
"grad_norm": 0.44030866026878357,
|
| 343 |
+
"learning_rate": 3.0865828381745515e-06,
|
| 344 |
+
"loss": 0.3924,
|
| 345 |
+
"step": 48
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 1.9797979797979797,
|
| 349 |
+
"grad_norm": 0.512447714805603,
|
| 350 |
+
"learning_rate": 2.862224532848591e-06,
|
| 351 |
+
"loss": 0.4813,
|
| 352 |
+
"step": 49
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 2.0202020202020203,
|
| 356 |
+
"grad_norm": 0.5484603643417358,
|
| 357 |
+
"learning_rate": 2.6430163158700116e-06,
|
| 358 |
+
"loss": 0.4593,
|
| 359 |
+
"step": 50
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 2.0606060606060606,
|
| 363 |
+
"grad_norm": 0.44288182258605957,
|
| 364 |
+
"learning_rate": 2.429486279033892e-06,
|
| 365 |
+
"loss": 0.3801,
|
| 366 |
+
"step": 51
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 2.101010101010101,
|
| 370 |
+
"grad_norm": 0.43875348567962646,
|
| 371 |
+
"learning_rate": 2.2221488349019903e-06,
|
| 372 |
+
"loss": 0.3617,
|
| 373 |
+
"step": 52
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 2.1414141414141414,
|
| 377 |
+
"grad_norm": 0.4406426250934601,
|
| 378 |
+
"learning_rate": 2.0215034775378336e-06,
|
| 379 |
+
"loss": 0.3975,
|
| 380 |
+
"step": 53
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 2.1818181818181817,
|
| 384 |
+
"grad_norm": 0.4345356822013855,
|
| 385 |
+
"learning_rate": 1.8280335791817733e-06,
|
| 386 |
+
"loss": 0.3506,
|
| 387 |
+
"step": 54
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 2.2222222222222223,
|
| 391 |
+
"grad_norm": 0.45012521743774414,
|
| 392 |
+
"learning_rate": 1.642205225764908e-06,
|
| 393 |
+
"loss": 0.3519,
|
| 394 |
+
"step": 55
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 2.2626262626262625,
|
| 398 |
+
"grad_norm": 0.43018749356269836,
|
| 399 |
+
"learning_rate": 1.4644660940672628e-06,
|
| 400 |
+
"loss": 0.3426,
|
| 401 |
+
"step": 56
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 2.303030303030303,
|
| 405 |
+
"grad_norm": 0.4245786666870117,
|
| 406 |
+
"learning_rate": 1.2952443732252058e-06,
|
| 407 |
+
"loss": 0.3566,
|
| 408 |
+
"step": 57
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 2.3434343434343434,
|
| 412 |
+
"grad_norm": 0.44446811079978943,
|
| 413 |
+
"learning_rate": 1.134947733186315e-06,
|
| 414 |
+
"loss": 0.3737,
|
| 415 |
+
"step": 58
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 2.3838383838383836,
|
| 419 |
+
"grad_norm": 0.45123612880706787,
|
| 420 |
+
"learning_rate": 9.83962342596776e-07,
|
| 421 |
+
"loss": 0.3814,
|
| 422 |
+
"step": 59
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 2.4242424242424243,
|
| 426 |
+
"grad_norm": 0.4223995506763458,
|
| 427 |
+
"learning_rate": 8.426519384872733e-07,
|
| 428 |
+
"loss": 0.3604,
|
| 429 |
+
"step": 60
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 2.4646464646464645,
|
| 433 |
+
"grad_norm": 0.4496898949146271,
|
| 434 |
+
"learning_rate": 7.113569499986401e-07,
|
| 435 |
+
"loss": 0.3379,
|
| 436 |
+
"step": 61
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 2.505050505050505,
|
| 440 |
+
"grad_norm": 0.45103389024734497,
|
| 441 |
+
"learning_rate": 5.903936782582253e-07,
|
| 442 |
+
"loss": 0.3728,
|
| 443 |
+
"step": 62
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 2.5454545454545454,
|
| 447 |
+
"grad_norm": 0.46011683344841003,
|
| 448 |
+
"learning_rate": 4.800535343827834e-07,
|
| 449 |
+
"loss": 0.3624,
|
| 450 |
+
"step": 63
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 2.5858585858585856,
|
| 454 |
+
"grad_norm": 0.4292215406894684,
|
| 455 |
+
"learning_rate": 3.8060233744356634e-07,
|
| 456 |
+
"loss": 0.3703,
|
| 457 |
+
"step": 64
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 2.6262626262626263,
|
| 461 |
+
"grad_norm": 0.4275359809398651,
|
| 462 |
+
"learning_rate": 2.9227967408489653e-07,
|
| 463 |
+
"loss": 0.3596,
|
| 464 |
+
"step": 65
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 2.6666666666666665,
|
| 468 |
+
"grad_norm": 0.41896435618400574,
|
| 469 |
+
"learning_rate": 2.152983213389559e-07,
|
| 470 |
+
"loss": 0.3647,
|
| 471 |
+
"step": 66
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 2.707070707070707,
|
| 475 |
+
"grad_norm": 0.4374232292175293,
|
| 476 |
+
"learning_rate": 1.4984373402728014e-07,
|
| 477 |
+
"loss": 0.3672,
|
| 478 |
+
"step": 67
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 2.7474747474747474,
|
| 482 |
+
"grad_norm": 0.4519655704498291,
|
| 483 |
+
"learning_rate": 9.607359798384785e-08,
|
| 484 |
+
"loss": 0.3811,
|
| 485 |
+
"step": 68
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 2.787878787878788,
|
| 489 |
+
"grad_norm": 0.4365183711051941,
|
| 490 |
+
"learning_rate": 5.411745017609493e-08,
|
| 491 |
+
"loss": 0.3629,
|
| 492 |
+
"step": 69
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 2.8282828282828283,
|
| 496 |
+
"grad_norm": 0.4325156807899475,
|
| 497 |
+
"learning_rate": 2.4076366639015914e-08,
|
| 498 |
+
"loss": 0.3517,
|
| 499 |
+
"step": 70
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 2.8686868686868685,
|
| 503 |
+
"grad_norm": 0.4426824748516083,
|
| 504 |
+
"learning_rate": 6.022718974137976e-09,
|
| 505 |
+
"loss": 0.3676,
|
| 506 |
+
"step": 71
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 2.909090909090909,
|
| 510 |
+
"grad_norm": 0.5022251605987549,
|
| 511 |
+
"learning_rate": 0.0,
|
| 512 |
+
"loss": 0.3794,
|
| 513 |
+
"step": 72
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 2.909090909090909,
|
| 517 |
+
"step": 72,
|
| 518 |
+
"total_flos": 3.5981250321711104e+16,
|
| 519 |
+
"train_loss": 0.4774101939466264,
|
| 520 |
+
"train_runtime": 9083.6349,
|
| 521 |
+
"train_samples_per_second": 0.392,
|
| 522 |
+
"train_steps_per_second": 0.008
|
| 523 |
+
}
|
| 524 |
+
],
|
| 525 |
+
"logging_steps": 1,
|
| 526 |
+
"max_steps": 72,
|
| 527 |
+
"num_input_tokens_seen": 0,
|
| 528 |
+
"num_train_epochs": 3,
|
| 529 |
+
"save_steps": 200,
|
| 530 |
+
"stateful_callbacks": {
|
| 531 |
+
"TrainerControl": {
|
| 532 |
+
"args": {
|
| 533 |
+
"should_epoch_stop": false,
|
| 534 |
+
"should_evaluate": false,
|
| 535 |
+
"should_log": false,
|
| 536 |
+
"should_save": true,
|
| 537 |
+
"should_training_stop": true
|
| 538 |
+
},
|
| 539 |
+
"attributes": {}
|
| 540 |
+
}
|
| 541 |
+
},
|
| 542 |
+
"total_flos": 3.5981250321711104e+16,
|
| 543 |
+
"train_batch_size": 1,
|
| 544 |
+
"trial_name": null,
|
| 545 |
+
"trial_params": null
|
| 546 |
+
}
|
training_loss.png
ADDED
|