End of training
Browse files- README.md +3 -1
- trainer_state.json +328 -34
README.md
CHANGED
|
@@ -3,6 +3,8 @@ base_model: facebook/musicgen-melody
|
|
| 3 |
library_name: peft
|
| 4 |
license: cc-by-nc-4.0
|
| 5 |
tags:
|
|
|
|
|
|
|
| 6 |
- generated_from_trainer
|
| 7 |
model-index:
|
| 8 |
- name: musicgen-finetune-sanity-check
|
|
@@ -14,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 14 |
|
| 15 |
# musicgen-finetune-sanity-check
|
| 16 |
|
| 17 |
-
This model is a fine-tuned version of [facebook/musicgen-melody](https://huggingface.co/facebook/musicgen-melody) on
|
| 18 |
|
| 19 |
## Model description
|
| 20 |
|
|
|
|
| 3 |
library_name: peft
|
| 4 |
license: cc-by-nc-4.0
|
| 5 |
tags:
|
| 6 |
+
- text-to-audio
|
| 7 |
+
- tiny-punk
|
| 8 |
- generated_from_trainer
|
| 9 |
model-index:
|
| 10 |
- name: musicgen-finetune-sanity-check
|
|
|
|
| 16 |
|
| 17 |
# musicgen-finetune-sanity-check
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [facebook/musicgen-melody](https://huggingface.co/facebook/musicgen-melody) on the ylacombe/tiny-punk dataset.
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
trainer_state.json
CHANGED
|
@@ -1,67 +1,361 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 3.
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 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.
|
| 13 |
-
"grad_norm":
|
| 14 |
-
"learning_rate": 0.
|
| 15 |
-
"loss": 9.
|
| 16 |
"step": 2
|
| 17 |
},
|
| 18 |
{
|
| 19 |
-
"epoch":
|
| 20 |
-
"grad_norm":
|
| 21 |
-
"learning_rate": 0.
|
| 22 |
-
"loss":
|
| 23 |
"step": 4
|
| 24 |
},
|
| 25 |
{
|
| 26 |
-
"epoch":
|
| 27 |
-
"grad_norm":
|
| 28 |
-
"learning_rate": 0.
|
| 29 |
-
"loss": 8.
|
| 30 |
"step": 6
|
| 31 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 32 |
{
|
| 33 |
"epoch": 2.0,
|
| 34 |
-
"grad_norm": 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 35 |
"learning_rate": 6.666666666666667e-05,
|
| 36 |
-
"loss":
|
| 37 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 38 |
},
|
| 39 |
{
|
| 40 |
-
"epoch": 2.
|
| 41 |
-
"grad_norm":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 42 |
"learning_rate": 3.3333333333333335e-05,
|
| 43 |
-
"loss": 7.
|
| 44 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 45 |
},
|
| 46 |
{
|
| 47 |
-
"epoch": 3.
|
| 48 |
-
"grad_norm": 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 49 |
"learning_rate": 0.0,
|
| 50 |
-
"loss":
|
| 51 |
-
"step":
|
| 52 |
},
|
| 53 |
{
|
| 54 |
-
"epoch": 3.
|
| 55 |
-
"step":
|
| 56 |
-
"total_flos":
|
| 57 |
-
"train_loss": 7.
|
| 58 |
-
"train_runtime":
|
| 59 |
-
"train_samples_per_second": 0.
|
| 60 |
-
"train_steps_per_second": 0.
|
| 61 |
}
|
| 62 |
],
|
| 63 |
"logging_steps": 2,
|
| 64 |
-
"max_steps":
|
| 65 |
"num_input_tokens_seen": 0,
|
| 66 |
"num_train_epochs": 4,
|
| 67 |
"save_steps": 500,
|
|
@@ -77,7 +371,7 @@
|
|
| 77 |
"attributes": {}
|
| 78 |
}
|
| 79 |
},
|
| 80 |
-
"total_flos":
|
| 81 |
"train_batch_size": 2,
|
| 82 |
"trial_name": null,
|
| 83 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.857142857142857,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 96,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.08163265306122448,
|
| 13 |
+
"grad_norm": 0.9611280560493469,
|
| 14 |
+
"learning_rate": 0.00019583333333333334,
|
| 15 |
+
"loss": 9.6138,
|
| 16 |
"step": 2
|
| 17 |
},
|
| 18 |
{
|
| 19 |
+
"epoch": 0.16326530612244897,
|
| 20 |
+
"grad_norm": 1.6276118755340576,
|
| 21 |
+
"learning_rate": 0.00019166666666666667,
|
| 22 |
+
"loss": 9.1817,
|
| 23 |
"step": 4
|
| 24 |
},
|
| 25 |
{
|
| 26 |
+
"epoch": 0.24489795918367346,
|
| 27 |
+
"grad_norm": 1.9113811254501343,
|
| 28 |
+
"learning_rate": 0.0001875,
|
| 29 |
+
"loss": 8.6034,
|
| 30 |
"step": 6
|
| 31 |
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.32653061224489793,
|
| 34 |
+
"grad_norm": 1.9783806800842285,
|
| 35 |
+
"learning_rate": 0.00018333333333333334,
|
| 36 |
+
"loss": 8.2011,
|
| 37 |
+
"step": 8
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.40816326530612246,
|
| 41 |
+
"grad_norm": 1.256810188293457,
|
| 42 |
+
"learning_rate": 0.0001791666666666667,
|
| 43 |
+
"loss": 7.825,
|
| 44 |
+
"step": 10
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.4897959183673469,
|
| 48 |
+
"grad_norm": 1.0618529319763184,
|
| 49 |
+
"learning_rate": 0.000175,
|
| 50 |
+
"loss": 7.5991,
|
| 51 |
+
"step": 12
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.5714285714285714,
|
| 55 |
+
"grad_norm": 1.0928442478179932,
|
| 56 |
+
"learning_rate": 0.00017083333333333333,
|
| 57 |
+
"loss": 7.5382,
|
| 58 |
+
"step": 14
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.6530612244897959,
|
| 62 |
+
"grad_norm": 1.0726333856582642,
|
| 63 |
+
"learning_rate": 0.0001666666666666667,
|
| 64 |
+
"loss": 7.5217,
|
| 65 |
+
"step": 16
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.7346938775510204,
|
| 69 |
+
"grad_norm": 0.9622203707695007,
|
| 70 |
+
"learning_rate": 0.00016250000000000002,
|
| 71 |
+
"loss": 7.4223,
|
| 72 |
+
"step": 18
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.8163265306122449,
|
| 76 |
+
"grad_norm": 0.9835846424102783,
|
| 77 |
+
"learning_rate": 0.00015833333333333332,
|
| 78 |
+
"loss": 7.3894,
|
| 79 |
+
"step": 20
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.8979591836734694,
|
| 83 |
+
"grad_norm": 0.7535036206245422,
|
| 84 |
+
"learning_rate": 0.00015416666666666668,
|
| 85 |
+
"loss": 7.3294,
|
| 86 |
+
"step": 22
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.9795918367346939,
|
| 90 |
+
"grad_norm": 0.5977053046226501,
|
| 91 |
+
"learning_rate": 0.00015000000000000001,
|
| 92 |
+
"loss": 7.3581,
|
| 93 |
+
"step": 24
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 1.0408163265306123,
|
| 97 |
+
"grad_norm": 1.4706302881240845,
|
| 98 |
+
"learning_rate": 0.00014583333333333335,
|
| 99 |
+
"loss": 5.4914,
|
| 100 |
+
"step": 26
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 1.1224489795918366,
|
| 104 |
+
"grad_norm": 0.9165309071540833,
|
| 105 |
+
"learning_rate": 0.00014166666666666668,
|
| 106 |
+
"loss": 7.2332,
|
| 107 |
+
"step": 28
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 1.2040816326530612,
|
| 111 |
+
"grad_norm": 1.0459541082382202,
|
| 112 |
+
"learning_rate": 0.0001375,
|
| 113 |
+
"loss": 7.2485,
|
| 114 |
+
"step": 30
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 1.2857142857142856,
|
| 118 |
+
"grad_norm": 0.7298290133476257,
|
| 119 |
+
"learning_rate": 0.00013333333333333334,
|
| 120 |
+
"loss": 7.2555,
|
| 121 |
+
"step": 32
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 1.3673469387755102,
|
| 125 |
+
"grad_norm": 0.7277728319168091,
|
| 126 |
+
"learning_rate": 0.00012916666666666667,
|
| 127 |
+
"loss": 7.1953,
|
| 128 |
+
"step": 34
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.4489795918367347,
|
| 132 |
+
"grad_norm": 0.6085571646690369,
|
| 133 |
+
"learning_rate": 0.000125,
|
| 134 |
+
"loss": 7.1782,
|
| 135 |
+
"step": 36
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 1.5306122448979593,
|
| 139 |
+
"grad_norm": 0.621771514415741,
|
| 140 |
+
"learning_rate": 0.00012083333333333333,
|
| 141 |
+
"loss": 7.1948,
|
| 142 |
+
"step": 38
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 1.6122448979591837,
|
| 146 |
+
"grad_norm": 0.8418042659759521,
|
| 147 |
+
"learning_rate": 0.00011666666666666668,
|
| 148 |
+
"loss": 7.1403,
|
| 149 |
+
"step": 40
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.693877551020408,
|
| 153 |
+
"grad_norm": 0.4234924018383026,
|
| 154 |
+
"learning_rate": 0.00011250000000000001,
|
| 155 |
+
"loss": 7.1515,
|
| 156 |
+
"step": 42
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 1.7755102040816326,
|
| 160 |
+
"grad_norm": 0.6041470766067505,
|
| 161 |
+
"learning_rate": 0.00010833333333333333,
|
| 162 |
+
"loss": 7.0812,
|
| 163 |
+
"step": 44
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 1.8571428571428572,
|
| 167 |
+
"grad_norm": 0.8113789558410645,
|
| 168 |
+
"learning_rate": 0.00010416666666666667,
|
| 169 |
+
"loss": 7.1907,
|
| 170 |
+
"step": 46
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 1.9387755102040818,
|
| 174 |
+
"grad_norm": 0.8824118375778198,
|
| 175 |
+
"learning_rate": 0.0001,
|
| 176 |
+
"loss": 7.1823,
|
| 177 |
+
"step": 48
|
| 178 |
+
},
|
| 179 |
{
|
| 180 |
"epoch": 2.0,
|
| 181 |
+
"grad_norm": 0.4565996527671814,
|
| 182 |
+
"learning_rate": 9.583333333333334e-05,
|
| 183 |
+
"loss": 5.3337,
|
| 184 |
+
"step": 50
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 2.0816326530612246,
|
| 188 |
+
"grad_norm": 0.6504805088043213,
|
| 189 |
+
"learning_rate": 9.166666666666667e-05,
|
| 190 |
+
"loss": 7.1268,
|
| 191 |
+
"step": 52
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 2.163265306122449,
|
| 195 |
+
"grad_norm": 0.39629825949668884,
|
| 196 |
+
"learning_rate": 8.75e-05,
|
| 197 |
+
"loss": 7.1279,
|
| 198 |
+
"step": 54
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 2.2448979591836733,
|
| 202 |
+
"grad_norm": 0.48973432183265686,
|
| 203 |
+
"learning_rate": 8.333333333333334e-05,
|
| 204 |
+
"loss": 7.1235,
|
| 205 |
+
"step": 56
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 2.326530612244898,
|
| 209 |
+
"grad_norm": 0.4701223373413086,
|
| 210 |
+
"learning_rate": 7.916666666666666e-05,
|
| 211 |
+
"loss": 7.0456,
|
| 212 |
+
"step": 58
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 2.4081632653061225,
|
| 216 |
+
"grad_norm": 1.1409740447998047,
|
| 217 |
+
"learning_rate": 7.500000000000001e-05,
|
| 218 |
+
"loss": 7.1346,
|
| 219 |
+
"step": 60
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 2.489795918367347,
|
| 223 |
+
"grad_norm": 0.48205825686454773,
|
| 224 |
+
"learning_rate": 7.083333333333334e-05,
|
| 225 |
+
"loss": 7.0549,
|
| 226 |
+
"step": 62
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 2.571428571428571,
|
| 230 |
+
"grad_norm": 0.6595655083656311,
|
| 231 |
"learning_rate": 6.666666666666667e-05,
|
| 232 |
+
"loss": 7.1589,
|
| 233 |
+
"step": 64
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 2.6530612244897958,
|
| 237 |
+
"grad_norm": 0.8976457715034485,
|
| 238 |
+
"learning_rate": 6.25e-05,
|
| 239 |
+
"loss": 7.0514,
|
| 240 |
+
"step": 66
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 2.7346938775510203,
|
| 244 |
+
"grad_norm": 0.7210097312927246,
|
| 245 |
+
"learning_rate": 5.833333333333334e-05,
|
| 246 |
+
"loss": 7.1126,
|
| 247 |
+
"step": 68
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 2.816326530612245,
|
| 251 |
+
"grad_norm": 0.49198052287101746,
|
| 252 |
+
"learning_rate": 5.4166666666666664e-05,
|
| 253 |
+
"loss": 7.1056,
|
| 254 |
+
"step": 70
|
| 255 |
},
|
| 256 |
{
|
| 257 |
+
"epoch": 2.8979591836734695,
|
| 258 |
+
"grad_norm": 0.48084384202957153,
|
| 259 |
+
"learning_rate": 5e-05,
|
| 260 |
+
"loss": 6.9983,
|
| 261 |
+
"step": 72
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 2.979591836734694,
|
| 265 |
+
"grad_norm": 0.5943397879600525,
|
| 266 |
+
"learning_rate": 4.5833333333333334e-05,
|
| 267 |
+
"loss": 7.1149,
|
| 268 |
+
"step": 74
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 3.0408163265306123,
|
| 272 |
+
"grad_norm": 0.49961674213409424,
|
| 273 |
+
"learning_rate": 4.166666666666667e-05,
|
| 274 |
+
"loss": 5.322,
|
| 275 |
+
"step": 76
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 3.122448979591837,
|
| 279 |
+
"grad_norm": 0.5228291153907776,
|
| 280 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 281 |
+
"loss": 7.0475,
|
| 282 |
+
"step": 78
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 3.204081632653061,
|
| 286 |
+
"grad_norm": 0.7281824350357056,
|
| 287 |
"learning_rate": 3.3333333333333335e-05,
|
| 288 |
+
"loss": 7.0873,
|
| 289 |
+
"step": 80
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 3.2857142857142856,
|
| 293 |
+
"grad_norm": 0.49217817187309265,
|
| 294 |
+
"learning_rate": 2.916666666666667e-05,
|
| 295 |
+
"loss": 7.0653,
|
| 296 |
+
"step": 82
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 3.36734693877551,
|
| 300 |
+
"grad_norm": 0.6683712005615234,
|
| 301 |
+
"learning_rate": 2.5e-05,
|
| 302 |
+
"loss": 7.0252,
|
| 303 |
+
"step": 84
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 3.4489795918367347,
|
| 307 |
+
"grad_norm": 0.7695971131324768,
|
| 308 |
+
"learning_rate": 2.0833333333333336e-05,
|
| 309 |
+
"loss": 7.0718,
|
| 310 |
+
"step": 86
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 3.5306122448979593,
|
| 314 |
+
"grad_norm": 0.6157537698745728,
|
| 315 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 316 |
+
"loss": 7.0925,
|
| 317 |
+
"step": 88
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 3.612244897959184,
|
| 321 |
+
"grad_norm": 0.5091469287872314,
|
| 322 |
+
"learning_rate": 1.25e-05,
|
| 323 |
+
"loss": 6.9613,
|
| 324 |
+
"step": 90
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 3.693877551020408,
|
| 328 |
+
"grad_norm": 0.5973119735717773,
|
| 329 |
+
"learning_rate": 8.333333333333334e-06,
|
| 330 |
+
"loss": 7.01,
|
| 331 |
+
"step": 92
|
| 332 |
},
|
| 333 |
{
|
| 334 |
+
"epoch": 3.7755102040816326,
|
| 335 |
+
"grad_norm": 0.44761213660240173,
|
| 336 |
+
"learning_rate": 4.166666666666667e-06,
|
| 337 |
+
"loss": 7.1092,
|
| 338 |
+
"step": 94
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 3.857142857142857,
|
| 342 |
+
"grad_norm": 0.6290495991706848,
|
| 343 |
"learning_rate": 0.0,
|
| 344 |
+
"loss": 7.0562,
|
| 345 |
+
"step": 96
|
| 346 |
},
|
| 347 |
{
|
| 348 |
+
"epoch": 3.857142857142857,
|
| 349 |
+
"step": 96,
|
| 350 |
+
"total_flos": 97587854499492.0,
|
| 351 |
+
"train_loss": 7.217979848384857,
|
| 352 |
+
"train_runtime": 2726.5862,
|
| 353 |
+
"train_samples_per_second": 0.574,
|
| 354 |
+
"train_steps_per_second": 0.035
|
| 355 |
}
|
| 356 |
],
|
| 357 |
"logging_steps": 2,
|
| 358 |
+
"max_steps": 96,
|
| 359 |
"num_input_tokens_seen": 0,
|
| 360 |
"num_train_epochs": 4,
|
| 361 |
"save_steps": 500,
|
|
|
|
| 371 |
"attributes": {}
|
| 372 |
}
|
| 373 |
},
|
| 374 |
+
"total_flos": 97587854499492.0,
|
| 375 |
"train_batch_size": 2,
|
| 376 |
"trial_name": null,
|
| 377 |
"trial_params": null
|