End of training
Browse files- README.md +2 -1
- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +525 -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: 3k_globalbatchsize128_lr2e5_epochs3
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# 3k_globalbatchsize128_lr2e5_epochs3
|
| 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: 3k_globalbatchsize128_lr2e5_epochs3
|
|
|
|
| 16 |
|
| 17 |
# 3k_globalbatchsize128_lr2e5_epochs3
|
| 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/openthoughts_3000 dataset.
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.9546666666666668,
|
| 3 |
+
"total_flos": 1.8368167563545805e+17,
|
| 4 |
+
"train_loss": 0.5622327051300934,
|
| 5 |
+
"train_runtime": 9047.4576,
|
| 6 |
+
"train_samples_per_second": 0.994,
|
| 7 |
+
"train_steps_per_second": 0.008
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.9546666666666668,
|
| 3 |
+
"total_flos": 1.8368167563545805e+17,
|
| 4 |
+
"train_loss": 0.5622327051300934,
|
| 5 |
+
"train_runtime": 9047.4576,
|
| 6 |
+
"train_samples_per_second": 0.994,
|
| 7 |
+
"train_steps_per_second": 0.008
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,525 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.9546666666666668,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 69,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.042666666666666665,
|
| 13 |
+
"grad_norm": 5.959728345663076,
|
| 14 |
+
"learning_rate": 2.8571428571428573e-06,
|
| 15 |
+
"loss": 0.8546,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.08533333333333333,
|
| 20 |
+
"grad_norm": 6.094613172565375,
|
| 21 |
+
"learning_rate": 5.7142857142857145e-06,
|
| 22 |
+
"loss": 0.8868,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.128,
|
| 27 |
+
"grad_norm": 5.386341750579915,
|
| 28 |
+
"learning_rate": 8.571428571428571e-06,
|
| 29 |
+
"loss": 0.832,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.17066666666666666,
|
| 34 |
+
"grad_norm": 2.5797511388626746,
|
| 35 |
+
"learning_rate": 1.1428571428571429e-05,
|
| 36 |
+
"loss": 0.7985,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.21333333333333335,
|
| 41 |
+
"grad_norm": 3.779386282818932,
|
| 42 |
+
"learning_rate": 1.4285714285714287e-05,
|
| 43 |
+
"loss": 0.7783,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.256,
|
| 48 |
+
"grad_norm": 4.229706702803126,
|
| 49 |
+
"learning_rate": 1.7142857142857142e-05,
|
| 50 |
+
"loss": 0.7815,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.2986666666666667,
|
| 55 |
+
"grad_norm": 4.617508058304087,
|
| 56 |
+
"learning_rate": 2e-05,
|
| 57 |
+
"loss": 0.7589,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.3413333333333333,
|
| 62 |
+
"grad_norm": 2.8605623999583067,
|
| 63 |
+
"learning_rate": 1.998716507171053e-05,
|
| 64 |
+
"loss": 0.7121,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.384,
|
| 69 |
+
"grad_norm": 2.8915143875516227,
|
| 70 |
+
"learning_rate": 1.994869323391895e-05,
|
| 71 |
+
"loss": 0.7246,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.4266666666666667,
|
| 76 |
+
"grad_norm": 2.1151893328356457,
|
| 77 |
+
"learning_rate": 1.9884683243281117e-05,
|
| 78 |
+
"loss": 0.6802,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.4693333333333333,
|
| 83 |
+
"grad_norm": 1.3469196763058695,
|
| 84 |
+
"learning_rate": 1.9795299412524948e-05,
|
| 85 |
+
"loss": 0.649,
|
| 86 |
+
"step": 11
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.512,
|
| 90 |
+
"grad_norm": 1.281775936596799,
|
| 91 |
+
"learning_rate": 1.9680771188662044e-05,
|
| 92 |
+
"loss": 0.6418,
|
| 93 |
+
"step": 12
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.5546666666666666,
|
| 97 |
+
"grad_norm": 1.0850775880881365,
|
| 98 |
+
"learning_rate": 1.954139256400049e-05,
|
| 99 |
+
"loss": 0.615,
|
| 100 |
+
"step": 13
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.5973333333333334,
|
| 104 |
+
"grad_norm": 0.8195762946099127,
|
| 105 |
+
"learning_rate": 1.9377521321470806e-05,
|
| 106 |
+
"loss": 0.602,
|
| 107 |
+
"step": 14
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.64,
|
| 111 |
+
"grad_norm": 0.8606474232660462,
|
| 112 |
+
"learning_rate": 1.918957811620231e-05,
|
| 113 |
+
"loss": 0.5955,
|
| 114 |
+
"step": 15
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.6826666666666666,
|
| 118 |
+
"grad_norm": 0.6863293915797495,
|
| 119 |
+
"learning_rate": 1.897804539570742e-05,
|
| 120 |
+
"loss": 0.5931,
|
| 121 |
+
"step": 16
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.7253333333333334,
|
| 125 |
+
"grad_norm": 0.7127857574760672,
|
| 126 |
+
"learning_rate": 1.8743466161445823e-05,
|
| 127 |
+
"loss": 0.5931,
|
| 128 |
+
"step": 17
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.768,
|
| 132 |
+
"grad_norm": 0.6761402123068821,
|
| 133 |
+
"learning_rate": 1.848644257494751e-05,
|
| 134 |
+
"loss": 0.6253,
|
| 135 |
+
"step": 18
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.8106666666666666,
|
| 139 |
+
"grad_norm": 0.6908240602604472,
|
| 140 |
+
"learning_rate": 1.8207634412072765e-05,
|
| 141 |
+
"loss": 0.5733,
|
| 142 |
+
"step": 19
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.8533333333333334,
|
| 146 |
+
"grad_norm": 0.5975435355673366,
|
| 147 |
+
"learning_rate": 1.7907757369376984e-05,
|
| 148 |
+
"loss": 0.6043,
|
| 149 |
+
"step": 20
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.896,
|
| 153 |
+
"grad_norm": 0.6552793881271102,
|
| 154 |
+
"learning_rate": 1.758758122692791e-05,
|
| 155 |
+
"loss": 0.5973,
|
| 156 |
+
"step": 21
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.9386666666666666,
|
| 160 |
+
"grad_norm": 0.7611523739276765,
|
| 161 |
+
"learning_rate": 1.72479278722912e-05,
|
| 162 |
+
"loss": 0.5591,
|
| 163 |
+
"step": 22
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.9813333333333333,
|
| 167 |
+
"grad_norm": 0.6508644582109435,
|
| 168 |
+
"learning_rate": 1.688966919075687e-05,
|
| 169 |
+
"loss": 0.5855,
|
| 170 |
+
"step": 23
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 1.0293333333333334,
|
| 174 |
+
"grad_norm": 1.4185151217030356,
|
| 175 |
+
"learning_rate": 1.6513724827222225e-05,
|
| 176 |
+
"loss": 0.9357,
|
| 177 |
+
"step": 24
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 1.072,
|
| 181 |
+
"grad_norm": 0.5452898243798924,
|
| 182 |
+
"learning_rate": 1.612105982547663e-05,
|
| 183 |
+
"loss": 0.5117,
|
| 184 |
+
"step": 25
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 1.1146666666666667,
|
| 188 |
+
"grad_norm": 0.6944885284299619,
|
| 189 |
+
"learning_rate": 1.5712682150947926e-05,
|
| 190 |
+
"loss": 0.5366,
|
| 191 |
+
"step": 26
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 1.1573333333333333,
|
| 195 |
+
"grad_norm": 0.783190829130972,
|
| 196 |
+
"learning_rate": 1.5289640103269626e-05,
|
| 197 |
+
"loss": 0.5493,
|
| 198 |
+
"step": 27
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 1.2,
|
| 202 |
+
"grad_norm": 0.6776819900072719,
|
| 203 |
+
"learning_rate": 1.4853019625310813e-05,
|
| 204 |
+
"loss": 0.5365,
|
| 205 |
+
"step": 28
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 1.2426666666666666,
|
| 209 |
+
"grad_norm": 0.7900333868686757,
|
| 210 |
+
"learning_rate": 1.4403941515576344e-05,
|
| 211 |
+
"loss": 0.51,
|
| 212 |
+
"step": 29
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 1.2853333333333334,
|
| 216 |
+
"grad_norm": 0.5665470546997332,
|
| 217 |
+
"learning_rate": 1.3943558551133186e-05,
|
| 218 |
+
"loss": 0.4923,
|
| 219 |
+
"step": 30
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 1.328,
|
| 223 |
+
"grad_norm": 0.7357023227151142,
|
| 224 |
+
"learning_rate": 1.3473052528448203e-05,
|
| 225 |
+
"loss": 0.5626,
|
| 226 |
+
"step": 31
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 1.3706666666666667,
|
| 230 |
+
"grad_norm": 0.7181139107624689,
|
| 231 |
+
"learning_rate": 1.2993631229733584e-05,
|
| 232 |
+
"loss": 0.5226,
|
| 233 |
+
"step": 32
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 1.4133333333333333,
|
| 237 |
+
"grad_norm": 0.6093315557894886,
|
| 238 |
+
"learning_rate": 1.2506525322587207e-05,
|
| 239 |
+
"loss": 0.4995,
|
| 240 |
+
"step": 33
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 1.456,
|
| 244 |
+
"grad_norm": 0.5340833598913288,
|
| 245 |
+
"learning_rate": 1.2012985200886602e-05,
|
| 246 |
+
"loss": 0.4901,
|
| 247 |
+
"step": 34
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 1.4986666666666666,
|
| 251 |
+
"grad_norm": 0.6143559874227241,
|
| 252 |
+
"learning_rate": 1.1514277775045768e-05,
|
| 253 |
+
"loss": 0.5237,
|
| 254 |
+
"step": 35
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 1.5413333333333332,
|
| 258 |
+
"grad_norm": 0.507660612192559,
|
| 259 |
+
"learning_rate": 1.1011683219874324e-05,
|
| 260 |
+
"loss": 0.4985,
|
| 261 |
+
"step": 36
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 1.584,
|
| 265 |
+
"grad_norm": 0.6308358642347149,
|
| 266 |
+
"learning_rate": 1.0506491688387128e-05,
|
| 267 |
+
"loss": 0.5597,
|
| 268 |
+
"step": 37
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 1.6266666666666667,
|
| 272 |
+
"grad_norm": 0.40611142763475594,
|
| 273 |
+
"learning_rate": 1e-05,
|
| 274 |
+
"loss": 0.4834,
|
| 275 |
+
"step": 38
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 1.6693333333333333,
|
| 279 |
+
"grad_norm": 0.555694918110193,
|
| 280 |
+
"learning_rate": 9.493508311612874e-06,
|
| 281 |
+
"loss": 0.5282,
|
| 282 |
+
"step": 39
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 1.712,
|
| 286 |
+
"grad_norm": 0.4782914827020497,
|
| 287 |
+
"learning_rate": 8.98831678012568e-06,
|
| 288 |
+
"loss": 0.5029,
|
| 289 |
+
"step": 40
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 1.7546666666666666,
|
| 293 |
+
"grad_norm": 0.40447180311906644,
|
| 294 |
+
"learning_rate": 8.485722224954237e-06,
|
| 295 |
+
"loss": 0.5287,
|
| 296 |
+
"step": 41
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 1.7973333333333334,
|
| 300 |
+
"grad_norm": 0.4516541829796801,
|
| 301 |
+
"learning_rate": 7.987014799113398e-06,
|
| 302 |
+
"loss": 0.5072,
|
| 303 |
+
"step": 42
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 1.8399999999999999,
|
| 307 |
+
"grad_norm": 0.37653071625781426,
|
| 308 |
+
"learning_rate": 7.493474677412795e-06,
|
| 309 |
+
"loss": 0.4584,
|
| 310 |
+
"step": 43
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 1.8826666666666667,
|
| 314 |
+
"grad_norm": 0.3984563912306908,
|
| 315 |
+
"learning_rate": 7.006368770266421e-06,
|
| 316 |
+
"loss": 0.5267,
|
| 317 |
+
"step": 44
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 1.9253333333333333,
|
| 321 |
+
"grad_norm": 0.38863265116874834,
|
| 322 |
+
"learning_rate": 6.526947471551799e-06,
|
| 323 |
+
"loss": 0.4965,
|
| 324 |
+
"step": 45
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 1.968,
|
| 328 |
+
"grad_norm": 0.39995047568592906,
|
| 329 |
+
"learning_rate": 6.056441448866817e-06,
|
| 330 |
+
"loss": 0.4757,
|
| 331 |
+
"step": 46
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 2.016,
|
| 335 |
+
"grad_norm": 0.6674558520856042,
|
| 336 |
+
"learning_rate": 5.5960584844236565e-06,
|
| 337 |
+
"loss": 0.7987,
|
| 338 |
+
"step": 47
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 2.058666666666667,
|
| 342 |
+
"grad_norm": 0.3698994867240691,
|
| 343 |
+
"learning_rate": 5.146980374689192e-06,
|
| 344 |
+
"loss": 0.4257,
|
| 345 |
+
"step": 48
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 2.1013333333333333,
|
| 349 |
+
"grad_norm": 0.43400395036861983,
|
| 350 |
+
"learning_rate": 4.710359896730379e-06,
|
| 351 |
+
"loss": 0.4947,
|
| 352 |
+
"step": 49
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 2.144,
|
| 356 |
+
"grad_norm": 0.4005441898018298,
|
| 357 |
+
"learning_rate": 4.287317849052075e-06,
|
| 358 |
+
"loss": 0.4512,
|
| 359 |
+
"step": 50
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 2.1866666666666665,
|
| 363 |
+
"grad_norm": 0.40707949452679015,
|
| 364 |
+
"learning_rate": 3.878940174523371e-06,
|
| 365 |
+
"loss": 0.533,
|
| 366 |
+
"step": 51
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 2.2293333333333334,
|
| 370 |
+
"grad_norm": 0.3605166200767298,
|
| 371 |
+
"learning_rate": 3.48627517277778e-06,
|
| 372 |
+
"loss": 0.4365,
|
| 373 |
+
"step": 52
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 2.2720000000000002,
|
| 377 |
+
"grad_norm": 0.3793619736022353,
|
| 378 |
+
"learning_rate": 3.110330809243134e-06,
|
| 379 |
+
"loss": 0.4743,
|
| 380 |
+
"step": 53
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 2.3146666666666667,
|
| 384 |
+
"grad_norm": 0.36583057188811624,
|
| 385 |
+
"learning_rate": 2.7520721277088023e-06,
|
| 386 |
+
"loss": 0.4635,
|
| 387 |
+
"step": 54
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 2.3573333333333335,
|
| 391 |
+
"grad_norm": 0.39070534110508154,
|
| 392 |
+
"learning_rate": 2.4124187730720916e-06,
|
| 393 |
+
"loss": 0.468,
|
| 394 |
+
"step": 55
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 2.4,
|
| 398 |
+
"grad_norm": 0.4033662541656621,
|
| 399 |
+
"learning_rate": 2.092242630623016e-06,
|
| 400 |
+
"loss": 0.4704,
|
| 401 |
+
"step": 56
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 2.4426666666666668,
|
| 405 |
+
"grad_norm": 0.323553634819707,
|
| 406 |
+
"learning_rate": 1.7923655879272395e-06,
|
| 407 |
+
"loss": 0.4326,
|
| 408 |
+
"step": 57
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 2.485333333333333,
|
| 412 |
+
"grad_norm": 0.3020317061209811,
|
| 413 |
+
"learning_rate": 1.5135574250524898e-06,
|
| 414 |
+
"loss": 0.4623,
|
| 415 |
+
"step": 58
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 2.528,
|
| 419 |
+
"grad_norm": 0.2918391492968299,
|
| 420 |
+
"learning_rate": 1.2565338385541792e-06,
|
| 421 |
+
"loss": 0.4694,
|
| 422 |
+
"step": 59
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 2.570666666666667,
|
| 426 |
+
"grad_norm": 0.28335286446618535,
|
| 427 |
+
"learning_rate": 1.0219546042925842e-06,
|
| 428 |
+
"loss": 0.4282,
|
| 429 |
+
"step": 60
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 2.6133333333333333,
|
| 433 |
+
"grad_norm": 0.2948398534467495,
|
| 434 |
+
"learning_rate": 8.10421883797694e-07,
|
| 435 |
+
"loss": 0.4456,
|
| 436 |
+
"step": 61
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 2.656,
|
| 440 |
+
"grad_norm": 0.2870039768314063,
|
| 441 |
+
"learning_rate": 6.22478678529197e-07,
|
| 442 |
+
"loss": 0.4457,
|
| 443 |
+
"step": 62
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 2.6986666666666665,
|
| 447 |
+
"grad_norm": 0.2835603884217034,
|
| 448 |
+
"learning_rate": 4.5860743599951186e-07,
|
| 449 |
+
"loss": 0.4228,
|
| 450 |
+
"step": 63
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 2.7413333333333334,
|
| 454 |
+
"grad_norm": 0.32534507708819593,
|
| 455 |
+
"learning_rate": 3.1922881133795827e-07,
|
| 456 |
+
"loss": 0.5117,
|
| 457 |
+
"step": 64
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 2.784,
|
| 461 |
+
"grad_norm": 0.254851146211296,
|
| 462 |
+
"learning_rate": 2.0470058747505516e-07,
|
| 463 |
+
"loss": 0.3893,
|
| 464 |
+
"step": 65
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 2.8266666666666667,
|
| 468 |
+
"grad_norm": 0.299877118299828,
|
| 469 |
+
"learning_rate": 1.1531675671888621e-07,
|
| 470 |
+
"loss": 0.492,
|
| 471 |
+
"step": 66
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 2.8693333333333335,
|
| 475 |
+
"grad_norm": 0.29694063668641374,
|
| 476 |
+
"learning_rate": 5.1306766081048456e-08,
|
| 477 |
+
"loss": 0.4389,
|
| 478 |
+
"step": 67
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 2.912,
|
| 482 |
+
"grad_norm": 0.27153960798477816,
|
| 483 |
+
"learning_rate": 1.2834928289472415e-08,
|
| 484 |
+
"loss": 0.4697,
|
| 485 |
+
"step": 68
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 2.9546666666666668,
|
| 489 |
+
"grad_norm": 0.30779957596150975,
|
| 490 |
+
"learning_rate": 0.0,
|
| 491 |
+
"loss": 0.4917,
|
| 492 |
+
"step": 69
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 2.9546666666666668,
|
| 496 |
+
"step": 69,
|
| 497 |
+
"total_flos": 1.8368167563545805e+17,
|
| 498 |
+
"train_loss": 0.5622327051300934,
|
| 499 |
+
"train_runtime": 9047.4576,
|
| 500 |
+
"train_samples_per_second": 0.994,
|
| 501 |
+
"train_steps_per_second": 0.008
|
| 502 |
+
}
|
| 503 |
+
],
|
| 504 |
+
"logging_steps": 1.0,
|
| 505 |
+
"max_steps": 69,
|
| 506 |
+
"num_input_tokens_seen": 0,
|
| 507 |
+
"num_train_epochs": 3,
|
| 508 |
+
"save_steps": 500,
|
| 509 |
+
"stateful_callbacks": {
|
| 510 |
+
"TrainerControl": {
|
| 511 |
+
"args": {
|
| 512 |
+
"should_epoch_stop": false,
|
| 513 |
+
"should_evaluate": false,
|
| 514 |
+
"should_log": false,
|
| 515 |
+
"should_save": true,
|
| 516 |
+
"should_training_stop": true
|
| 517 |
+
},
|
| 518 |
+
"attributes": {}
|
| 519 |
+
}
|
| 520 |
+
},
|
| 521 |
+
"total_flos": 1.8368167563545805e+17,
|
| 522 |
+
"train_batch_size": 1,
|
| 523 |
+
"trial_name": null,
|
| 524 |
+
"trial_params": null
|
| 525 |
+
}
|
training_loss.png
ADDED
|