End of training
Browse files- README.md +3 -1
- trainer_state.json +302 -29
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-melody-lora-punk-colab
|
|
@@ -14,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 14 |
|
| 15 |
# musicgen-melody-lora-punk-colab
|
| 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-melody-lora-punk-colab
|
|
|
|
| 16 |
|
| 17 |
# musicgen-melody-lora-punk-colab
|
| 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
|
@@ -1,69 +1,342 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 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": 0.5925925925925926,
|
| 13 |
-
"grad_norm": 1.
|
| 14 |
-
"learning_rate": 0.
|
| 15 |
-
"loss": 9.
|
| 16 |
"step": 2
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 1.1851851851851851,
|
| 20 |
-
"grad_norm": 1.
|
| 21 |
-
"learning_rate": 0.
|
| 22 |
-
"loss": 9.
|
| 23 |
"step": 4
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 1.7777777777777777,
|
| 27 |
-
"grad_norm": 2.
|
| 28 |
-
"learning_rate": 0.
|
| 29 |
-
"loss": 8.
|
| 30 |
"step": 6
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"epoch": 2.3703703703703702,
|
| 34 |
-
"grad_norm":
|
| 35 |
-
"learning_rate":
|
| 36 |
-
"loss":
|
| 37 |
"step": 8
|
| 38 |
},
|
| 39 |
{
|
| 40 |
"epoch": 2.962962962962963,
|
| 41 |
-
"grad_norm":
|
| 42 |
-
"learning_rate":
|
| 43 |
-
"loss": 7.
|
| 44 |
"step": 10
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 3.5555555555555554,
|
| 48 |
-
"grad_norm":
|
| 49 |
-
"learning_rate": 0.
|
| 50 |
-
"loss": 7.
|
| 51 |
"step": 12
|
| 52 |
},
|
| 53 |
{
|
| 54 |
-
"epoch":
|
| 55 |
-
"
|
| 56 |
-
"
|
| 57 |
-
"
|
| 58 |
-
"
|
| 59 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 60 |
"train_steps_per_second": 0.037
|
| 61 |
}
|
| 62 |
],
|
| 63 |
"logging_steps": 2,
|
| 64 |
-
"max_steps":
|
| 65 |
"num_input_tokens_seen": 0,
|
| 66 |
-
"num_train_epochs":
|
| 67 |
"save_steps": 500,
|
| 68 |
"stateful_callbacks": {
|
| 69 |
"TrainerControl": {
|
|
@@ -77,7 +350,7 @@
|
|
| 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": 26.666666666666668,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 90,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.5925925925925926,
|
| 13 |
+
"grad_norm": 1.0835238695144653,
|
| 14 |
+
"learning_rate": 0.00019555555555555556,
|
| 15 |
+
"loss": 9.4668,
|
| 16 |
"step": 2
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 1.1851851851851851,
|
| 20 |
+
"grad_norm": 1.3387597799301147,
|
| 21 |
+
"learning_rate": 0.00019111111111111114,
|
| 22 |
+
"loss": 9.0964,
|
| 23 |
"step": 4
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 1.7777777777777777,
|
| 27 |
+
"grad_norm": 2.4566526412963867,
|
| 28 |
+
"learning_rate": 0.0001866666666666667,
|
| 29 |
+
"loss": 8.5058,
|
| 30 |
"step": 6
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"epoch": 2.3703703703703702,
|
| 34 |
+
"grad_norm": 1.337947964668274,
|
| 35 |
+
"learning_rate": 0.00018222222222222224,
|
| 36 |
+
"loss": 7.8295,
|
| 37 |
"step": 8
|
| 38 |
},
|
| 39 |
{
|
| 40 |
"epoch": 2.962962962962963,
|
| 41 |
+
"grad_norm": 0.9213329553604126,
|
| 42 |
+
"learning_rate": 0.00017777777777777779,
|
| 43 |
+
"loss": 7.55,
|
| 44 |
"step": 10
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 3.5555555555555554,
|
| 48 |
+
"grad_norm": 0.8294873237609863,
|
| 49 |
+
"learning_rate": 0.00017333333333333334,
|
| 50 |
+
"loss": 7.4103,
|
| 51 |
"step": 12
|
| 52 |
},
|
| 53 |
{
|
| 54 |
+
"epoch": 4.148148148148148,
|
| 55 |
+
"grad_norm": 1.0435646772384644,
|
| 56 |
+
"learning_rate": 0.00016888888888888889,
|
| 57 |
+
"loss": 7.3669,
|
| 58 |
+
"step": 14
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 4.7407407407407405,
|
| 62 |
+
"grad_norm": 2.152470111846924,
|
| 63 |
+
"learning_rate": 0.00016444444444444444,
|
| 64 |
+
"loss": 7.3731,
|
| 65 |
+
"step": 16
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 5.333333333333333,
|
| 69 |
+
"grad_norm": 0.6850627064704895,
|
| 70 |
+
"learning_rate": 0.00016,
|
| 71 |
+
"loss": 7.3274,
|
| 72 |
+
"step": 18
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 5.925925925925926,
|
| 76 |
+
"grad_norm": 0.9927621483802795,
|
| 77 |
+
"learning_rate": 0.00015555555555555556,
|
| 78 |
+
"loss": 7.2687,
|
| 79 |
+
"step": 20
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 6.518518518518518,
|
| 83 |
+
"grad_norm": 0.6255151629447937,
|
| 84 |
+
"learning_rate": 0.0001511111111111111,
|
| 85 |
+
"loss": 7.2457,
|
| 86 |
+
"step": 22
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 7.111111111111111,
|
| 90 |
+
"grad_norm": 0.4171934425830841,
|
| 91 |
+
"learning_rate": 0.00014666666666666666,
|
| 92 |
+
"loss": 7.265,
|
| 93 |
+
"step": 24
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 7.703703703703704,
|
| 97 |
+
"grad_norm": 0.7594227194786072,
|
| 98 |
+
"learning_rate": 0.00014222222222222224,
|
| 99 |
+
"loss": 7.2059,
|
| 100 |
+
"step": 26
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 8.296296296296296,
|
| 104 |
+
"grad_norm": 0.6241652965545654,
|
| 105 |
+
"learning_rate": 0.0001377777777777778,
|
| 106 |
+
"loss": 7.2223,
|
| 107 |
+
"step": 28
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 8.88888888888889,
|
| 111 |
+
"grad_norm": 0.6361931562423706,
|
| 112 |
+
"learning_rate": 0.00013333333333333334,
|
| 113 |
+
"loss": 7.1813,
|
| 114 |
+
"step": 30
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 9.481481481481481,
|
| 118 |
+
"grad_norm": 0.40144020318984985,
|
| 119 |
+
"learning_rate": 0.00012888888888888892,
|
| 120 |
+
"loss": 7.1944,
|
| 121 |
+
"step": 32
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 10.074074074074074,
|
| 125 |
+
"grad_norm": 0.8601672053337097,
|
| 126 |
+
"learning_rate": 0.00012444444444444444,
|
| 127 |
+
"loss": 7.191,
|
| 128 |
+
"step": 34
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 10.666666666666666,
|
| 132 |
+
"grad_norm": 0.47764790058135986,
|
| 133 |
+
"learning_rate": 0.00012,
|
| 134 |
+
"loss": 7.1806,
|
| 135 |
+
"step": 36
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 11.25925925925926,
|
| 139 |
+
"grad_norm": 0.6741082072257996,
|
| 140 |
+
"learning_rate": 0.00011555555555555555,
|
| 141 |
+
"loss": 7.1588,
|
| 142 |
+
"step": 38
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 11.851851851851851,
|
| 146 |
+
"grad_norm": 0.320622056722641,
|
| 147 |
+
"learning_rate": 0.00011111111111111112,
|
| 148 |
+
"loss": 7.1678,
|
| 149 |
+
"step": 40
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 12.444444444444445,
|
| 153 |
+
"grad_norm": 0.41680437326431274,
|
| 154 |
+
"learning_rate": 0.00010666666666666667,
|
| 155 |
+
"loss": 7.1937,
|
| 156 |
+
"step": 42
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 13.037037037037036,
|
| 160 |
+
"grad_norm": 0.5265238285064697,
|
| 161 |
+
"learning_rate": 0.00010222222222222222,
|
| 162 |
+
"loss": 7.1729,
|
| 163 |
+
"step": 44
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 13.62962962962963,
|
| 167 |
+
"grad_norm": 0.2438785880804062,
|
| 168 |
+
"learning_rate": 9.777777777777778e-05,
|
| 169 |
+
"loss": 7.1447,
|
| 170 |
+
"step": 46
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 14.222222222222221,
|
| 174 |
+
"grad_norm": 0.2717892527580261,
|
| 175 |
+
"learning_rate": 9.333333333333334e-05,
|
| 176 |
+
"loss": 7.1401,
|
| 177 |
+
"step": 48
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 14.814814814814815,
|
| 181 |
+
"grad_norm": 0.27455106377601624,
|
| 182 |
+
"learning_rate": 8.888888888888889e-05,
|
| 183 |
+
"loss": 7.1263,
|
| 184 |
+
"step": 50
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 15.407407407407407,
|
| 188 |
+
"grad_norm": 0.32036423683166504,
|
| 189 |
+
"learning_rate": 8.444444444444444e-05,
|
| 190 |
+
"loss": 7.1606,
|
| 191 |
+
"step": 52
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 16.0,
|
| 195 |
+
"grad_norm": 0.3542112708091736,
|
| 196 |
+
"learning_rate": 8e-05,
|
| 197 |
+
"loss": 7.1612,
|
| 198 |
+
"step": 54
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 16.59259259259259,
|
| 202 |
+
"grad_norm": 0.2720729112625122,
|
| 203 |
+
"learning_rate": 7.555555555555556e-05,
|
| 204 |
+
"loss": 7.157,
|
| 205 |
+
"step": 56
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 17.185185185185187,
|
| 209 |
+
"grad_norm": 0.4563415050506592,
|
| 210 |
+
"learning_rate": 7.111111111111112e-05,
|
| 211 |
+
"loss": 7.1165,
|
| 212 |
+
"step": 58
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 17.77777777777778,
|
| 216 |
+
"grad_norm": 0.3706892430782318,
|
| 217 |
+
"learning_rate": 6.666666666666667e-05,
|
| 218 |
+
"loss": 7.1504,
|
| 219 |
+
"step": 60
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 18.37037037037037,
|
| 223 |
+
"grad_norm": 0.4367642402648926,
|
| 224 |
+
"learning_rate": 6.222222222222222e-05,
|
| 225 |
+
"loss": 7.1585,
|
| 226 |
+
"step": 62
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 18.962962962962962,
|
| 230 |
+
"grad_norm": 0.35599270462989807,
|
| 231 |
+
"learning_rate": 5.7777777777777776e-05,
|
| 232 |
+
"loss": 7.121,
|
| 233 |
+
"step": 64
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 19.555555555555557,
|
| 237 |
+
"grad_norm": 0.28254929184913635,
|
| 238 |
+
"learning_rate": 5.333333333333333e-05,
|
| 239 |
+
"loss": 7.1481,
|
| 240 |
+
"step": 66
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 20.14814814814815,
|
| 244 |
+
"grad_norm": 0.3943895399570465,
|
| 245 |
+
"learning_rate": 4.888888888888889e-05,
|
| 246 |
+
"loss": 7.1082,
|
| 247 |
+
"step": 68
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 20.74074074074074,
|
| 251 |
+
"grad_norm": 0.2905910313129425,
|
| 252 |
+
"learning_rate": 4.4444444444444447e-05,
|
| 253 |
+
"loss": 7.1596,
|
| 254 |
+
"step": 70
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 21.333333333333332,
|
| 258 |
+
"grad_norm": 0.33000853657722473,
|
| 259 |
+
"learning_rate": 4e-05,
|
| 260 |
+
"loss": 7.1279,
|
| 261 |
+
"step": 72
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 21.925925925925927,
|
| 265 |
+
"grad_norm": 0.30440381169319153,
|
| 266 |
+
"learning_rate": 3.555555555555556e-05,
|
| 267 |
+
"loss": 7.1007,
|
| 268 |
+
"step": 74
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 22.51851851851852,
|
| 272 |
+
"grad_norm": 0.31049448251724243,
|
| 273 |
+
"learning_rate": 3.111111111111111e-05,
|
| 274 |
+
"loss": 7.1304,
|
| 275 |
+
"step": 76
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 23.11111111111111,
|
| 279 |
+
"grad_norm": 0.33641088008880615,
|
| 280 |
+
"learning_rate": 2.6666666666666667e-05,
|
| 281 |
+
"loss": 7.1468,
|
| 282 |
+
"step": 78
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 23.703703703703702,
|
| 286 |
+
"grad_norm": 0.5838092565536499,
|
| 287 |
+
"learning_rate": 2.2222222222222223e-05,
|
| 288 |
+
"loss": 7.1533,
|
| 289 |
+
"step": 80
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 24.296296296296298,
|
| 293 |
+
"grad_norm": 0.2617644965648651,
|
| 294 |
+
"learning_rate": 1.777777777777778e-05,
|
| 295 |
+
"loss": 7.1076,
|
| 296 |
+
"step": 82
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 24.88888888888889,
|
| 300 |
+
"grad_norm": 0.23922277987003326,
|
| 301 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 302 |
+
"loss": 7.1408,
|
| 303 |
+
"step": 84
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 25.48148148148148,
|
| 307 |
+
"grad_norm": 0.28710824251174927,
|
| 308 |
+
"learning_rate": 8.88888888888889e-06,
|
| 309 |
+
"loss": 7.0894,
|
| 310 |
+
"step": 86
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 26.074074074074073,
|
| 314 |
+
"grad_norm": 0.5698680877685547,
|
| 315 |
+
"learning_rate": 4.444444444444445e-06,
|
| 316 |
+
"loss": 7.1309,
|
| 317 |
+
"step": 88
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 26.666666666666668,
|
| 321 |
+
"grad_norm": 0.3135036528110504,
|
| 322 |
+
"learning_rate": 0.0,
|
| 323 |
+
"loss": 7.1452,
|
| 324 |
+
"step": 90
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 26.666666666666668,
|
| 328 |
+
"step": 90,
|
| 329 |
+
"total_flos": 410861219852448.0,
|
| 330 |
+
"train_loss": 7.326659817165798,
|
| 331 |
+
"train_runtime": 2404.3353,
|
| 332 |
+
"train_samples_per_second": 0.674,
|
| 333 |
"train_steps_per_second": 0.037
|
| 334 |
}
|
| 335 |
],
|
| 336 |
"logging_steps": 2,
|
| 337 |
+
"max_steps": 90,
|
| 338 |
"num_input_tokens_seen": 0,
|
| 339 |
+
"num_train_epochs": 30,
|
| 340 |
"save_steps": 500,
|
| 341 |
"stateful_callbacks": {
|
| 342 |
"TrainerControl": {
|
|
|
|
| 350 |
"attributes": {}
|
| 351 |
}
|
| 352 |
},
|
| 353 |
+
"total_flos": 410861219852448.0,
|
| 354 |
"train_batch_size": 2,
|
| 355 |
"trial_name": null,
|
| 356 |
"trial_params": null
|