Training in progress, epoch 0
Browse files- all_results.json +8 -0
- pytorch_model.bin +1 -1
- runs/Jul31_02-05-34_4d8ae2de2193/events.out.tfevents.1690769311.4d8ae2de2193.4377.10 +3 -0
- runs/Jul31_02-05-34_4d8ae2de2193/events.out.tfevents.1690769374.4d8ae2de2193.4377.11 +3 -0
- runs/Jul31_02-11-10_4d8ae2de2193/events.out.tfevents.1690769489.4d8ae2de2193.4377.12 +3 -0
- train_results.json +8 -0
- trainer_state.json +187 -0
- training_args.bin +1 -1
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.94,
|
| 3 |
+
"total_flos": 8.866156938264576e+16,
|
| 4 |
+
"train_loss": 0.011351865083724988,
|
| 5 |
+
"train_runtime": 119.1901,
|
| 6 |
+
"train_samples_per_second": 13.189,
|
| 7 |
+
"train_steps_per_second": 0.403
|
| 8 |
+
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 196637789
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d3ba9cc4dc3b0fb5bb67f5c7cb70128447beeb4b9d167f2b31c58cd9fcfe7fd4
|
| 3 |
size 196637789
|
runs/Jul31_02-05-34_4d8ae2de2193/events.out.tfevents.1690769311.4d8ae2de2193.4377.10
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:57fe32880ef9fc411719f5157c6ef0f98e66be7ba33046b0b5033c35c1263c22
|
| 3 |
+
size 6782
|
runs/Jul31_02-05-34_4d8ae2de2193/events.out.tfevents.1690769374.4d8ae2de2193.4377.11
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5552828d72c49b79e2f029e2e940d8731177960d4eef96d17348b5972cb3cf55
|
| 3 |
+
size 6782
|
runs/Jul31_02-11-10_4d8ae2de2193/events.out.tfevents.1690769489.4d8ae2de2193.4377.12
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3721b2686b39dc8ff650ee93ea2d91a720271d0a3151a972a00cbbeb5c3153c9
|
| 3 |
+
size 6733
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.94,
|
| 3 |
+
"total_flos": 8.866156938264576e+16,
|
| 4 |
+
"train_loss": 0.011351865083724988,
|
| 5 |
+
"train_runtime": 119.1901,
|
| 6 |
+
"train_samples_per_second": 13.189,
|
| 7 |
+
"train_steps_per_second": 0.403
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,187 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9886363636363636,
|
| 3 |
+
"best_model_checkpoint": "focal-patacotron/checkpoint-48",
|
| 4 |
+
"epoch": 1.9393939393939394,
|
| 5 |
+
"global_step": 48,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.08,
|
| 12 |
+
"learning_rate": 2e-05,
|
| 13 |
+
"loss": 0.0018,
|
| 14 |
+
"step": 2
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.16,
|
| 18 |
+
"learning_rate": 4e-05,
|
| 19 |
+
"loss": 0.0023,
|
| 20 |
+
"step": 4
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.24,
|
| 24 |
+
"learning_rate": 4.883720930232558e-05,
|
| 25 |
+
"loss": 0.0042,
|
| 26 |
+
"step": 6
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.32,
|
| 30 |
+
"learning_rate": 4.651162790697675e-05,
|
| 31 |
+
"loss": 0.0545,
|
| 32 |
+
"step": 8
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.4,
|
| 36 |
+
"learning_rate": 4.418604651162791e-05,
|
| 37 |
+
"loss": 0.0046,
|
| 38 |
+
"step": 10
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.48,
|
| 42 |
+
"learning_rate": 4.186046511627907e-05,
|
| 43 |
+
"loss": 0.0044,
|
| 44 |
+
"step": 12
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.57,
|
| 48 |
+
"learning_rate": 3.953488372093023e-05,
|
| 49 |
+
"loss": 0.001,
|
| 50 |
+
"step": 14
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.65,
|
| 54 |
+
"learning_rate": 3.7209302325581394e-05,
|
| 55 |
+
"loss": 0.0107,
|
| 56 |
+
"step": 16
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.73,
|
| 60 |
+
"learning_rate": 3.488372093023256e-05,
|
| 61 |
+
"loss": 0.0002,
|
| 62 |
+
"step": 18
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.81,
|
| 66 |
+
"learning_rate": 3.2558139534883724e-05,
|
| 67 |
+
"loss": 0.0172,
|
| 68 |
+
"step": 20
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.89,
|
| 72 |
+
"learning_rate": 3.0232558139534883e-05,
|
| 73 |
+
"loss": 0.0001,
|
| 74 |
+
"step": 22
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.97,
|
| 78 |
+
"learning_rate": 2.7906976744186048e-05,
|
| 79 |
+
"loss": 0.0043,
|
| 80 |
+
"step": 24
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.97,
|
| 84 |
+
"eval_accuracy": 0.9772727272727273,
|
| 85 |
+
"eval_loss": 0.06200653687119484,
|
| 86 |
+
"eval_runtime": 1.6222,
|
| 87 |
+
"eval_samples_per_second": 54.248,
|
| 88 |
+
"eval_steps_per_second": 6.781,
|
| 89 |
+
"step": 24
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 1.05,
|
| 93 |
+
"learning_rate": 2.5581395348837212e-05,
|
| 94 |
+
"loss": 0.0,
|
| 95 |
+
"step": 26
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 1.13,
|
| 99 |
+
"learning_rate": 2.3255813953488374e-05,
|
| 100 |
+
"loss": 0.0151,
|
| 101 |
+
"step": 28
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 1.21,
|
| 105 |
+
"learning_rate": 2.0930232558139536e-05,
|
| 106 |
+
"loss": 0.0006,
|
| 107 |
+
"step": 30
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 1.29,
|
| 111 |
+
"learning_rate": 1.8604651162790697e-05,
|
| 112 |
+
"loss": 0.0001,
|
| 113 |
+
"step": 32
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 1.37,
|
| 117 |
+
"learning_rate": 1.6279069767441862e-05,
|
| 118 |
+
"loss": 0.1418,
|
| 119 |
+
"step": 34
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 1.45,
|
| 123 |
+
"learning_rate": 1.3953488372093024e-05,
|
| 124 |
+
"loss": 0.003,
|
| 125 |
+
"step": 36
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 1.54,
|
| 129 |
+
"learning_rate": 1.1627906976744187e-05,
|
| 130 |
+
"loss": 0.0002,
|
| 131 |
+
"step": 38
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 1.62,
|
| 135 |
+
"learning_rate": 9.302325581395349e-06,
|
| 136 |
+
"loss": 0.0063,
|
| 137 |
+
"step": 40
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.7,
|
| 141 |
+
"learning_rate": 6.976744186046512e-06,
|
| 142 |
+
"loss": 0.0,
|
| 143 |
+
"step": 42
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 1.78,
|
| 147 |
+
"learning_rate": 4.651162790697674e-06,
|
| 148 |
+
"loss": 0.0,
|
| 149 |
+
"step": 44
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.86,
|
| 153 |
+
"learning_rate": 2.325581395348837e-06,
|
| 154 |
+
"loss": 0.0002,
|
| 155 |
+
"step": 46
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 1.94,
|
| 159 |
+
"learning_rate": 0.0,
|
| 160 |
+
"loss": 0.0,
|
| 161 |
+
"step": 48
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 1.94,
|
| 165 |
+
"eval_accuracy": 0.9886363636363636,
|
| 166 |
+
"eval_loss": 0.013738363049924374,
|
| 167 |
+
"eval_runtime": 1.5171,
|
| 168 |
+
"eval_samples_per_second": 58.006,
|
| 169 |
+
"eval_steps_per_second": 7.251,
|
| 170 |
+
"step": 48
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 1.94,
|
| 174 |
+
"step": 48,
|
| 175 |
+
"total_flos": 8.866156938264576e+16,
|
| 176 |
+
"train_loss": 0.011351865083724988,
|
| 177 |
+
"train_runtime": 119.1901,
|
| 178 |
+
"train_samples_per_second": 13.189,
|
| 179 |
+
"train_steps_per_second": 0.403
|
| 180 |
+
}
|
| 181 |
+
],
|
| 182 |
+
"max_steps": 48,
|
| 183 |
+
"num_train_epochs": 2,
|
| 184 |
+
"total_flos": 8.866156938264576e+16,
|
| 185 |
+
"trial_name": null,
|
| 186 |
+
"trial_params": null
|
| 187 |
+
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3963
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:abe48f955ed086a1f8413c7174f5b024fd23357ca933c578285e42106e3e0f7a
|
| 3 |
size 3963
|