End of training
Browse files- README.md +3 -1
- trainer_state.json +451 -59
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-lora-aminmaj-chords
|
|
@@ -14,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 14 |
|
| 15 |
# musicgen-small-lora-aminmaj-chords
|
| 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 |
+
- chords
|
| 8 |
- generated_from_trainer
|
| 9 |
model-index:
|
| 10 |
- name: musicgen-small-lora-aminmaj-chords
|
|
|
|
| 16 |
|
| 17 |
# musicgen-small-lora-aminmaj-chords
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [facebook/musicgen-small](https://huggingface.co/facebook/musicgen-small) on the megwei/syntheory dataset.
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
trainer_state.json
CHANGED
|
@@ -1,109 +1,501 @@
|
|
| 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":
|
| 15 |
-
"loss": 76.
|
| 16 |
"step": 2
|
| 17 |
},
|
| 18 |
{
|
| 19 |
-
"epoch": 0.
|
| 20 |
-
"grad_norm":
|
| 21 |
-
"learning_rate":
|
| 22 |
-
"loss":
|
| 23 |
"step": 4
|
| 24 |
},
|
| 25 |
{
|
| 26 |
-
"epoch": 0.
|
| 27 |
-
"grad_norm":
|
| 28 |
-
"learning_rate":
|
| 29 |
-
"loss":
|
| 30 |
"step": 6
|
| 31 |
},
|
| 32 |
{
|
| 33 |
-
"epoch":
|
| 34 |
-
"grad_norm":
|
| 35 |
-
"learning_rate":
|
| 36 |
-
"loss":
|
| 37 |
"step": 8
|
| 38 |
},
|
| 39 |
{
|
| 40 |
-
"epoch":
|
| 41 |
-
"grad_norm":
|
| 42 |
-
"learning_rate":
|
| 43 |
-
"loss":
|
| 44 |
"step": 10
|
| 45 |
},
|
| 46 |
{
|
| 47 |
-
"epoch":
|
| 48 |
-
"grad_norm":
|
| 49 |
-
"learning_rate":
|
| 50 |
-
"loss":
|
| 51 |
"step": 12
|
| 52 |
},
|
| 53 |
{
|
| 54 |
-
"epoch":
|
| 55 |
-
"grad_norm":
|
| 56 |
-
"learning_rate":
|
| 57 |
-
"loss":
|
| 58 |
"step": 14
|
| 59 |
},
|
| 60 |
{
|
| 61 |
-
"epoch":
|
| 62 |
-
"grad_norm":
|
| 63 |
-
"learning_rate":
|
| 64 |
-
"loss":
|
| 65 |
"step": 16
|
| 66 |
},
|
| 67 |
{
|
| 68 |
-
"epoch":
|
| 69 |
-
"grad_norm":
|
| 70 |
-
"learning_rate":
|
| 71 |
-
"loss":
|
| 72 |
"step": 18
|
| 73 |
},
|
| 74 |
{
|
| 75 |
-
"epoch":
|
| 76 |
-
"grad_norm":
|
| 77 |
-
"learning_rate":
|
| 78 |
-
"loss":
|
| 79 |
"step": 20
|
| 80 |
},
|
| 81 |
{
|
| 82 |
-
"epoch":
|
| 83 |
-
"grad_norm":
|
| 84 |
-
"learning_rate":
|
| 85 |
-
"loss":
|
| 86 |
"step": 22
|
| 87 |
},
|
| 88 |
{
|
| 89 |
-
"epoch":
|
| 90 |
-
"grad_norm":
|
| 91 |
-
"learning_rate":
|
| 92 |
-
"loss":
|
| 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": 4,
|
| 109 |
"save_steps": 500,
|
|
@@ -119,7 +511,7 @@
|
|
| 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": 3.898550724637681,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 136,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.057971014492753624,
|
| 13 |
+
"grad_norm": 55.32845687866211,
|
| 14 |
+
"learning_rate": 0.0001985294117647059,
|
| 15 |
+
"loss": 76.4214,
|
| 16 |
"step": 2
|
| 17 |
},
|
| 18 |
{
|
| 19 |
+
"epoch": 0.11594202898550725,
|
| 20 |
+
"grad_norm": 59.647117614746094,
|
| 21 |
+
"learning_rate": 0.00019558823529411764,
|
| 22 |
+
"loss": 66.9992,
|
| 23 |
"step": 4
|
| 24 |
},
|
| 25 |
{
|
| 26 |
+
"epoch": 0.17391304347826086,
|
| 27 |
+
"grad_norm": 37.24838638305664,
|
| 28 |
+
"learning_rate": 0.00019264705882352944,
|
| 29 |
+
"loss": 53.3101,
|
| 30 |
"step": 6
|
| 31 |
},
|
| 32 |
{
|
| 33 |
+
"epoch": 0.2318840579710145,
|
| 34 |
+
"grad_norm": 31.579923629760742,
|
| 35 |
+
"learning_rate": 0.00018970588235294117,
|
| 36 |
+
"loss": 43.1133,
|
| 37 |
"step": 8
|
| 38 |
},
|
| 39 |
{
|
| 40 |
+
"epoch": 0.2898550724637681,
|
| 41 |
+
"grad_norm": 33.05708312988281,
|
| 42 |
+
"learning_rate": 0.00018676470588235297,
|
| 43 |
+
"loss": 41.4356,
|
| 44 |
"step": 10
|
| 45 |
},
|
| 46 |
{
|
| 47 |
+
"epoch": 0.34782608695652173,
|
| 48 |
+
"grad_norm": 19.261913299560547,
|
| 49 |
+
"learning_rate": 0.0001838235294117647,
|
| 50 |
+
"loss": 40.5694,
|
| 51 |
"step": 12
|
| 52 |
},
|
| 53 |
{
|
| 54 |
+
"epoch": 0.4057971014492754,
|
| 55 |
+
"grad_norm": 10.231746673583984,
|
| 56 |
+
"learning_rate": 0.00018088235294117647,
|
| 57 |
+
"loss": 35.4952,
|
| 58 |
"step": 14
|
| 59 |
},
|
| 60 |
{
|
| 61 |
+
"epoch": 0.463768115942029,
|
| 62 |
+
"grad_norm": 12.686185836791992,
|
| 63 |
+
"learning_rate": 0.00017794117647058823,
|
| 64 |
+
"loss": 35.9178,
|
| 65 |
"step": 16
|
| 66 |
},
|
| 67 |
{
|
| 68 |
+
"epoch": 0.5217391304347826,
|
| 69 |
+
"grad_norm": 5.934300899505615,
|
| 70 |
+
"learning_rate": 0.000175,
|
| 71 |
+
"loss": 36.0789,
|
| 72 |
"step": 18
|
| 73 |
},
|
| 74 |
{
|
| 75 |
+
"epoch": 0.5797101449275363,
|
| 76 |
+
"grad_norm": 6.5412092208862305,
|
| 77 |
+
"learning_rate": 0.0001720588235294118,
|
| 78 |
+
"loss": 36.4717,
|
| 79 |
"step": 20
|
| 80 |
},
|
| 81 |
{
|
| 82 |
+
"epoch": 0.6376811594202898,
|
| 83 |
+
"grad_norm": 7.47074031829834,
|
| 84 |
+
"learning_rate": 0.00016911764705882353,
|
| 85 |
+
"loss": 36.1205,
|
| 86 |
"step": 22
|
| 87 |
},
|
| 88 |
{
|
| 89 |
+
"epoch": 0.6956521739130435,
|
| 90 |
+
"grad_norm": 7.197345733642578,
|
| 91 |
+
"learning_rate": 0.00016617647058823532,
|
| 92 |
+
"loss": 35.8026,
|
| 93 |
"step": 24
|
| 94 |
},
|
| 95 |
{
|
| 96 |
+
"epoch": 0.7536231884057971,
|
| 97 |
+
"grad_norm": 8.729438781738281,
|
| 98 |
+
"learning_rate": 0.00016323529411764706,
|
| 99 |
+
"loss": 36.109,
|
| 100 |
+
"step": 26
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.8115942028985508,
|
| 104 |
+
"grad_norm": 10.730180740356445,
|
| 105 |
+
"learning_rate": 0.00016029411764705885,
|
| 106 |
+
"loss": 34.3386,
|
| 107 |
+
"step": 28
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.8695652173913043,
|
| 111 |
+
"grad_norm": 8.981538772583008,
|
| 112 |
+
"learning_rate": 0.0001573529411764706,
|
| 113 |
+
"loss": 33.3324,
|
| 114 |
+
"step": 30
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.927536231884058,
|
| 118 |
+
"grad_norm": 13.125741958618164,
|
| 119 |
+
"learning_rate": 0.00015441176470588238,
|
| 120 |
+
"loss": 34.8168,
|
| 121 |
+
"step": 32
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.9855072463768116,
|
| 125 |
+
"grad_norm": 7.202057361602783,
|
| 126 |
+
"learning_rate": 0.00015147058823529412,
|
| 127 |
+
"loss": 33.9379,
|
| 128 |
+
"step": 34
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.0289855072463767,
|
| 132 |
+
"grad_norm": 7.689969539642334,
|
| 133 |
+
"learning_rate": 0.00014852941176470588,
|
| 134 |
+
"loss": 26.4506,
|
| 135 |
+
"step": 36
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 1.0869565217391304,
|
| 139 |
+
"grad_norm": 12.119438171386719,
|
| 140 |
+
"learning_rate": 0.00014558823529411765,
|
| 141 |
+
"loss": 34.1455,
|
| 142 |
+
"step": 38
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 1.144927536231884,
|
| 146 |
+
"grad_norm": 10.431544303894043,
|
| 147 |
+
"learning_rate": 0.0001426470588235294,
|
| 148 |
+
"loss": 33.6817,
|
| 149 |
+
"step": 40
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.2028985507246377,
|
| 153 |
+
"grad_norm": 6.7350311279296875,
|
| 154 |
+
"learning_rate": 0.00013970588235294118,
|
| 155 |
+
"loss": 34.3042,
|
| 156 |
+
"step": 42
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 1.2608695652173914,
|
| 160 |
+
"grad_norm": 7.63714599609375,
|
| 161 |
+
"learning_rate": 0.00013676470588235294,
|
| 162 |
+
"loss": 33.6539,
|
| 163 |
+
"step": 44
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 1.318840579710145,
|
| 167 |
+
"grad_norm": 14.94995403289795,
|
| 168 |
+
"learning_rate": 0.0001338235294117647,
|
| 169 |
+
"loss": 34.8423,
|
| 170 |
+
"step": 46
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 1.3768115942028984,
|
| 174 |
+
"grad_norm": 5.653194904327393,
|
| 175 |
+
"learning_rate": 0.00013088235294117647,
|
| 176 |
+
"loss": 33.6543,
|
| 177 |
+
"step": 48
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 1.434782608695652,
|
| 181 |
+
"grad_norm": 7.0490946769714355,
|
| 182 |
+
"learning_rate": 0.00012794117647058824,
|
| 183 |
+
"loss": 34.4564,
|
| 184 |
+
"step": 50
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 1.4927536231884058,
|
| 188 |
+
"grad_norm": 9.5311279296875,
|
| 189 |
+
"learning_rate": 0.000125,
|
| 190 |
+
"loss": 34.0708,
|
| 191 |
+
"step": 52
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 1.5507246376811594,
|
| 195 |
+
"grad_norm": 9.313169479370117,
|
| 196 |
+
"learning_rate": 0.00012205882352941178,
|
| 197 |
+
"loss": 35.0762,
|
| 198 |
+
"step": 54
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 1.608695652173913,
|
| 202 |
+
"grad_norm": 6.120841026306152,
|
| 203 |
+
"learning_rate": 0.00011911764705882353,
|
| 204 |
+
"loss": 33.5708,
|
| 205 |
+
"step": 56
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 1.6666666666666665,
|
| 209 |
+
"grad_norm": 19.58426856994629,
|
| 210 |
+
"learning_rate": 0.00011617647058823531,
|
| 211 |
+
"loss": 32.583,
|
| 212 |
+
"step": 58
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 1.7246376811594204,
|
| 216 |
+
"grad_norm": 10.036286354064941,
|
| 217 |
+
"learning_rate": 0.00011323529411764706,
|
| 218 |
+
"loss": 35.4897,
|
| 219 |
+
"step": 60
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 1.7826086956521738,
|
| 223 |
+
"grad_norm": 9.211186408996582,
|
| 224 |
+
"learning_rate": 0.00011029411764705884,
|
| 225 |
+
"loss": 33.5828,
|
| 226 |
+
"step": 62
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 1.8405797101449275,
|
| 230 |
+
"grad_norm": 7.165535926818848,
|
| 231 |
+
"learning_rate": 0.00010735294117647059,
|
| 232 |
+
"loss": 34.0128,
|
| 233 |
+
"step": 64
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 1.8985507246376812,
|
| 237 |
+
"grad_norm": 8.84890079498291,
|
| 238 |
+
"learning_rate": 0.00010441176470588237,
|
| 239 |
+
"loss": 34.0061,
|
| 240 |
+
"step": 66
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 1.9565217391304348,
|
| 244 |
+
"grad_norm": 6.122589111328125,
|
| 245 |
+
"learning_rate": 0.00010147058823529412,
|
| 246 |
+
"loss": 34.1371,
|
| 247 |
+
"step": 68
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 2.0,
|
| 251 |
+
"grad_norm": 5.6373186111450195,
|
| 252 |
+
"learning_rate": 9.852941176470589e-05,
|
| 253 |
+
"loss": 25.4753,
|
| 254 |
+
"step": 70
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 2.0579710144927534,
|
| 258 |
+
"grad_norm": 10.314593315124512,
|
| 259 |
+
"learning_rate": 9.558823529411765e-05,
|
| 260 |
+
"loss": 33.9195,
|
| 261 |
+
"step": 72
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 2.1159420289855073,
|
| 265 |
+
"grad_norm": 8.193323135375977,
|
| 266 |
+
"learning_rate": 9.264705882352942e-05,
|
| 267 |
+
"loss": 33.1874,
|
| 268 |
+
"step": 74
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 2.1739130434782608,
|
| 272 |
+
"grad_norm": 9.070418357849121,
|
| 273 |
+
"learning_rate": 8.970588235294118e-05,
|
| 274 |
+
"loss": 33.3055,
|
| 275 |
+
"step": 76
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 2.2318840579710146,
|
| 279 |
+
"grad_norm": 8.063404083251953,
|
| 280 |
+
"learning_rate": 8.676470588235295e-05,
|
| 281 |
+
"loss": 34.1831,
|
| 282 |
+
"step": 78
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 2.289855072463768,
|
| 286 |
+
"grad_norm": 7.3460516929626465,
|
| 287 |
+
"learning_rate": 8.382352941176471e-05,
|
| 288 |
+
"loss": 32.5002,
|
| 289 |
+
"step": 80
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 2.3478260869565215,
|
| 293 |
+
"grad_norm": 7.9106974601745605,
|
| 294 |
+
"learning_rate": 8.088235294117648e-05,
|
| 295 |
+
"loss": 33.9427,
|
| 296 |
+
"step": 82
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 2.4057971014492754,
|
| 300 |
+
"grad_norm": 6.9293532371521,
|
| 301 |
+
"learning_rate": 7.794117647058824e-05,
|
| 302 |
+
"loss": 32.7437,
|
| 303 |
+
"step": 84
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 2.463768115942029,
|
| 307 |
+
"grad_norm": 5.583312511444092,
|
| 308 |
+
"learning_rate": 7.500000000000001e-05,
|
| 309 |
+
"loss": 32.4636,
|
| 310 |
+
"step": 86
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 2.5217391304347827,
|
| 314 |
+
"grad_norm": 9.602357864379883,
|
| 315 |
+
"learning_rate": 7.205882352941177e-05,
|
| 316 |
+
"loss": 34.4266,
|
| 317 |
+
"step": 88
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 2.579710144927536,
|
| 321 |
+
"grad_norm": 7.29642391204834,
|
| 322 |
+
"learning_rate": 6.911764705882354e-05,
|
| 323 |
+
"loss": 33.2233,
|
| 324 |
+
"step": 90
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 2.63768115942029,
|
| 328 |
+
"grad_norm": 7.916087627410889,
|
| 329 |
+
"learning_rate": 6.61764705882353e-05,
|
| 330 |
+
"loss": 32.328,
|
| 331 |
+
"step": 92
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 2.6956521739130435,
|
| 335 |
+
"grad_norm": 9.700789451599121,
|
| 336 |
+
"learning_rate": 6.323529411764705e-05,
|
| 337 |
+
"loss": 33.3864,
|
| 338 |
+
"step": 94
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 2.753623188405797,
|
| 342 |
+
"grad_norm": 7.925725936889648,
|
| 343 |
+
"learning_rate": 6.0294117647058825e-05,
|
| 344 |
+
"loss": 33.0956,
|
| 345 |
+
"step": 96
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 2.8115942028985508,
|
| 349 |
+
"grad_norm": 7.136451721191406,
|
| 350 |
+
"learning_rate": 5.735294117647059e-05,
|
| 351 |
+
"loss": 34.077,
|
| 352 |
+
"step": 98
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 2.869565217391304,
|
| 356 |
+
"grad_norm": 7.057907581329346,
|
| 357 |
+
"learning_rate": 5.441176470588235e-05,
|
| 358 |
+
"loss": 32.854,
|
| 359 |
+
"step": 100
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 2.927536231884058,
|
| 363 |
+
"grad_norm": 8.482731819152832,
|
| 364 |
+
"learning_rate": 5.147058823529411e-05,
|
| 365 |
+
"loss": 31.9702,
|
| 366 |
+
"step": 102
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 2.9855072463768115,
|
| 370 |
+
"grad_norm": 8.195663452148438,
|
| 371 |
+
"learning_rate": 4.8529411764705885e-05,
|
| 372 |
+
"loss": 32.0516,
|
| 373 |
+
"step": 104
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 3.028985507246377,
|
| 377 |
+
"grad_norm": 13.711084365844727,
|
| 378 |
+
"learning_rate": 4.558823529411765e-05,
|
| 379 |
+
"loss": 23.3778,
|
| 380 |
+
"step": 106
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 3.0869565217391304,
|
| 384 |
+
"grad_norm": 13.546501159667969,
|
| 385 |
+
"learning_rate": 4.2647058823529415e-05,
|
| 386 |
+
"loss": 32.14,
|
| 387 |
+
"step": 108
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 3.1449275362318843,
|
| 391 |
+
"grad_norm": 11.532342910766602,
|
| 392 |
+
"learning_rate": 3.970588235294117e-05,
|
| 393 |
+
"loss": 32.6737,
|
| 394 |
+
"step": 110
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 3.2028985507246377,
|
| 398 |
+
"grad_norm": 9.859041213989258,
|
| 399 |
+
"learning_rate": 3.6764705882352945e-05,
|
| 400 |
+
"loss": 32.2716,
|
| 401 |
+
"step": 112
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 3.260869565217391,
|
| 405 |
+
"grad_norm": 7.993894577026367,
|
| 406 |
+
"learning_rate": 3.382352941176471e-05,
|
| 407 |
+
"loss": 32.8686,
|
| 408 |
+
"step": 114
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 3.318840579710145,
|
| 412 |
+
"grad_norm": 5.935787677764893,
|
| 413 |
+
"learning_rate": 3.0882352941176475e-05,
|
| 414 |
+
"loss": 33.3099,
|
| 415 |
+
"step": 116
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 3.3768115942028984,
|
| 419 |
+
"grad_norm": 8.535140037536621,
|
| 420 |
+
"learning_rate": 2.7941176470588236e-05,
|
| 421 |
+
"loss": 33.1781,
|
| 422 |
+
"step": 118
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 3.4347826086956523,
|
| 426 |
+
"grad_norm": 8.691988945007324,
|
| 427 |
+
"learning_rate": 2.5e-05,
|
| 428 |
+
"loss": 31.1977,
|
| 429 |
+
"step": 120
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 3.4927536231884058,
|
| 433 |
+
"grad_norm": 7.092562675476074,
|
| 434 |
+
"learning_rate": 2.2058823529411766e-05,
|
| 435 |
+
"loss": 32.9427,
|
| 436 |
+
"step": 122
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 3.550724637681159,
|
| 440 |
+
"grad_norm": 10.397586822509766,
|
| 441 |
+
"learning_rate": 1.9117647058823528e-05,
|
| 442 |
+
"loss": 32.8582,
|
| 443 |
+
"step": 124
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 3.608695652173913,
|
| 447 |
+
"grad_norm": 7.606701374053955,
|
| 448 |
+
"learning_rate": 1.6176470588235296e-05,
|
| 449 |
+
"loss": 33.5666,
|
| 450 |
+
"step": 126
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 3.6666666666666665,
|
| 454 |
+
"grad_norm": 9.118799209594727,
|
| 455 |
+
"learning_rate": 1.323529411764706e-05,
|
| 456 |
+
"loss": 32.2489,
|
| 457 |
+
"step": 128
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 3.7246376811594204,
|
| 461 |
+
"grad_norm": 8.418676376342773,
|
| 462 |
+
"learning_rate": 1.0294117647058824e-05,
|
| 463 |
+
"loss": 32.8995,
|
| 464 |
+
"step": 130
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 3.782608695652174,
|
| 468 |
+
"grad_norm": 7.379878044128418,
|
| 469 |
+
"learning_rate": 7.3529411764705884e-06,
|
| 470 |
+
"loss": 33.5503,
|
| 471 |
+
"step": 132
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 3.8405797101449277,
|
| 475 |
+
"grad_norm": 7.183637619018555,
|
| 476 |
+
"learning_rate": 4.411764705882353e-06,
|
| 477 |
+
"loss": 31.911,
|
| 478 |
+
"step": 134
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 3.898550724637681,
|
| 482 |
+
"grad_norm": 12.431236267089844,
|
| 483 |
+
"learning_rate": 1.4705882352941177e-06,
|
| 484 |
+
"loss": 31.6491,
|
| 485 |
+
"step": 136
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 3.898550724637681,
|
| 489 |
+
"step": 136,
|
| 490 |
+
"total_flos": 29261690983296.0,
|
| 491 |
+
"train_loss": 35.055379671208996,
|
| 492 |
+
"train_runtime": 354.4991,
|
| 493 |
+
"train_samples_per_second": 6.229,
|
| 494 |
+
"train_steps_per_second": 0.384
|
| 495 |
}
|
| 496 |
],
|
| 497 |
"logging_steps": 2,
|
| 498 |
+
"max_steps": 136,
|
| 499 |
"num_input_tokens_seen": 0,
|
| 500 |
"num_train_epochs": 4,
|
| 501 |
"save_steps": 500,
|
|
|
|
| 511 |
"attributes": {}
|
| 512 |
}
|
| 513 |
},
|
| 514 |
+
"total_flos": 29261690983296.0,
|
| 515 |
"train_batch_size": 2,
|
| 516 |
"trial_name": null,
|
| 517 |
"trial_params": null
|