End of training
Browse files- README.md +2 -1
- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +427 -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: 316_globalbatchsize64_lr1e5_epochs11
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# 316_globalbatchsize64_lr1e5_epochs11
|
| 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: 316_globalbatchsize64_lr1e5_epochs11
|
|
|
|
| 16 |
|
| 17 |
# 316_globalbatchsize64_lr1e5_epochs11
|
| 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_316 dataset.
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 11.0,
|
| 3 |
+
"total_flos": 7.2096946944213e+16,
|
| 4 |
+
"train_loss": 0.5119519038633866,
|
| 5 |
+
"train_runtime": 4574.7649,
|
| 6 |
+
"train_samples_per_second": 0.76,
|
| 7 |
+
"train_steps_per_second": 0.012
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 11.0,
|
| 3 |
+
"total_flos": 7.2096946944213e+16,
|
| 4 |
+
"train_loss": 0.5119519038633866,
|
| 5 |
+
"train_runtime": 4574.7649,
|
| 6 |
+
"train_samples_per_second": 0.76,
|
| 7 |
+
"train_steps_per_second": 0.012
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,427 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 11.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 55,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.2,
|
| 13 |
+
"grad_norm": 5.58191849443318,
|
| 14 |
+
"learning_rate": 1.6666666666666667e-06,
|
| 15 |
+
"loss": 0.832,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.4,
|
| 20 |
+
"grad_norm": 6.007948512959091,
|
| 21 |
+
"learning_rate": 3.3333333333333333e-06,
|
| 22 |
+
"loss": 0.8909,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.6,
|
| 27 |
+
"grad_norm": 6.0255585610086735,
|
| 28 |
+
"learning_rate": 5e-06,
|
| 29 |
+
"loss": 0.9081,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.8,
|
| 34 |
+
"grad_norm": 4.644075351255504,
|
| 35 |
+
"learning_rate": 6.666666666666667e-06,
|
| 36 |
+
"loss": 0.8743,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 1.0,
|
| 41 |
+
"grad_norm": 2.3038887112593174,
|
| 42 |
+
"learning_rate": 8.333333333333334e-06,
|
| 43 |
+
"loss": 0.786,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 1.2,
|
| 48 |
+
"grad_norm": 3.650329710982678,
|
| 49 |
+
"learning_rate": 1e-05,
|
| 50 |
+
"loss": 0.7736,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 1.4,
|
| 55 |
+
"grad_norm": 4.205154823404291,
|
| 56 |
+
"learning_rate": 9.989726963751683e-06,
|
| 57 |
+
"loss": 0.8117,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 1.6,
|
| 62 |
+
"grad_norm": 3.911828128691874,
|
| 63 |
+
"learning_rate": 9.95895006911623e-06,
|
| 64 |
+
"loss": 0.7514,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 1.8,
|
| 69 |
+
"grad_norm": 4.214024990796431,
|
| 70 |
+
"learning_rate": 9.907795784955327e-06,
|
| 71 |
+
"loss": 0.7586,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 2.0,
|
| 76 |
+
"grad_norm": 2.7698062964200068,
|
| 77 |
+
"learning_rate": 9.836474315195148e-06,
|
| 78 |
+
"loss": 0.7152,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 2.2,
|
| 83 |
+
"grad_norm": 1.8116452493978696,
|
| 84 |
+
"learning_rate": 9.745278735053345e-06,
|
| 85 |
+
"loss": 0.704,
|
| 86 |
+
"step": 11
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 2.4,
|
| 90 |
+
"grad_norm": 1.8985512249239473,
|
| 91 |
+
"learning_rate": 9.63458378673011e-06,
|
| 92 |
+
"loss": 0.6505,
|
| 93 |
+
"step": 12
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 2.6,
|
| 97 |
+
"grad_norm": 1.4773868938287453,
|
| 98 |
+
"learning_rate": 9.504844339512096e-06,
|
| 99 |
+
"loss": 0.6324,
|
| 100 |
+
"step": 13
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 2.8,
|
| 104 |
+
"grad_norm": 1.4266759505360602,
|
| 105 |
+
"learning_rate": 9.356593520616948e-06,
|
| 106 |
+
"loss": 0.6565,
|
| 107 |
+
"step": 14
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 3.0,
|
| 111 |
+
"grad_norm": 1.0611745837489175,
|
| 112 |
+
"learning_rate": 9.190440524459203e-06,
|
| 113 |
+
"loss": 0.6319,
|
| 114 |
+
"step": 15
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 3.2,
|
| 118 |
+
"grad_norm": 1.055849673211094,
|
| 119 |
+
"learning_rate": 9.007068109339783e-06,
|
| 120 |
+
"loss": 0.5656,
|
| 121 |
+
"step": 16
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 3.4,
|
| 125 |
+
"grad_norm": 0.9855784963514713,
|
| 126 |
+
"learning_rate": 8.807229791845673e-06,
|
| 127 |
+
"loss": 0.6401,
|
| 128 |
+
"step": 17
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 3.6,
|
| 132 |
+
"grad_norm": 0.7932227090477307,
|
| 133 |
+
"learning_rate": 8.591746750488639e-06,
|
| 134 |
+
"loss": 0.5781,
|
| 135 |
+
"step": 18
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 3.8,
|
| 139 |
+
"grad_norm": 0.830586979303682,
|
| 140 |
+
"learning_rate": 8.361504451306585e-06,
|
| 141 |
+
"loss": 0.5785,
|
| 142 |
+
"step": 19
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 4.0,
|
| 146 |
+
"grad_norm": 0.7067580011380711,
|
| 147 |
+
"learning_rate": 8.117449009293668e-06,
|
| 148 |
+
"loss": 0.5093,
|
| 149 |
+
"step": 20
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 4.2,
|
| 153 |
+
"grad_norm": 0.6788679779875981,
|
| 154 |
+
"learning_rate": 7.860583300610849e-06,
|
| 155 |
+
"loss": 0.5455,
|
| 156 |
+
"step": 21
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 4.4,
|
| 160 |
+
"grad_norm": 0.718594983442148,
|
| 161 |
+
"learning_rate": 7.591962841552627e-06,
|
| 162 |
+
"loss": 0.4969,
|
| 163 |
+
"step": 22
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 4.6,
|
| 167 |
+
"grad_norm": 0.6792524185531629,
|
| 168 |
+
"learning_rate": 7.312691451204178e-06,
|
| 169 |
+
"loss": 0.505,
|
| 170 |
+
"step": 23
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 4.8,
|
| 174 |
+
"grad_norm": 0.624121428175489,
|
| 175 |
+
"learning_rate": 7.023916715611969e-06,
|
| 176 |
+
"loss": 0.5118,
|
| 177 |
+
"step": 24
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 5.0,
|
| 181 |
+
"grad_norm": 0.5866679034879868,
|
| 182 |
+
"learning_rate": 6.726825272106539e-06,
|
| 183 |
+
"loss": 0.4977,
|
| 184 |
+
"step": 25
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 5.2,
|
| 188 |
+
"grad_norm": 0.6541053139221744,
|
| 189 |
+
"learning_rate": 6.4226379331551625e-06,
|
| 190 |
+
"loss": 0.5107,
|
| 191 |
+
"step": 26
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 5.4,
|
| 195 |
+
"grad_norm": 0.6179729762263901,
|
| 196 |
+
"learning_rate": 6.112604669781572e-06,
|
| 197 |
+
"loss": 0.4753,
|
| 198 |
+
"step": 27
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 5.6,
|
| 202 |
+
"grad_norm": 0.5110907906450618,
|
| 203 |
+
"learning_rate": 5.797999475166897e-06,
|
| 204 |
+
"loss": 0.464,
|
| 205 |
+
"step": 28
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 5.8,
|
| 209 |
+
"grad_norm": 0.5916016788987642,
|
| 210 |
+
"learning_rate": 5.480115129538409e-06,
|
| 211 |
+
"loss": 0.4265,
|
| 212 |
+
"step": 29
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 6.0,
|
| 216 |
+
"grad_norm": 0.6131427148946387,
|
| 217 |
+
"learning_rate": 5.160257887858278e-06,
|
| 218 |
+
"loss": 0.4162,
|
| 219 |
+
"step": 30
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 6.2,
|
| 223 |
+
"grad_norm": 0.5923194910882649,
|
| 224 |
+
"learning_rate": 4.839742112141725e-06,
|
| 225 |
+
"loss": 0.4364,
|
| 226 |
+
"step": 31
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 6.4,
|
| 230 |
+
"grad_norm": 0.4934222921527663,
|
| 231 |
+
"learning_rate": 4.5198848704615915e-06,
|
| 232 |
+
"loss": 0.4143,
|
| 233 |
+
"step": 32
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 6.6,
|
| 237 |
+
"grad_norm": 0.46501676824156285,
|
| 238 |
+
"learning_rate": 4.2020005248331056e-06,
|
| 239 |
+
"loss": 0.398,
|
| 240 |
+
"step": 33
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 6.8,
|
| 244 |
+
"grad_norm": 0.4758685754011838,
|
| 245 |
+
"learning_rate": 3.887395330218429e-06,
|
| 246 |
+
"loss": 0.421,
|
| 247 |
+
"step": 34
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 7.0,
|
| 251 |
+
"grad_norm": 0.41565545297424444,
|
| 252 |
+
"learning_rate": 3.5773620668448384e-06,
|
| 253 |
+
"loss": 0.3872,
|
| 254 |
+
"step": 35
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 7.2,
|
| 258 |
+
"grad_norm": 0.44031956045158555,
|
| 259 |
+
"learning_rate": 3.273174727893463e-06,
|
| 260 |
+
"loss": 0.3793,
|
| 261 |
+
"step": 36
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 7.4,
|
| 265 |
+
"grad_norm": 0.40056453890873994,
|
| 266 |
+
"learning_rate": 2.976083284388031e-06,
|
| 267 |
+
"loss": 0.3972,
|
| 268 |
+
"step": 37
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 7.6,
|
| 272 |
+
"grad_norm": 0.3939615232231488,
|
| 273 |
+
"learning_rate": 2.687308548795825e-06,
|
| 274 |
+
"loss": 0.3577,
|
| 275 |
+
"step": 38
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 7.8,
|
| 279 |
+
"grad_norm": 0.40540452178576725,
|
| 280 |
+
"learning_rate": 2.408037158447375e-06,
|
| 281 |
+
"loss": 0.3726,
|
| 282 |
+
"step": 39
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 8.0,
|
| 286 |
+
"grad_norm": 0.3699910313670184,
|
| 287 |
+
"learning_rate": 2.139416699389153e-06,
|
| 288 |
+
"loss": 0.3728,
|
| 289 |
+
"step": 40
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 8.2,
|
| 293 |
+
"grad_norm": 0.3820504670511669,
|
| 294 |
+
"learning_rate": 1.8825509907063328e-06,
|
| 295 |
+
"loss": 0.3232,
|
| 296 |
+
"step": 41
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 8.4,
|
| 300 |
+
"grad_norm": 0.365388314632681,
|
| 301 |
+
"learning_rate": 1.6384955486934157e-06,
|
| 302 |
+
"loss": 0.3751,
|
| 303 |
+
"step": 42
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 8.6,
|
| 307 |
+
"grad_norm": 0.38734756199047365,
|
| 308 |
+
"learning_rate": 1.4082532495113627e-06,
|
| 309 |
+
"loss": 0.3527,
|
| 310 |
+
"step": 43
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 8.8,
|
| 314 |
+
"grad_norm": 0.38621310947270643,
|
| 315 |
+
"learning_rate": 1.1927702081543279e-06,
|
| 316 |
+
"loss": 0.3582,
|
| 317 |
+
"step": 44
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 9.0,
|
| 321 |
+
"grad_norm": 0.38286731046607325,
|
| 322 |
+
"learning_rate": 9.929318906602176e-07,
|
| 323 |
+
"loss": 0.3585,
|
| 324 |
+
"step": 45
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 9.2,
|
| 328 |
+
"grad_norm": 0.3672592415291107,
|
| 329 |
+
"learning_rate": 8.095594755407971e-07,
|
| 330 |
+
"loss": 0.3448,
|
| 331 |
+
"step": 46
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 9.4,
|
| 335 |
+
"grad_norm": 0.35096100077575865,
|
| 336 |
+
"learning_rate": 6.43406479383053e-07,
|
| 337 |
+
"loss": 0.3245,
|
| 338 |
+
"step": 47
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 9.6,
|
| 342 |
+
"grad_norm": 0.3565018420303435,
|
| 343 |
+
"learning_rate": 4.951556604879049e-07,
|
| 344 |
+
"loss": 0.3354,
|
| 345 |
+
"step": 48
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 9.8,
|
| 349 |
+
"grad_norm": 0.3622219349004091,
|
| 350 |
+
"learning_rate": 3.6541621326989183e-07,
|
| 351 |
+
"loss": 0.3437,
|
| 352 |
+
"step": 49
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 10.0,
|
| 356 |
+
"grad_norm": 0.32738171468724364,
|
| 357 |
+
"learning_rate": 2.547212649466568e-07,
|
| 358 |
+
"loss": 0.3435,
|
| 359 |
+
"step": 50
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 10.2,
|
| 363 |
+
"grad_norm": 0.36495266048417707,
|
| 364 |
+
"learning_rate": 1.6352568480485277e-07,
|
| 365 |
+
"loss": 0.3301,
|
| 366 |
+
"step": 51
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 10.4,
|
| 370 |
+
"grad_norm": 0.3585813764442277,
|
| 371 |
+
"learning_rate": 9.22042150446728e-08,
|
| 372 |
+
"loss": 0.3517,
|
| 373 |
+
"step": 52
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 10.6,
|
| 377 |
+
"grad_norm": 0.35255968331342985,
|
| 378 |
+
"learning_rate": 4.104993088376974e-08,
|
| 379 |
+
"loss": 0.3478,
|
| 380 |
+
"step": 53
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 10.8,
|
| 384 |
+
"grad_norm": 0.345420004338979,
|
| 385 |
+
"learning_rate": 1.0273036248318325e-08,
|
| 386 |
+
"loss": 0.3138,
|
| 387 |
+
"step": 54
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 11.0,
|
| 391 |
+
"grad_norm": 0.3486318369230819,
|
| 392 |
+
"learning_rate": 0.0,
|
| 393 |
+
"loss": 0.3197,
|
| 394 |
+
"step": 55
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 11.0,
|
| 398 |
+
"step": 55,
|
| 399 |
+
"total_flos": 7.2096946944213e+16,
|
| 400 |
+
"train_loss": 0.5119519038633866,
|
| 401 |
+
"train_runtime": 4574.7649,
|
| 402 |
+
"train_samples_per_second": 0.76,
|
| 403 |
+
"train_steps_per_second": 0.012
|
| 404 |
+
}
|
| 405 |
+
],
|
| 406 |
+
"logging_steps": 1.0,
|
| 407 |
+
"max_steps": 55,
|
| 408 |
+
"num_input_tokens_seen": 0,
|
| 409 |
+
"num_train_epochs": 11,
|
| 410 |
+
"save_steps": 500,
|
| 411 |
+
"stateful_callbacks": {
|
| 412 |
+
"TrainerControl": {
|
| 413 |
+
"args": {
|
| 414 |
+
"should_epoch_stop": false,
|
| 415 |
+
"should_evaluate": false,
|
| 416 |
+
"should_log": false,
|
| 417 |
+
"should_save": true,
|
| 418 |
+
"should_training_stop": true
|
| 419 |
+
},
|
| 420 |
+
"attributes": {}
|
| 421 |
+
}
|
| 422 |
+
},
|
| 423 |
+
"total_flos": 7.2096946944213e+16,
|
| 424 |
+
"train_batch_size": 1,
|
| 425 |
+
"trial_name": null,
|
| 426 |
+
"trial_params": null
|
| 427 |
+
}
|
training_loss.png
ADDED
|