Commit
•
1e49ff6
1
Parent(s):
b0e68fd
End of training
Browse files- README.md +3 -1
- trainer_state.json +300 -48
README.md
CHANGED
|
@@ -3,6 +3,8 @@ library_name: peft
|
|
| 3 |
license: cc-by-nc-4.0
|
| 4 |
base_model: facebook/musicgen-small
|
| 5 |
tags:
|
|
|
|
|
|
|
| 6 |
- generated_from_trainer
|
| 7 |
model-index:
|
| 8 |
- name: musicgen-small-ft1
|
|
@@ -14,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 14 |
|
| 15 |
# musicgen-small-ft1
|
| 16 |
|
| 17 |
-
This model is a fine-tuned version of [facebook/musicgen-small](https://huggingface.co/facebook/musicgen-small) on
|
| 18 |
|
| 19 |
## Model description
|
| 20 |
|
|
|
|
| 3 |
license: cc-by-nc-4.0
|
| 4 |
base_model: facebook/musicgen-small
|
| 5 |
tags:
|
| 6 |
+
- text-to-audio
|
| 7 |
+
- indian
|
| 8 |
- generated_from_trainer
|
| 9 |
model-index:
|
| 10 |
- name: musicgen-small-ft1
|
|
|
|
| 16 |
|
| 17 |
# musicgen-small-ft1
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [facebook/musicgen-small](https://huggingface.co/facebook/musicgen-small) on the DevPanda004/indian-music-and-metadata-3 dataset.
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
trainer_state.json
CHANGED
|
@@ -1,111 +1,363 @@
|
|
| 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": 0.16,
|
| 13 |
-
"grad_norm":
|
| 14 |
-
"learning_rate": 0.
|
| 15 |
-
"loss": 9.
|
| 16 |
"step": 2
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 0.32,
|
| 20 |
-
"grad_norm":
|
| 21 |
-
"learning_rate": 0.
|
| 22 |
-
"loss":
|
| 23 |
"step": 4
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 0.48,
|
| 27 |
-
"grad_norm":
|
| 28 |
-
"learning_rate": 0.
|
| 29 |
-
"loss": 8.
|
| 30 |
"step": 6
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"epoch": 0.64,
|
| 34 |
-
"grad_norm":
|
| 35 |
-
"learning_rate": 0.
|
| 36 |
-
"loss": 7.
|
| 37 |
"step": 8
|
| 38 |
},
|
| 39 |
{
|
| 40 |
"epoch": 0.8,
|
| 41 |
-
"grad_norm":
|
| 42 |
-
"learning_rate": 0.
|
| 43 |
-
"loss": 7.
|
| 44 |
"step": 10
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.96,
|
| 48 |
-
"grad_norm":
|
| 49 |
-
"learning_rate": 0.
|
| 50 |
-
"loss": 7.
|
| 51 |
"step": 12
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 1.08,
|
| 55 |
-
"grad_norm":
|
| 56 |
-
"learning_rate":
|
| 57 |
-
"loss": 5.
|
| 58 |
"step": 14
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"epoch": 1.24,
|
| 62 |
-
"grad_norm":
|
| 63 |
-
"learning_rate":
|
| 64 |
-
"loss": 7.
|
| 65 |
"step": 16
|
| 66 |
},
|
| 67 |
{
|
| 68 |
"epoch": 1.4,
|
| 69 |
-
"grad_norm":
|
| 70 |
-
"learning_rate":
|
| 71 |
-
"loss": 7.
|
| 72 |
"step": 18
|
| 73 |
},
|
| 74 |
{
|
| 75 |
"epoch": 1.56,
|
| 76 |
-
"grad_norm":
|
| 77 |
-
"learning_rate":
|
| 78 |
-
"loss":
|
| 79 |
"step": 20
|
| 80 |
},
|
| 81 |
{
|
| 82 |
"epoch": 1.72,
|
| 83 |
-
"grad_norm":
|
| 84 |
-
"learning_rate":
|
| 85 |
-
"loss":
|
| 86 |
"step": 22
|
| 87 |
},
|
| 88 |
{
|
| 89 |
"epoch": 1.88,
|
| 90 |
-
"grad_norm":
|
| 91 |
-
"learning_rate":
|
| 92 |
-
"loss": 6.
|
| 93 |
"step": 24
|
| 94 |
},
|
| 95 |
{
|
| 96 |
-
"epoch":
|
| 97 |
-
"
|
| 98 |
-
"
|
| 99 |
-
"
|
| 100 |
-
"
|
| 101 |
-
|
| 102 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 103 |
}
|
| 104 |
],
|
| 105 |
"logging_steps": 2,
|
| 106 |
-
"max_steps":
|
| 107 |
"num_input_tokens_seen": 0,
|
| 108 |
-
"num_train_epochs":
|
| 109 |
"save_steps": 500,
|
| 110 |
"stateful_callbacks": {
|
| 111 |
"TrainerControl": {
|
|
@@ -119,7 +371,7 @@
|
|
| 119 |
"attributes": {}
|
| 120 |
}
|
| 121 |
},
|
| 122 |
-
"total_flos":
|
| 123 |
"train_batch_size": 2,
|
| 124 |
"trial_name": null,
|
| 125 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 7.4,
|
| 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": 0.16,
|
| 13 |
+
"grad_norm": 24.299409866333008,
|
| 14 |
+
"learning_rate": 0.00019583333333333334,
|
| 15 |
+
"loss": 9.6308,
|
| 16 |
"step": 2
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 0.32,
|
| 20 |
+
"grad_norm": 21.645837783813477,
|
| 21 |
+
"learning_rate": 0.00019166666666666667,
|
| 22 |
+
"loss": 8.8304,
|
| 23 |
"step": 4
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 0.48,
|
| 27 |
+
"grad_norm": 26.87311553955078,
|
| 28 |
+
"learning_rate": 0.0001875,
|
| 29 |
+
"loss": 8.2558,
|
| 30 |
"step": 6
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"epoch": 0.64,
|
| 34 |
+
"grad_norm": 20.85015106201172,
|
| 35 |
+
"learning_rate": 0.00018333333333333334,
|
| 36 |
+
"loss": 7.6341,
|
| 37 |
"step": 8
|
| 38 |
},
|
| 39 |
{
|
| 40 |
"epoch": 0.8,
|
| 41 |
+
"grad_norm": 11.373078346252441,
|
| 42 |
+
"learning_rate": 0.0001791666666666667,
|
| 43 |
+
"loss": 7.3657,
|
| 44 |
"step": 10
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.96,
|
| 48 |
+
"grad_norm": 8.73630428314209,
|
| 49 |
+
"learning_rate": 0.000175,
|
| 50 |
+
"loss": 7.3537,
|
| 51 |
"step": 12
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 1.08,
|
| 55 |
+
"grad_norm": 5.606980323791504,
|
| 56 |
+
"learning_rate": 0.00017083333333333333,
|
| 57 |
+
"loss": 5.4308,
|
| 58 |
"step": 14
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"epoch": 1.24,
|
| 62 |
+
"grad_norm": 4.6125168800354,
|
| 63 |
+
"learning_rate": 0.0001666666666666667,
|
| 64 |
+
"loss": 7.1842,
|
| 65 |
"step": 16
|
| 66 |
},
|
| 67 |
{
|
| 68 |
"epoch": 1.4,
|
| 69 |
+
"grad_norm": 7.653925895690918,
|
| 70 |
+
"learning_rate": 0.00016250000000000002,
|
| 71 |
+
"loss": 7.0222,
|
| 72 |
"step": 18
|
| 73 |
},
|
| 74 |
{
|
| 75 |
"epoch": 1.56,
|
| 76 |
+
"grad_norm": 4.941583633422852,
|
| 77 |
+
"learning_rate": 0.00015833333333333332,
|
| 78 |
+
"loss": 6.962,
|
| 79 |
"step": 20
|
| 80 |
},
|
| 81 |
{
|
| 82 |
"epoch": 1.72,
|
| 83 |
+
"grad_norm": 6.187161922454834,
|
| 84 |
+
"learning_rate": 0.00015416666666666668,
|
| 85 |
+
"loss": 6.9915,
|
| 86 |
"step": 22
|
| 87 |
},
|
| 88 |
{
|
| 89 |
"epoch": 1.88,
|
| 90 |
+
"grad_norm": 3.677783489227295,
|
| 91 |
+
"learning_rate": 0.00015000000000000001,
|
| 92 |
+
"loss": 6.7917,
|
| 93 |
"step": 24
|
| 94 |
},
|
| 95 |
{
|
| 96 |
+
"epoch": 2.0,
|
| 97 |
+
"grad_norm": 3.971726417541504,
|
| 98 |
+
"learning_rate": 0.00014583333333333335,
|
| 99 |
+
"loss": 5.0888,
|
| 100 |
+
"step": 26
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 2.16,
|
| 104 |
+
"grad_norm": 4.507529258728027,
|
| 105 |
+
"learning_rate": 0.00014166666666666668,
|
| 106 |
+
"loss": 6.969,
|
| 107 |
+
"step": 28
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 2.32,
|
| 111 |
+
"grad_norm": 5.118126392364502,
|
| 112 |
+
"learning_rate": 0.0001375,
|
| 113 |
+
"loss": 6.702,
|
| 114 |
+
"step": 30
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 2.48,
|
| 118 |
+
"grad_norm": 4.643431663513184,
|
| 119 |
+
"learning_rate": 0.00013333333333333334,
|
| 120 |
+
"loss": 6.9216,
|
| 121 |
+
"step": 32
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 2.64,
|
| 125 |
+
"grad_norm": 3.6992788314819336,
|
| 126 |
+
"learning_rate": 0.00012916666666666667,
|
| 127 |
+
"loss": 6.8128,
|
| 128 |
+
"step": 34
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 2.8,
|
| 132 |
+
"grad_norm": 4.0084614753723145,
|
| 133 |
+
"learning_rate": 0.000125,
|
| 134 |
+
"loss": 6.8316,
|
| 135 |
+
"step": 36
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 2.96,
|
| 139 |
+
"grad_norm": 3.2957804203033447,
|
| 140 |
+
"learning_rate": 0.00012083333333333333,
|
| 141 |
+
"loss": 6.7879,
|
| 142 |
+
"step": 38
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 3.08,
|
| 146 |
+
"grad_norm": 5.090462684631348,
|
| 147 |
+
"learning_rate": 0.00011666666666666668,
|
| 148 |
+
"loss": 5.0059,
|
| 149 |
+
"step": 40
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 3.24,
|
| 153 |
+
"grad_norm": 5.256293773651123,
|
| 154 |
+
"learning_rate": 0.00011250000000000001,
|
| 155 |
+
"loss": 6.8814,
|
| 156 |
+
"step": 42
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 3.4,
|
| 160 |
+
"grad_norm": 4.577947616577148,
|
| 161 |
+
"learning_rate": 0.00010833333333333333,
|
| 162 |
+
"loss": 6.7358,
|
| 163 |
+
"step": 44
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 3.56,
|
| 167 |
+
"grad_norm": 4.876791954040527,
|
| 168 |
+
"learning_rate": 0.00010416666666666667,
|
| 169 |
+
"loss": 6.8413,
|
| 170 |
+
"step": 46
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 3.7199999999999998,
|
| 174 |
+
"grad_norm": 3.020899534225464,
|
| 175 |
+
"learning_rate": 0.0001,
|
| 176 |
+
"loss": 6.8198,
|
| 177 |
+
"step": 48
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 3.88,
|
| 181 |
+
"grad_norm": 3.4423134326934814,
|
| 182 |
+
"learning_rate": 9.583333333333334e-05,
|
| 183 |
+
"loss": 6.696,
|
| 184 |
+
"step": 50
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 4.0,
|
| 188 |
+
"grad_norm": 1.9926425218582153,
|
| 189 |
+
"learning_rate": 9.166666666666667e-05,
|
| 190 |
+
"loss": 5.1219,
|
| 191 |
+
"step": 52
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 4.16,
|
| 195 |
+
"grad_norm": 3.435487985610962,
|
| 196 |
+
"learning_rate": 8.75e-05,
|
| 197 |
+
"loss": 6.7308,
|
| 198 |
+
"step": 54
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 4.32,
|
| 202 |
+
"grad_norm": 3.666560649871826,
|
| 203 |
+
"learning_rate": 8.333333333333334e-05,
|
| 204 |
+
"loss": 6.807,
|
| 205 |
+
"step": 56
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 4.48,
|
| 209 |
+
"grad_norm": 5.933062553405762,
|
| 210 |
+
"learning_rate": 7.916666666666666e-05,
|
| 211 |
+
"loss": 6.5088,
|
| 212 |
+
"step": 58
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 4.64,
|
| 216 |
+
"grad_norm": 7.5597944259643555,
|
| 217 |
+
"learning_rate": 7.500000000000001e-05,
|
| 218 |
+
"loss": 6.8242,
|
| 219 |
+
"step": 60
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 4.8,
|
| 223 |
+
"grad_norm": 4.08908224105835,
|
| 224 |
+
"learning_rate": 7.083333333333334e-05,
|
| 225 |
+
"loss": 6.7755,
|
| 226 |
+
"step": 62
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 4.96,
|
| 230 |
+
"grad_norm": 2.845886707305908,
|
| 231 |
+
"learning_rate": 6.666666666666667e-05,
|
| 232 |
+
"loss": 6.7024,
|
| 233 |
+
"step": 64
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 5.08,
|
| 237 |
+
"grad_norm": 4.930906295776367,
|
| 238 |
+
"learning_rate": 6.25e-05,
|
| 239 |
+
"loss": 5.0796,
|
| 240 |
+
"step": 66
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 5.24,
|
| 244 |
+
"grad_norm": 4.909699440002441,
|
| 245 |
+
"learning_rate": 5.833333333333334e-05,
|
| 246 |
+
"loss": 6.6225,
|
| 247 |
+
"step": 68
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 5.4,
|
| 251 |
+
"grad_norm": 5.248680591583252,
|
| 252 |
+
"learning_rate": 5.4166666666666664e-05,
|
| 253 |
+
"loss": 6.6255,
|
| 254 |
+
"step": 70
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 5.5600000000000005,
|
| 258 |
+
"grad_norm": 4.862923622131348,
|
| 259 |
+
"learning_rate": 5e-05,
|
| 260 |
+
"loss": 6.6052,
|
| 261 |
+
"step": 72
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 5.72,
|
| 265 |
+
"grad_norm": 4.014983177185059,
|
| 266 |
+
"learning_rate": 4.5833333333333334e-05,
|
| 267 |
+
"loss": 6.7604,
|
| 268 |
+
"step": 74
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 5.88,
|
| 272 |
+
"grad_norm": 5.7904887199401855,
|
| 273 |
+
"learning_rate": 4.166666666666667e-05,
|
| 274 |
+
"loss": 6.5661,
|
| 275 |
+
"step": 76
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 6.0,
|
| 279 |
+
"grad_norm": 2.4023070335388184,
|
| 280 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 281 |
+
"loss": 4.9485,
|
| 282 |
+
"step": 78
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 6.16,
|
| 286 |
+
"grad_norm": 8.205228805541992,
|
| 287 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 288 |
+
"loss": 6.4406,
|
| 289 |
+
"step": 80
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 6.32,
|
| 293 |
+
"grad_norm": 4.756229400634766,
|
| 294 |
+
"learning_rate": 2.916666666666667e-05,
|
| 295 |
+
"loss": 6.701,
|
| 296 |
+
"step": 82
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 6.48,
|
| 300 |
+
"grad_norm": 3.8812973499298096,
|
| 301 |
+
"learning_rate": 2.5e-05,
|
| 302 |
+
"loss": 6.4635,
|
| 303 |
+
"step": 84
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 6.64,
|
| 307 |
+
"grad_norm": 4.376280784606934,
|
| 308 |
+
"learning_rate": 2.0833333333333336e-05,
|
| 309 |
+
"loss": 6.6409,
|
| 310 |
+
"step": 86
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 6.8,
|
| 314 |
+
"grad_norm": 3.6164727210998535,
|
| 315 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 316 |
+
"loss": 6.5085,
|
| 317 |
+
"step": 88
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 6.96,
|
| 321 |
+
"grad_norm": 3.8249928951263428,
|
| 322 |
+
"learning_rate": 1.25e-05,
|
| 323 |
+
"loss": 6.6132,
|
| 324 |
+
"step": 90
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 7.08,
|
| 328 |
+
"grad_norm": 3.8151330947875977,
|
| 329 |
+
"learning_rate": 8.333333333333334e-06,
|
| 330 |
+
"loss": 5.0894,
|
| 331 |
+
"step": 92
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 7.24,
|
| 335 |
+
"grad_norm": 4.085716724395752,
|
| 336 |
+
"learning_rate": 4.166666666666667e-06,
|
| 337 |
+
"loss": 6.5454,
|
| 338 |
+
"step": 94
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 7.4,
|
| 342 |
+
"grad_norm": 5.319828987121582,
|
| 343 |
+
"learning_rate": 0.0,
|
| 344 |
+
"loss": 6.5279,
|
| 345 |
+
"step": 96
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 7.4,
|
| 349 |
+
"step": 96,
|
| 350 |
+
"total_flos": 238308734281248.0,
|
| 351 |
+
"train_loss": 6.6824056307474775,
|
| 352 |
+
"train_runtime": 800.3785,
|
| 353 |
+
"train_samples_per_second": 1.999,
|
| 354 |
+
"train_steps_per_second": 0.12
|
| 355 |
}
|
| 356 |
],
|
| 357 |
"logging_steps": 2,
|
| 358 |
+
"max_steps": 96,
|
| 359 |
"num_input_tokens_seen": 0,
|
| 360 |
+
"num_train_epochs": 8,
|
| 361 |
"save_steps": 500,
|
| 362 |
"stateful_callbacks": {
|
| 363 |
"TrainerControl": {
|
|
|
|
| 371 |
"attributes": {}
|
| 372 |
}
|
| 373 |
},
|
| 374 |
+
"total_flos": 238308734281248.0,
|
| 375 |
"train_batch_size": 2,
|
| 376 |
"trial_name": null,
|
| 377 |
"trial_params": null
|