Commit
•
d1eaad8
1
Parent(s):
9748a5f
End of training
Browse files- README.md +5 -3
- all_results.json +15 -0
- eval_results.json +9 -0
- train_results.json +9 -0
- trainer_state.json +387 -0
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: salami_truncsplit_model_mid
|
|
@@ -14,10 +16,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 14 |
|
| 15 |
# salami_truncsplit_model_mid
|
| 16 |
|
| 17 |
-
This model is a fine-tuned version of [facebook/musicgen-small](https://huggingface.co/facebook/musicgen-small) on
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
-
- Loss:
|
| 20 |
-
- Clap: 0.
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
|
|
| 3 |
license: cc-by-nc-4.0
|
| 4 |
base_model: facebook/musicgen-small
|
| 5 |
tags:
|
| 6 |
+
- text-to-audio
|
| 7 |
+
- taufiqsyed/salami_cleaned_sampled
|
| 8 |
- generated_from_trainer
|
| 9 |
model-index:
|
| 10 |
- name: salami_truncsplit_model_mid
|
|
|
|
| 16 |
|
| 17 |
# salami_truncsplit_model_mid
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [facebook/musicgen-small](https://huggingface.co/facebook/musicgen-small) on the TAUFIQSYED/SALAMI_CLEANED_SAMPLED - DEFAULT dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 6.5818
|
| 22 |
+
- Clap: 0.1330
|
| 23 |
|
| 24 |
## Model description
|
| 25 |
|
all_results.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.7199999999999998,
|
| 3 |
+
"eval_clap": 0.1329956203699112,
|
| 4 |
+
"eval_loss": 6.581780910491943,
|
| 5 |
+
"eval_runtime": 202.5749,
|
| 6 |
+
"eval_samples": 32,
|
| 7 |
+
"eval_samples_per_second": 0.158,
|
| 8 |
+
"eval_steps_per_second": 0.158,
|
| 9 |
+
"total_flos": 180716776957944.0,
|
| 10 |
+
"train_loss": 6.281136025985082,
|
| 11 |
+
"train_runtime": 1764.029,
|
| 12 |
+
"train_samples": 400,
|
| 13 |
+
"train_samples_per_second": 0.907,
|
| 14 |
+
"train_steps_per_second": 0.027
|
| 15 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.7199999999999998,
|
| 3 |
+
"eval_clap": 0.1329956203699112,
|
| 4 |
+
"eval_loss": 6.581780910491943,
|
| 5 |
+
"eval_runtime": 202.5749,
|
| 6 |
+
"eval_samples": 32,
|
| 7 |
+
"eval_samples_per_second": 0.158,
|
| 8 |
+
"eval_steps_per_second": 0.158
|
| 9 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.7199999999999998,
|
| 3 |
+
"total_flos": 180716776957944.0,
|
| 4 |
+
"train_loss": 6.281136025985082,
|
| 5 |
+
"train_runtime": 1764.029,
|
| 6 |
+
"train_samples": 400,
|
| 7 |
+
"train_samples_per_second": 0.907,
|
| 8 |
+
"train_steps_per_second": 0.027
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,387 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.7199999999999998,
|
| 5 |
+
"eval_steps": 25,
|
| 6 |
+
"global_step": 48,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.08,
|
| 13 |
+
"grad_norm": 90.5236587524414,
|
| 14 |
+
"learning_rate": 0.0002,
|
| 15 |
+
"loss": 9.8877,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.16,
|
| 20 |
+
"grad_norm": 60.02783966064453,
|
| 21 |
+
"learning_rate": 0.0002,
|
| 22 |
+
"loss": 9.4404,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.24,
|
| 27 |
+
"grad_norm": 102.20321655273438,
|
| 28 |
+
"learning_rate": 0.0002,
|
| 29 |
+
"loss": 8.8638,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.32,
|
| 34 |
+
"grad_norm": 82.49861145019531,
|
| 35 |
+
"learning_rate": 0.0002,
|
| 36 |
+
"loss": 8.0872,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.4,
|
| 41 |
+
"grad_norm": 81.60125732421875,
|
| 42 |
+
"learning_rate": 0.0002,
|
| 43 |
+
"loss": 7.2292,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.48,
|
| 48 |
+
"grad_norm": 52.2266960144043,
|
| 49 |
+
"learning_rate": 0.0002,
|
| 50 |
+
"loss": 7.0472,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.56,
|
| 55 |
+
"grad_norm": 75.96226501464844,
|
| 56 |
+
"learning_rate": 0.0002,
|
| 57 |
+
"loss": 7.2919,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.64,
|
| 62 |
+
"grad_norm": 70.42675018310547,
|
| 63 |
+
"learning_rate": 0.0002,
|
| 64 |
+
"loss": 7.1477,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.72,
|
| 69 |
+
"grad_norm": 52.09629821777344,
|
| 70 |
+
"learning_rate": 0.0002,
|
| 71 |
+
"loss": 6.899,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.8,
|
| 76 |
+
"grad_norm": 28.537267684936523,
|
| 77 |
+
"learning_rate": 0.0002,
|
| 78 |
+
"loss": 6.7016,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.88,
|
| 83 |
+
"grad_norm": 29.203533172607422,
|
| 84 |
+
"learning_rate": 0.0002,
|
| 85 |
+
"loss": 6.1981,
|
| 86 |
+
"step": 11
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.96,
|
| 90 |
+
"grad_norm": 23.664485931396484,
|
| 91 |
+
"learning_rate": 0.0002,
|
| 92 |
+
"loss": 6.3924,
|
| 93 |
+
"step": 12
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 1.0,
|
| 97 |
+
"grad_norm": 9.723264694213867,
|
| 98 |
+
"learning_rate": 0.0002,
|
| 99 |
+
"loss": 3.2305,
|
| 100 |
+
"step": 13
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 1.08,
|
| 104 |
+
"grad_norm": 18.88973045349121,
|
| 105 |
+
"learning_rate": 0.0002,
|
| 106 |
+
"loss": 6.3592,
|
| 107 |
+
"step": 14
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 1.16,
|
| 111 |
+
"grad_norm": 20.770938873291016,
|
| 112 |
+
"learning_rate": 0.0002,
|
| 113 |
+
"loss": 6.1203,
|
| 114 |
+
"step": 15
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 1.24,
|
| 118 |
+
"grad_norm": 10.570067405700684,
|
| 119 |
+
"learning_rate": 0.0002,
|
| 120 |
+
"loss": 6.4217,
|
| 121 |
+
"step": 16
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 1.32,
|
| 125 |
+
"grad_norm": 13.833821296691895,
|
| 126 |
+
"learning_rate": 0.0002,
|
| 127 |
+
"loss": 6.439,
|
| 128 |
+
"step": 17
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.4,
|
| 132 |
+
"grad_norm": 19.160987854003906,
|
| 133 |
+
"learning_rate": 0.0002,
|
| 134 |
+
"loss": 5.8242,
|
| 135 |
+
"step": 18
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 1.48,
|
| 139 |
+
"grad_norm": 10.99656867980957,
|
| 140 |
+
"learning_rate": 0.0002,
|
| 141 |
+
"loss": 6.1287,
|
| 142 |
+
"step": 19
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 1.56,
|
| 146 |
+
"grad_norm": 16.58768081665039,
|
| 147 |
+
"learning_rate": 0.0002,
|
| 148 |
+
"loss": 6.408,
|
| 149 |
+
"step": 20
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.6400000000000001,
|
| 153 |
+
"grad_norm": 11.93716812133789,
|
| 154 |
+
"learning_rate": 0.0002,
|
| 155 |
+
"loss": 6.3103,
|
| 156 |
+
"step": 21
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 1.72,
|
| 160 |
+
"grad_norm": 9.053961753845215,
|
| 161 |
+
"learning_rate": 0.0002,
|
| 162 |
+
"loss": 6.2692,
|
| 163 |
+
"step": 22
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 1.8,
|
| 167 |
+
"grad_norm": 19.67817497253418,
|
| 168 |
+
"learning_rate": 0.0002,
|
| 169 |
+
"loss": 5.9086,
|
| 170 |
+
"step": 23
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 1.88,
|
| 174 |
+
"grad_norm": 10.540741920471191,
|
| 175 |
+
"learning_rate": 0.0002,
|
| 176 |
+
"loss": 6.1991,
|
| 177 |
+
"step": 24
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 1.96,
|
| 181 |
+
"grad_norm": 8.84691333770752,
|
| 182 |
+
"learning_rate": 0.0002,
|
| 183 |
+
"loss": 6.1812,
|
| 184 |
+
"step": 25
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 1.96,
|
| 188 |
+
"eval_clap": 0.13957726955413818,
|
| 189 |
+
"eval_loss": 5.896897315979004,
|
| 190 |
+
"eval_runtime": 206.5396,
|
| 191 |
+
"eval_samples_per_second": 0.155,
|
| 192 |
+
"eval_steps_per_second": 0.155,
|
| 193 |
+
"step": 25
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 2.0,
|
| 197 |
+
"grad_norm": 3.9374849796295166,
|
| 198 |
+
"learning_rate": 0.0002,
|
| 199 |
+
"loss": 3.1408,
|
| 200 |
+
"step": 26
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 2.08,
|
| 204 |
+
"grad_norm": 6.420533180236816,
|
| 205 |
+
"learning_rate": 0.0002,
|
| 206 |
+
"loss": 6.196,
|
| 207 |
+
"step": 27
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 2.16,
|
| 211 |
+
"grad_norm": 10.713640213012695,
|
| 212 |
+
"learning_rate": 0.0002,
|
| 213 |
+
"loss": 6.4188,
|
| 214 |
+
"step": 28
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 2.24,
|
| 218 |
+
"grad_norm": 13.720645904541016,
|
| 219 |
+
"learning_rate": 0.0002,
|
| 220 |
+
"loss": 5.9628,
|
| 221 |
+
"step": 29
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 2.32,
|
| 225 |
+
"grad_norm": 13.317567825317383,
|
| 226 |
+
"learning_rate": 0.0002,
|
| 227 |
+
"loss": 6.1474,
|
| 228 |
+
"step": 30
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 2.4,
|
| 232 |
+
"grad_norm": 11.3407621383667,
|
| 233 |
+
"learning_rate": 0.0002,
|
| 234 |
+
"loss": 5.9697,
|
| 235 |
+
"step": 31
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 2.48,
|
| 239 |
+
"grad_norm": 9.393121719360352,
|
| 240 |
+
"learning_rate": 0.0002,
|
| 241 |
+
"loss": 6.1152,
|
| 242 |
+
"step": 32
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 2.56,
|
| 246 |
+
"grad_norm": 14.54958438873291,
|
| 247 |
+
"learning_rate": 0.0002,
|
| 248 |
+
"loss": 5.7045,
|
| 249 |
+
"step": 33
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 2.64,
|
| 253 |
+
"grad_norm": 13.25341796875,
|
| 254 |
+
"learning_rate": 0.0002,
|
| 255 |
+
"loss": 6.2739,
|
| 256 |
+
"step": 34
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 2.7199999999999998,
|
| 260 |
+
"grad_norm": 10.817360877990723,
|
| 261 |
+
"learning_rate": 0.0002,
|
| 262 |
+
"loss": 5.9946,
|
| 263 |
+
"step": 35
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 2.8,
|
| 267 |
+
"grad_norm": 18.011138916015625,
|
| 268 |
+
"learning_rate": 0.0002,
|
| 269 |
+
"loss": 5.5463,
|
| 270 |
+
"step": 36
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 2.88,
|
| 274 |
+
"grad_norm": 18.857688903808594,
|
| 275 |
+
"learning_rate": 0.0002,
|
| 276 |
+
"loss": 6.4324,
|
| 277 |
+
"step": 37
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 2.96,
|
| 281 |
+
"grad_norm": 10.496877670288086,
|
| 282 |
+
"learning_rate": 0.0002,
|
| 283 |
+
"loss": 5.9915,
|
| 284 |
+
"step": 38
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 3.0,
|
| 288 |
+
"grad_norm": 4.552528381347656,
|
| 289 |
+
"learning_rate": 0.0002,
|
| 290 |
+
"loss": 3.1022,
|
| 291 |
+
"step": 39
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 3.08,
|
| 295 |
+
"grad_norm": 9.081900596618652,
|
| 296 |
+
"learning_rate": 0.0002,
|
| 297 |
+
"loss": 6.0394,
|
| 298 |
+
"step": 40
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 3.16,
|
| 302 |
+
"grad_norm": 13.829048156738281,
|
| 303 |
+
"learning_rate": 0.0002,
|
| 304 |
+
"loss": 5.9436,
|
| 305 |
+
"step": 41
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 3.24,
|
| 309 |
+
"grad_norm": 6.3993120193481445,
|
| 310 |
+
"learning_rate": 0.0002,
|
| 311 |
+
"loss": 6.276,
|
| 312 |
+
"step": 42
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 3.32,
|
| 316 |
+
"grad_norm": 20.436588287353516,
|
| 317 |
+
"learning_rate": 0.0002,
|
| 318 |
+
"loss": 5.7975,
|
| 319 |
+
"step": 43
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 3.4,
|
| 323 |
+
"grad_norm": 7.475179672241211,
|
| 324 |
+
"learning_rate": 0.0002,
|
| 325 |
+
"loss": 6.1817,
|
| 326 |
+
"step": 44
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 3.48,
|
| 330 |
+
"grad_norm": 17.927181243896484,
|
| 331 |
+
"learning_rate": 0.0002,
|
| 332 |
+
"loss": 5.8574,
|
| 333 |
+
"step": 45
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 3.56,
|
| 337 |
+
"grad_norm": 18.49729347229004,
|
| 338 |
+
"learning_rate": 0.0002,
|
| 339 |
+
"loss": 5.4645,
|
| 340 |
+
"step": 46
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 3.64,
|
| 344 |
+
"grad_norm": 16.93431854248047,
|
| 345 |
+
"learning_rate": 0.0002,
|
| 346 |
+
"loss": 5.7863,
|
| 347 |
+
"step": 47
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 3.7199999999999998,
|
| 351 |
+
"grad_norm": 10.554439544677734,
|
| 352 |
+
"learning_rate": 0.0002,
|
| 353 |
+
"loss": 6.1658,
|
| 354 |
+
"step": 48
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 3.7199999999999998,
|
| 358 |
+
"step": 48,
|
| 359 |
+
"total_flos": 180716776957944.0,
|
| 360 |
+
"train_loss": 6.281136025985082,
|
| 361 |
+
"train_runtime": 1764.029,
|
| 362 |
+
"train_samples_per_second": 0.907,
|
| 363 |
+
"train_steps_per_second": 0.027
|
| 364 |
+
}
|
| 365 |
+
],
|
| 366 |
+
"logging_steps": 1.0,
|
| 367 |
+
"max_steps": 48,
|
| 368 |
+
"num_input_tokens_seen": 0,
|
| 369 |
+
"num_train_epochs": 4,
|
| 370 |
+
"save_steps": 500,
|
| 371 |
+
"stateful_callbacks": {
|
| 372 |
+
"TrainerControl": {
|
| 373 |
+
"args": {
|
| 374 |
+
"should_epoch_stop": false,
|
| 375 |
+
"should_evaluate": false,
|
| 376 |
+
"should_log": false,
|
| 377 |
+
"should_save": true,
|
| 378 |
+
"should_training_stop": true
|
| 379 |
+
},
|
| 380 |
+
"attributes": {}
|
| 381 |
+
}
|
| 382 |
+
},
|
| 383 |
+
"total_flos": 180716776957944.0,
|
| 384 |
+
"train_batch_size": 2,
|
| 385 |
+
"trial_name": null,
|
| 386 |
+
"trial_params": null
|
| 387 |
+
}
|