Commit
•
91fb563
1
Parent(s):
9eafbd0
Training in progress, step 4000
Browse files- checkpoint-1000/trainer_state.json +0 -85
- {checkpoint-1000 → checkpoint-4000}/config.json +0 -0
- {checkpoint-1000 → checkpoint-4000}/optimizer.pt +1 -1
- {checkpoint-1000 → checkpoint-4000}/preprocessor_config.json +0 -0
- {checkpoint-1000 → checkpoint-4000}/pytorch_model.bin +1 -1
- {checkpoint-1000 → checkpoint-4000}/rng_state.pth +2 -2
- {checkpoint-1000 → checkpoint-4000}/scaler.pt +1 -1
- {checkpoint-1000 → checkpoint-4000}/scheduler.pt +1 -1
- checkpoint-4000/trainer_state.json +292 -0
- {checkpoint-1000 → checkpoint-4000}/training_args.bin +0 -0
- pytorch_model.bin +1 -1
checkpoint-1000/trainer_state.json
DELETED
|
@@ -1,85 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"best_metric": null,
|
| 3 |
-
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 10.415584415584416,
|
| 5 |
-
"global_step": 1000,
|
| 6 |
-
"is_hyper_param_search": false,
|
| 7 |
-
"is_local_process_zero": true,
|
| 8 |
-
"is_world_process_zero": true,
|
| 9 |
-
"log_history": [
|
| 10 |
-
{
|
| 11 |
-
"epoch": 1.04,
|
| 12 |
-
"learning_rate": 3.828125e-06,
|
| 13 |
-
"loss": 15.104,
|
| 14 |
-
"step": 100
|
| 15 |
-
},
|
| 16 |
-
{
|
| 17 |
-
"epoch": 2.08,
|
| 18 |
-
"learning_rate": 7.6953125e-06,
|
| 19 |
-
"loss": 12.2149,
|
| 20 |
-
"step": 200
|
| 21 |
-
},
|
| 22 |
-
{
|
| 23 |
-
"epoch": 3.12,
|
| 24 |
-
"learning_rate": 1.16015625e-05,
|
| 25 |
-
"loss": 4.9885,
|
| 26 |
-
"step": 300
|
| 27 |
-
},
|
| 28 |
-
{
|
| 29 |
-
"epoch": 4.17,
|
| 30 |
-
"learning_rate": 1.55078125e-05,
|
| 31 |
-
"loss": 3.3788,
|
| 32 |
-
"step": 400
|
| 33 |
-
},
|
| 34 |
-
{
|
| 35 |
-
"epoch": 5.21,
|
| 36 |
-
"learning_rate": 1.94140625e-05,
|
| 37 |
-
"loss": 3.1705,
|
| 38 |
-
"step": 500
|
| 39 |
-
},
|
| 40 |
-
{
|
| 41 |
-
"epoch": 6.25,
|
| 42 |
-
"learning_rate": 2.3320312499999995e-05,
|
| 43 |
-
"loss": 3.11,
|
| 44 |
-
"step": 600
|
| 45 |
-
},
|
| 46 |
-
{
|
| 47 |
-
"epoch": 7.29,
|
| 48 |
-
"learning_rate": 2.72265625e-05,
|
| 49 |
-
"loss": 3.0526,
|
| 50 |
-
"step": 700
|
| 51 |
-
},
|
| 52 |
-
{
|
| 53 |
-
"epoch": 8.33,
|
| 54 |
-
"learning_rate": 3.11328125e-05,
|
| 55 |
-
"loss": 3.0113,
|
| 56 |
-
"step": 800
|
| 57 |
-
},
|
| 58 |
-
{
|
| 59 |
-
"epoch": 9.37,
|
| 60 |
-
"learning_rate": 3.5039062499999995e-05,
|
| 61 |
-
"loss": 2.9601,
|
| 62 |
-
"step": 900
|
| 63 |
-
},
|
| 64 |
-
{
|
| 65 |
-
"epoch": 10.42,
|
| 66 |
-
"learning_rate": 3.89453125e-05,
|
| 67 |
-
"loss": 2.9099,
|
| 68 |
-
"step": 1000
|
| 69 |
-
},
|
| 70 |
-
{
|
| 71 |
-
"epoch": 10.42,
|
| 72 |
-
"eval_loss": 2.8369038105010986,
|
| 73 |
-
"eval_runtime": 198.5866,
|
| 74 |
-
"eval_samples_per_second": 25.405,
|
| 75 |
-
"eval_steps_per_second": 0.796,
|
| 76 |
-
"eval_wer": 1.0,
|
| 77 |
-
"step": 1000
|
| 78 |
-
}
|
| 79 |
-
],
|
| 80 |
-
"max_steps": 9600,
|
| 81 |
-
"num_train_epochs": 100,
|
| 82 |
-
"total_flos": 1.5571160176119996e+19,
|
| 83 |
-
"trial_name": null,
|
| 84 |
-
"trial_params": null
|
| 85 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
{checkpoint-1000 → checkpoint-4000}/config.json
RENAMED
|
File without changes
|
{checkpoint-1000 → checkpoint-4000}/optimizer.pt
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2490337809
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:32099ae8af68aa995295f81388cedfcdf53750287e2cd1926f799776c785dc9c
|
| 3 |
size 2490337809
|
{checkpoint-1000 → checkpoint-4000}/preprocessor_config.json
RENAMED
|
File without changes
|
{checkpoint-1000 → checkpoint-4000}/pytorch_model.bin
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1262063089
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fab49963e9b9398b213516e5f111a4b3c94b65baca6eae9896d23b2cf617fc05
|
| 3 |
size 1262063089
|
{checkpoint-1000 → checkpoint-4000}/rng_state.pth
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:e559b653fce1fd6e42abc077a407aa059eb06e45c8ac45dcbf93fe543450eb17
|
| 3 |
+
size 14567
|
{checkpoint-1000 → checkpoint-4000}/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:ffc5542c3d0c9ad1fafea3de6341fb1dabeb7678f192c2521c05b244b277441d
|
| 3 |
size 559
|
{checkpoint-1000 → checkpoint-4000}/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 sha256:75e54b5a1f763d35b841701c1be7a179a2db0d635cfe3a56e3782e5e0cf62c90
|
| 3 |
size 623
|
checkpoint-4000/trainer_state.json
ADDED
|
@@ -0,0 +1,292 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 41.664935064935065,
|
| 5 |
+
"global_step": 4000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 1.04,
|
| 12 |
+
"learning_rate": 3.828125e-06,
|
| 13 |
+
"loss": 15.104,
|
| 14 |
+
"step": 100
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 2.08,
|
| 18 |
+
"learning_rate": 7.6953125e-06,
|
| 19 |
+
"loss": 12.2149,
|
| 20 |
+
"step": 200
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 3.12,
|
| 24 |
+
"learning_rate": 1.16015625e-05,
|
| 25 |
+
"loss": 4.9885,
|
| 26 |
+
"step": 300
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 4.17,
|
| 30 |
+
"learning_rate": 1.55078125e-05,
|
| 31 |
+
"loss": 3.3788,
|
| 32 |
+
"step": 400
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 5.21,
|
| 36 |
+
"learning_rate": 1.94140625e-05,
|
| 37 |
+
"loss": 3.1705,
|
| 38 |
+
"step": 500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 6.25,
|
| 42 |
+
"learning_rate": 2.3320312499999995e-05,
|
| 43 |
+
"loss": 3.11,
|
| 44 |
+
"step": 600
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 7.29,
|
| 48 |
+
"learning_rate": 2.72265625e-05,
|
| 49 |
+
"loss": 3.0526,
|
| 50 |
+
"step": 700
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 8.33,
|
| 54 |
+
"learning_rate": 3.11328125e-05,
|
| 55 |
+
"loss": 3.0113,
|
| 56 |
+
"step": 800
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 9.37,
|
| 60 |
+
"learning_rate": 3.5039062499999995e-05,
|
| 61 |
+
"loss": 2.9601,
|
| 62 |
+
"step": 900
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 10.42,
|
| 66 |
+
"learning_rate": 3.89453125e-05,
|
| 67 |
+
"loss": 2.9099,
|
| 68 |
+
"step": 1000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 10.42,
|
| 72 |
+
"eval_loss": 2.8369038105010986,
|
| 73 |
+
"eval_runtime": 198.5866,
|
| 74 |
+
"eval_samples_per_second": 25.405,
|
| 75 |
+
"eval_steps_per_second": 0.796,
|
| 76 |
+
"eval_wer": 1.0,
|
| 77 |
+
"step": 1000
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 11.46,
|
| 81 |
+
"learning_rate": 4.28515625e-05,
|
| 82 |
+
"loss": 2.6653,
|
| 83 |
+
"step": 1100
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 12.5,
|
| 87 |
+
"learning_rate": 4.675781249999999e-05,
|
| 88 |
+
"loss": 1.8958,
|
| 89 |
+
"step": 1200
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 13.54,
|
| 93 |
+
"learning_rate": 5.0664062499999996e-05,
|
| 94 |
+
"loss": 1.4812,
|
| 95 |
+
"step": 1300
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 14.58,
|
| 99 |
+
"learning_rate": 5.45703125e-05,
|
| 100 |
+
"loss": 1.3358,
|
| 101 |
+
"step": 1400
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 15.62,
|
| 105 |
+
"learning_rate": 5.8476562499999996e-05,
|
| 106 |
+
"loss": 1.2522,
|
| 107 |
+
"step": 1500
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 16.66,
|
| 111 |
+
"learning_rate": 6.238281249999999e-05,
|
| 112 |
+
"loss": 1.1919,
|
| 113 |
+
"step": 1600
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 17.71,
|
| 117 |
+
"learning_rate": 6.62890625e-05,
|
| 118 |
+
"loss": 1.1663,
|
| 119 |
+
"step": 1700
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 18.75,
|
| 123 |
+
"learning_rate": 7.019531249999999e-05,
|
| 124 |
+
"loss": 1.1289,
|
| 125 |
+
"step": 1800
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 19.79,
|
| 129 |
+
"learning_rate": 7.410156249999999e-05,
|
| 130 |
+
"loss": 1.0902,
|
| 131 |
+
"step": 1900
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 20.83,
|
| 135 |
+
"learning_rate": 7.4248046875e-05,
|
| 136 |
+
"loss": 1.0745,
|
| 137 |
+
"step": 2000
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 20.83,
|
| 141 |
+
"eval_loss": 0.19572903215885162,
|
| 142 |
+
"eval_runtime": 202.06,
|
| 143 |
+
"eval_samples_per_second": 24.968,
|
| 144 |
+
"eval_steps_per_second": 0.782,
|
| 145 |
+
"eval_wer": 0.16725371193237237,
|
| 146 |
+
"step": 2000
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 21.87,
|
| 150 |
+
"learning_rate": 7.327148437499999e-05,
|
| 151 |
+
"loss": 1.0485,
|
| 152 |
+
"step": 2100
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 22.91,
|
| 156 |
+
"learning_rate": 7.2294921875e-05,
|
| 157 |
+
"loss": 1.0291,
|
| 158 |
+
"step": 2200
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 23.96,
|
| 162 |
+
"learning_rate": 7.1318359375e-05,
|
| 163 |
+
"loss": 1.007,
|
| 164 |
+
"step": 2300
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 25.0,
|
| 168 |
+
"learning_rate": 7.0341796875e-05,
|
| 169 |
+
"loss": 1.0008,
|
| 170 |
+
"step": 2400
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 26.04,
|
| 174 |
+
"learning_rate": 6.9365234375e-05,
|
| 175 |
+
"loss": 0.988,
|
| 176 |
+
"step": 2500
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 27.08,
|
| 180 |
+
"learning_rate": 6.8388671875e-05,
|
| 181 |
+
"loss": 0.9766,
|
| 182 |
+
"step": 2600
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 28.12,
|
| 186 |
+
"learning_rate": 6.7412109375e-05,
|
| 187 |
+
"loss": 0.9663,
|
| 188 |
+
"step": 2700
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 29.17,
|
| 192 |
+
"learning_rate": 6.6435546875e-05,
|
| 193 |
+
"loss": 0.9539,
|
| 194 |
+
"step": 2800
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 30.21,
|
| 198 |
+
"learning_rate": 6.545898437499999e-05,
|
| 199 |
+
"loss": 0.9479,
|
| 200 |
+
"step": 2900
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 31.25,
|
| 204 |
+
"learning_rate": 6.448242187499999e-05,
|
| 205 |
+
"loss": 0.934,
|
| 206 |
+
"step": 3000
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 31.25,
|
| 210 |
+
"eval_loss": 0.1579357087612152,
|
| 211 |
+
"eval_runtime": 198.7733,
|
| 212 |
+
"eval_samples_per_second": 25.381,
|
| 213 |
+
"eval_steps_per_second": 0.795,
|
| 214 |
+
"eval_wer": 0.1388858784003468,
|
| 215 |
+
"step": 3000
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 32.29,
|
| 219 |
+
"learning_rate": 6.3505859375e-05,
|
| 220 |
+
"loss": 0.9285,
|
| 221 |
+
"step": 3100
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 33.33,
|
| 225 |
+
"learning_rate": 6.252929687499999e-05,
|
| 226 |
+
"loss": 0.9121,
|
| 227 |
+
"step": 3200
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 34.37,
|
| 231 |
+
"learning_rate": 6.155273437499999e-05,
|
| 232 |
+
"loss": 0.9016,
|
| 233 |
+
"step": 3300
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 35.42,
|
| 237 |
+
"learning_rate": 6.0576171875e-05,
|
| 238 |
+
"loss": 0.9023,
|
| 239 |
+
"step": 3400
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 36.46,
|
| 243 |
+
"learning_rate": 5.9599609374999994e-05,
|
| 244 |
+
"loss": 0.9004,
|
| 245 |
+
"step": 3500
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 37.5,
|
| 249 |
+
"learning_rate": 5.862304687499999e-05,
|
| 250 |
+
"loss": 0.8844,
|
| 251 |
+
"step": 3600
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 38.54,
|
| 255 |
+
"learning_rate": 5.7646484375e-05,
|
| 256 |
+
"loss": 0.8771,
|
| 257 |
+
"step": 3700
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 39.58,
|
| 261 |
+
"learning_rate": 5.6669921875e-05,
|
| 262 |
+
"loss": 0.876,
|
| 263 |
+
"step": 3800
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 40.62,
|
| 267 |
+
"learning_rate": 5.569335937499999e-05,
|
| 268 |
+
"loss": 0.8708,
|
| 269 |
+
"step": 3900
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 41.66,
|
| 273 |
+
"learning_rate": 5.4716796874999997e-05,
|
| 274 |
+
"loss": 0.8691,
|
| 275 |
+
"step": 4000
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 41.66,
|
| 279 |
+
"eval_loss": 0.14571049809455872,
|
| 280 |
+
"eval_runtime": 195.237,
|
| 281 |
+
"eval_samples_per_second": 25.84,
|
| 282 |
+
"eval_steps_per_second": 0.809,
|
| 283 |
+
"eval_wer": 0.12899642353961202,
|
| 284 |
+
"step": 4000
|
| 285 |
+
}
|
| 286 |
+
],
|
| 287 |
+
"max_steps": 9600,
|
| 288 |
+
"num_train_epochs": 100,
|
| 289 |
+
"total_flos": 6.217407889828844e+19,
|
| 290 |
+
"trial_name": null,
|
| 291 |
+
"trial_params": null
|
| 292 |
+
}
|
{checkpoint-1000 → checkpoint-4000}/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 1262063089
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fab49963e9b9398b213516e5f111a4b3c94b65baca6eae9896d23b2cf617fc05
|
| 3 |
size 1262063089
|