Commit
•
b91a3a8
1
Parent(s):
de66726
Training in progress, step 400
Browse files- checkpoint-100/trainer_state.json +0 -85
- {checkpoint-100 → checkpoint-400}/config.json +0 -0
- {checkpoint-100 → checkpoint-400}/optimizer.pt +2 -2
- {checkpoint-100 → checkpoint-400}/preprocessor_config.json +0 -0
- {checkpoint-100 → checkpoint-400}/pytorch_model.bin +1 -1
- {checkpoint-100 → checkpoint-400}/rng_state.pth +1 -1
- {checkpoint-100 → checkpoint-400}/scaler.pt +1 -1
- {checkpoint-100 → checkpoint-400}/scheduler.pt +1 -1
- checkpoint-400/trainer_state.json +292 -0
- {checkpoint-100 → checkpoint-400}/training_args.bin +0 -0
- pytorch_model.bin +1 -1
checkpoint-100/trainer_state.json
DELETED
|
@@ -1,85 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"best_metric": null,
|
| 3 |
-
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0.0461361014994233,
|
| 5 |
-
"global_step": 100,
|
| 6 |
-
"is_hyper_param_search": false,
|
| 7 |
-
"is_local_process_zero": true,
|
| 8 |
-
"is_world_process_zero": true,
|
| 9 |
-
"log_history": [
|
| 10 |
-
{
|
| 11 |
-
"epoch": 0.0,
|
| 12 |
-
"learning_rate": 5.725190839694656e-06,
|
| 13 |
-
"loss": 12.7187,
|
| 14 |
-
"step": 10
|
| 15 |
-
},
|
| 16 |
-
{
|
| 17 |
-
"epoch": 0.01,
|
| 18 |
-
"learning_rate": 1.1450381679389312e-05,
|
| 19 |
-
"loss": 13.2124,
|
| 20 |
-
"step": 20
|
| 21 |
-
},
|
| 22 |
-
{
|
| 23 |
-
"epoch": 0.01,
|
| 24 |
-
"learning_rate": 1.6603053435114505e-05,
|
| 25 |
-
"loss": 14.1489,
|
| 26 |
-
"step": 30
|
| 27 |
-
},
|
| 28 |
-
{
|
| 29 |
-
"epoch": 0.02,
|
| 30 |
-
"learning_rate": 2.1755725190839692e-05,
|
| 31 |
-
"loss": 25.9008,
|
| 32 |
-
"step": 40
|
| 33 |
-
},
|
| 34 |
-
{
|
| 35 |
-
"epoch": 0.02,
|
| 36 |
-
"learning_rate": 2.6908396946564882e-05,
|
| 37 |
-
"loss": 31.3861,
|
| 38 |
-
"step": 50
|
| 39 |
-
},
|
| 40 |
-
{
|
| 41 |
-
"epoch": 0.03,
|
| 42 |
-
"learning_rate": 3.263358778625954e-05,
|
| 43 |
-
"loss": 8.9557,
|
| 44 |
-
"step": 60
|
| 45 |
-
},
|
| 46 |
-
{
|
| 47 |
-
"epoch": 0.03,
|
| 48 |
-
"learning_rate": 3.835877862595419e-05,
|
| 49 |
-
"loss": 5.8443,
|
| 50 |
-
"step": 70
|
| 51 |
-
},
|
| 52 |
-
{
|
| 53 |
-
"epoch": 0.04,
|
| 54 |
-
"learning_rate": 4.408396946564885e-05,
|
| 55 |
-
"loss": 4.3173,
|
| 56 |
-
"step": 80
|
| 57 |
-
},
|
| 58 |
-
{
|
| 59 |
-
"epoch": 0.04,
|
| 60 |
-
"learning_rate": 4.980916030534351e-05,
|
| 61 |
-
"loss": 4.7444,
|
| 62 |
-
"step": 90
|
| 63 |
-
},
|
| 64 |
-
{
|
| 65 |
-
"epoch": 0.05,
|
| 66 |
-
"learning_rate": 5.49618320610687e-05,
|
| 67 |
-
"loss": 4.542,
|
| 68 |
-
"step": 100
|
| 69 |
-
},
|
| 70 |
-
{
|
| 71 |
-
"epoch": 0.05,
|
| 72 |
-
"eval_loss": 3.579599618911743,
|
| 73 |
-
"eval_runtime": 132.6751,
|
| 74 |
-
"eval_samples_per_second": 34.822,
|
| 75 |
-
"eval_steps_per_second": 1.093,
|
| 76 |
-
"eval_wer": 1.0,
|
| 77 |
-
"step": 100
|
| 78 |
-
}
|
| 79 |
-
],
|
| 80 |
-
"max_steps": 6501,
|
| 81 |
-
"num_train_epochs": 3,
|
| 82 |
-
"total_flos": 1.8918949073894093e+18,
|
| 83 |
-
"trial_name": null,
|
| 84 |
-
"trial_params": null
|
| 85 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
{checkpoint-100 → checkpoint-400}/config.json
RENAMED
|
File without changes
|
{checkpoint-100 → checkpoint-400}/optimizer.pt
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bf161ebd936c8ad7c9d8aa09d6cfacea3c1f1b7830996289de6c09c5b17597b5
|
| 3 |
+
size 2490346001
|
{checkpoint-100 → checkpoint-400}/preprocessor_config.json
RENAMED
|
File without changes
|
{checkpoint-100 → checkpoint-400}/pytorch_model.bin
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1262067185
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3615598ae508e9ab81f60392073741effb41877fe43b3faf976c78e298f8b7ce
|
| 3 |
size 1262067185
|
{checkpoint-100 → checkpoint-400}/rng_state.pth
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14567
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6539ac9bd8d5283f6052bfeb40b134408bae7309c4985eb1a92a55b39e90aa50
|
| 3 |
size 14567
|
{checkpoint-100 → checkpoint-400}/scaler.pt
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 559
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c521307eec3705f40e440815e13caacabdaf54c21d0d7c9b9858aad14a054aa
|
| 3 |
size 559
|
{checkpoint-100 → checkpoint-400}/scheduler.pt
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 623
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:46afeb3652f3b68ce369c52d170c5c98db425df4214d18b1edefe2376ca2a92e
|
| 3 |
size 623
|
checkpoint-400/trainer_state.json
ADDED
|
@@ -0,0 +1,292 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.1845444059976932,
|
| 5 |
+
"global_step": 400,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.0,
|
| 12 |
+
"learning_rate": 5.725190839694656e-06,
|
| 13 |
+
"loss": 12.7187,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.01,
|
| 18 |
+
"learning_rate": 1.1450381679389312e-05,
|
| 19 |
+
"loss": 13.2124,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.01,
|
| 24 |
+
"learning_rate": 1.6603053435114505e-05,
|
| 25 |
+
"loss": 14.1489,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.02,
|
| 30 |
+
"learning_rate": 2.1755725190839692e-05,
|
| 31 |
+
"loss": 25.9008,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.02,
|
| 36 |
+
"learning_rate": 2.6908396946564882e-05,
|
| 37 |
+
"loss": 31.3861,
|
| 38 |
+
"step": 50
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.03,
|
| 42 |
+
"learning_rate": 3.263358778625954e-05,
|
| 43 |
+
"loss": 8.9557,
|
| 44 |
+
"step": 60
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.03,
|
| 48 |
+
"learning_rate": 3.835877862595419e-05,
|
| 49 |
+
"loss": 5.8443,
|
| 50 |
+
"step": 70
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.04,
|
| 54 |
+
"learning_rate": 4.408396946564885e-05,
|
| 55 |
+
"loss": 4.3173,
|
| 56 |
+
"step": 80
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.04,
|
| 60 |
+
"learning_rate": 4.980916030534351e-05,
|
| 61 |
+
"loss": 4.7444,
|
| 62 |
+
"step": 90
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.05,
|
| 66 |
+
"learning_rate": 5.49618320610687e-05,
|
| 67 |
+
"loss": 4.542,
|
| 68 |
+
"step": 100
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.05,
|
| 72 |
+
"eval_loss": 3.579599618911743,
|
| 73 |
+
"eval_runtime": 132.6751,
|
| 74 |
+
"eval_samples_per_second": 34.822,
|
| 75 |
+
"eval_steps_per_second": 1.093,
|
| 76 |
+
"eval_wer": 1.0,
|
| 77 |
+
"step": 100
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 0.05,
|
| 81 |
+
"learning_rate": 6.0687022900763354e-05,
|
| 82 |
+
"loss": 3.3873,
|
| 83 |
+
"step": 110
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 0.06,
|
| 87 |
+
"learning_rate": 6.641221374045802e-05,
|
| 88 |
+
"loss": 3.1783,
|
| 89 |
+
"step": 120
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.06,
|
| 93 |
+
"learning_rate": 7.213740458015267e-05,
|
| 94 |
+
"loss": 3.1672,
|
| 95 |
+
"step": 130
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.06,
|
| 99 |
+
"learning_rate": 7.494113029827315e-05,
|
| 100 |
+
"loss": 3.4915,
|
| 101 |
+
"step": 140
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.07,
|
| 105 |
+
"learning_rate": 7.483516483516483e-05,
|
| 106 |
+
"loss": 3.7276,
|
| 107 |
+
"step": 150
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.07,
|
| 111 |
+
"learning_rate": 7.471742543171114e-05,
|
| 112 |
+
"loss": 3.2435,
|
| 113 |
+
"step": 160
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 0.08,
|
| 117 |
+
"learning_rate": 7.459968602825744e-05,
|
| 118 |
+
"loss": 3.0634,
|
| 119 |
+
"step": 170
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 0.08,
|
| 123 |
+
"learning_rate": 7.448194662480377e-05,
|
| 124 |
+
"loss": 3.0859,
|
| 125 |
+
"step": 180
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 0.09,
|
| 129 |
+
"learning_rate": 7.436420722135007e-05,
|
| 130 |
+
"loss": 3.3592,
|
| 131 |
+
"step": 190
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 0.09,
|
| 135 |
+
"learning_rate": 7.425824175824176e-05,
|
| 136 |
+
"loss": 3.6018,
|
| 137 |
+
"step": 200
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.09,
|
| 141 |
+
"eval_loss": 3.3504831790924072,
|
| 142 |
+
"eval_runtime": 130.1255,
|
| 143 |
+
"eval_samples_per_second": 35.504,
|
| 144 |
+
"eval_steps_per_second": 1.114,
|
| 145 |
+
"eval_wer": 1.0,
|
| 146 |
+
"step": 200
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.1,
|
| 150 |
+
"learning_rate": 7.414050235478806e-05,
|
| 151 |
+
"loss": 3.1612,
|
| 152 |
+
"step": 210
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.1,
|
| 156 |
+
"learning_rate": 7.402276295133437e-05,
|
| 157 |
+
"loss": 3.0375,
|
| 158 |
+
"step": 220
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.11,
|
| 162 |
+
"learning_rate": 7.390502354788069e-05,
|
| 163 |
+
"loss": 3.08,
|
| 164 |
+
"step": 230
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.11,
|
| 168 |
+
"learning_rate": 7.3787284144427e-05,
|
| 169 |
+
"loss": 3.2809,
|
| 170 |
+
"step": 240
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.12,
|
| 174 |
+
"learning_rate": 7.368131868131867e-05,
|
| 175 |
+
"loss": 3.5351,
|
| 176 |
+
"step": 250
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.12,
|
| 180 |
+
"learning_rate": 7.356357927786499e-05,
|
| 181 |
+
"loss": 3.01,
|
| 182 |
+
"step": 260
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.12,
|
| 186 |
+
"learning_rate": 7.34458398744113e-05,
|
| 187 |
+
"loss": 3.0006,
|
| 188 |
+
"step": 270
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.13,
|
| 192 |
+
"learning_rate": 7.33281004709576e-05,
|
| 193 |
+
"loss": 3.0397,
|
| 194 |
+
"step": 280
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.13,
|
| 198 |
+
"learning_rate": 7.321036106750392e-05,
|
| 199 |
+
"loss": 3.1733,
|
| 200 |
+
"step": 290
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.14,
|
| 204 |
+
"learning_rate": 7.310439560439559e-05,
|
| 205 |
+
"loss": 3.5007,
|
| 206 |
+
"step": 300
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.14,
|
| 210 |
+
"eval_loss": 3.068483591079712,
|
| 211 |
+
"eval_runtime": 129.9806,
|
| 212 |
+
"eval_samples_per_second": 35.544,
|
| 213 |
+
"eval_steps_per_second": 1.116,
|
| 214 |
+
"eval_wer": 1.0,
|
| 215 |
+
"step": 300
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 0.14,
|
| 219 |
+
"learning_rate": 7.29866562009419e-05,
|
| 220 |
+
"loss": 2.9984,
|
| 221 |
+
"step": 310
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 0.15,
|
| 225 |
+
"learning_rate": 7.286891679748822e-05,
|
| 226 |
+
"loss": 3.0006,
|
| 227 |
+
"step": 320
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.15,
|
| 231 |
+
"learning_rate": 7.275117739403453e-05,
|
| 232 |
+
"loss": 3.029,
|
| 233 |
+
"step": 330
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.16,
|
| 237 |
+
"learning_rate": 7.263343799058085e-05,
|
| 238 |
+
"loss": 3.158,
|
| 239 |
+
"step": 340
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 0.16,
|
| 243 |
+
"learning_rate": 7.252747252747252e-05,
|
| 244 |
+
"loss": 3.4909,
|
| 245 |
+
"step": 350
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 0.17,
|
| 249 |
+
"learning_rate": 7.240973312401883e-05,
|
| 250 |
+
"loss": 3.001,
|
| 251 |
+
"step": 360
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 0.17,
|
| 255 |
+
"learning_rate": 7.229199372056515e-05,
|
| 256 |
+
"loss": 2.9925,
|
| 257 |
+
"step": 370
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 0.18,
|
| 261 |
+
"learning_rate": 7.217425431711145e-05,
|
| 262 |
+
"loss": 3.0009,
|
| 263 |
+
"step": 380
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 0.18,
|
| 267 |
+
"learning_rate": 7.205651491365776e-05,
|
| 268 |
+
"loss": 3.1263,
|
| 269 |
+
"step": 390
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.18,
|
| 273 |
+
"learning_rate": 7.195054945054944e-05,
|
| 274 |
+
"loss": 3.421,
|
| 275 |
+
"step": 400
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.18,
|
| 279 |
+
"eval_loss": 3.0357792377471924,
|
| 280 |
+
"eval_runtime": 130.0328,
|
| 281 |
+
"eval_samples_per_second": 35.529,
|
| 282 |
+
"eval_steps_per_second": 1.115,
|
| 283 |
+
"eval_wer": 1.0,
|
| 284 |
+
"step": 400
|
| 285 |
+
}
|
| 286 |
+
],
|
| 287 |
+
"max_steps": 6501,
|
| 288 |
+
"num_train_epochs": 3,
|
| 289 |
+
"total_flos": 7.566114292968407e+18,
|
| 290 |
+
"trial_name": null,
|
| 291 |
+
"trial_params": null
|
| 292 |
+
}
|
{checkpoint-100 → checkpoint-400}/training_args.bin
RENAMED
|
File without changes
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1262067185
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3615598ae508e9ab81f60392073741effb41877fe43b3faf976c78e298f8b7ce
|
| 3 |
size 1262067185
|