Training in progress, step 1000, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 966995080
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0c0e94765b4d94db639b25aa92e7ab864938a06ca386b080e39d32fdcdb0f83f
|
| 3 |
size 966995080
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1925064044
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fd55be4786c31c3edb602a43e9427bd058e0237d125903549b6554bc93a9b212
|
| 3 |
size 1925064044
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:298c3bc45193d5f9e013179fcd36fc29bded406f371da8183cdaa90d25f6d218
|
| 3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eaa3528dbf446124664be6010ae04f1f735b5fea142f7ff755065a21e5dce083
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,56 +1,308 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric":
|
| 3 |
-
"best_model_checkpoint": "./whisper-small-lt/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
-
"eval_steps":
|
| 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": 0.0125,
|
| 13 |
-
"grad_norm":
|
| 14 |
"learning_rate": 5.000000000000001e-07,
|
| 15 |
-
"loss": 0.
|
| 16 |
"step": 25
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 0.025,
|
| 20 |
-
"grad_norm": 1.
|
| 21 |
"learning_rate": 1.0000000000000002e-06,
|
| 22 |
-
"loss": 0.
|
| 23 |
"step": 50
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 0.0375,
|
| 27 |
-
"grad_norm":
|
| 28 |
"learning_rate": 1.5e-06,
|
| 29 |
-
"loss": 0.
|
| 30 |
"step": 75
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"epoch": 0.05,
|
| 34 |
-
"grad_norm":
|
| 35 |
"learning_rate": 2.0000000000000003e-06,
|
| 36 |
-
"loss": 0.
|
| 37 |
"step": 100
|
| 38 |
},
|
| 39 |
{
|
| 40 |
-
"epoch": 0.
|
| 41 |
-
"
|
| 42 |
-
"
|
| 43 |
-
"
|
| 44 |
-
"
|
| 45 |
-
|
| 46 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 47 |
}
|
| 48 |
],
|
| 49 |
"logging_steps": 25,
|
| 50 |
"max_steps": 2000,
|
| 51 |
"num_input_tokens_seen": 0,
|
| 52 |
"num_train_epochs": 9223372036854775807,
|
| 53 |
-
"save_steps":
|
| 54 |
"stateful_callbacks": {
|
| 55 |
"TrainerControl": {
|
| 56 |
"args": {
|
|
@@ -63,7 +315,7 @@
|
|
| 63 |
"attributes": {}
|
| 64 |
}
|
| 65 |
},
|
| 66 |
-
"total_flos": 4.
|
| 67 |
"train_batch_size": 16,
|
| 68 |
"trial_name": null,
|
| 69 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 33.69881109643329,
|
| 3 |
+
"best_model_checkpoint": "./whisper-small-lt/checkpoint-1000",
|
| 4 |
+
"epoch": 2.111,
|
| 5 |
+
"eval_steps": 1000,
|
| 6 |
+
"global_step": 1000,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.0125,
|
| 13 |
+
"grad_norm": 1.7294858694076538,
|
| 14 |
"learning_rate": 5.000000000000001e-07,
|
| 15 |
+
"loss": 0.0291,
|
| 16 |
"step": 25
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 0.025,
|
| 20 |
+
"grad_norm": 1.1127374172210693,
|
| 21 |
"learning_rate": 1.0000000000000002e-06,
|
| 22 |
+
"loss": 0.0178,
|
| 23 |
"step": 50
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 0.0375,
|
| 27 |
+
"grad_norm": 1.248637318611145,
|
| 28 |
"learning_rate": 1.5e-06,
|
| 29 |
+
"loss": 0.0202,
|
| 30 |
"step": 75
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"epoch": 0.05,
|
| 34 |
+
"grad_norm": 0.8879645466804504,
|
| 35 |
"learning_rate": 2.0000000000000003e-06,
|
| 36 |
+
"loss": 0.0166,
|
| 37 |
"step": 100
|
| 38 |
},
|
| 39 |
{
|
| 40 |
+
"epoch": 0.0625,
|
| 41 |
+
"grad_norm": 1.0460960865020752,
|
| 42 |
+
"learning_rate": 2.5e-06,
|
| 43 |
+
"loss": 0.0148,
|
| 44 |
+
"step": 125
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.075,
|
| 48 |
+
"grad_norm": 0.7859419584274292,
|
| 49 |
+
"learning_rate": 3e-06,
|
| 50 |
+
"loss": 0.0138,
|
| 51 |
+
"step": 150
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.0875,
|
| 55 |
+
"grad_norm": 0.6411359906196594,
|
| 56 |
+
"learning_rate": 3.5e-06,
|
| 57 |
+
"loss": 0.0124,
|
| 58 |
+
"step": 175
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.1,
|
| 62 |
+
"grad_norm": 1.4224746227264404,
|
| 63 |
+
"learning_rate": 4.000000000000001e-06,
|
| 64 |
+
"loss": 0.0157,
|
| 65 |
+
"step": 200
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.1125,
|
| 69 |
+
"grad_norm": 1.8457200527191162,
|
| 70 |
+
"learning_rate": 4.5e-06,
|
| 71 |
+
"loss": 0.0283,
|
| 72 |
+
"step": 225
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.125,
|
| 76 |
+
"grad_norm": 2.3054425716400146,
|
| 77 |
+
"learning_rate": 5e-06,
|
| 78 |
+
"loss": 0.0244,
|
| 79 |
+
"step": 250
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.1375,
|
| 83 |
+
"grad_norm": 2.961075782775879,
|
| 84 |
+
"learning_rate": 5.500000000000001e-06,
|
| 85 |
+
"loss": 0.0226,
|
| 86 |
+
"step": 275
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.15,
|
| 90 |
+
"grad_norm": 1.1010462045669556,
|
| 91 |
+
"learning_rate": 6e-06,
|
| 92 |
+
"loss": 0.0158,
|
| 93 |
+
"step": 300
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.1625,
|
| 97 |
+
"grad_norm": 1.5947000980377197,
|
| 98 |
+
"learning_rate": 6.5000000000000004e-06,
|
| 99 |
+
"loss": 0.0185,
|
| 100 |
+
"step": 325
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.175,
|
| 104 |
+
"grad_norm": 2.136035203933716,
|
| 105 |
+
"learning_rate": 7e-06,
|
| 106 |
+
"loss": 0.0182,
|
| 107 |
+
"step": 350
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.1875,
|
| 111 |
+
"grad_norm": 1.8465747833251953,
|
| 112 |
+
"learning_rate": 7.500000000000001e-06,
|
| 113 |
+
"loss": 0.0149,
|
| 114 |
+
"step": 375
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 1.0055,
|
| 118 |
+
"grad_norm": 2.093752384185791,
|
| 119 |
+
"learning_rate": 8.000000000000001e-06,
|
| 120 |
+
"loss": 0.0277,
|
| 121 |
+
"step": 400
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 1.018,
|
| 125 |
+
"grad_norm": 1.3066338300704956,
|
| 126 |
+
"learning_rate": 8.5e-06,
|
| 127 |
+
"loss": 0.0236,
|
| 128 |
+
"step": 425
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.0305,
|
| 132 |
+
"grad_norm": 2.310856819152832,
|
| 133 |
+
"learning_rate": 9e-06,
|
| 134 |
+
"loss": 0.023,
|
| 135 |
+
"step": 450
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 1.043,
|
| 139 |
+
"grad_norm": 1.4942700862884521,
|
| 140 |
+
"learning_rate": 9.5e-06,
|
| 141 |
+
"loss": 0.022,
|
| 142 |
+
"step": 475
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 1.0555,
|
| 146 |
+
"grad_norm": 1.1907243728637695,
|
| 147 |
+
"learning_rate": 1e-05,
|
| 148 |
+
"loss": 0.0183,
|
| 149 |
+
"step": 500
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.068,
|
| 153 |
+
"grad_norm": 1.8676977157592773,
|
| 154 |
+
"learning_rate": 9.833333333333333e-06,
|
| 155 |
+
"loss": 0.0183,
|
| 156 |
+
"step": 525
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 1.0805,
|
| 160 |
+
"grad_norm": 0.9104222059249878,
|
| 161 |
+
"learning_rate": 9.666666666666667e-06,
|
| 162 |
+
"loss": 0.016,
|
| 163 |
+
"step": 550
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 1.093,
|
| 167 |
+
"grad_norm": 1.465457558631897,
|
| 168 |
+
"learning_rate": 9.5e-06,
|
| 169 |
+
"loss": 0.0151,
|
| 170 |
+
"step": 575
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 1.1055,
|
| 174 |
+
"grad_norm": 1.5364313125610352,
|
| 175 |
+
"learning_rate": 9.333333333333334e-06,
|
| 176 |
+
"loss": 0.0205,
|
| 177 |
+
"step": 600
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 1.1179999999999999,
|
| 181 |
+
"grad_norm": 1.29054594039917,
|
| 182 |
+
"learning_rate": 9.166666666666666e-06,
|
| 183 |
+
"loss": 0.0198,
|
| 184 |
+
"step": 625
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 1.1305,
|
| 188 |
+
"grad_norm": 2.222632884979248,
|
| 189 |
+
"learning_rate": 9e-06,
|
| 190 |
+
"loss": 0.0167,
|
| 191 |
+
"step": 650
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 1.143,
|
| 195 |
+
"grad_norm": 1.1213107109069824,
|
| 196 |
+
"learning_rate": 8.833333333333334e-06,
|
| 197 |
+
"loss": 0.015,
|
| 198 |
+
"step": 675
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 1.1555,
|
| 202 |
+
"grad_norm": 3.053809642791748,
|
| 203 |
+
"learning_rate": 8.666666666666668e-06,
|
| 204 |
+
"loss": 0.0123,
|
| 205 |
+
"step": 700
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 1.168,
|
| 209 |
+
"grad_norm": 3.0312676429748535,
|
| 210 |
+
"learning_rate": 8.5e-06,
|
| 211 |
+
"loss": 0.0135,
|
| 212 |
+
"step": 725
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 1.1804999999999999,
|
| 216 |
+
"grad_norm": 1.2940341234207153,
|
| 217 |
+
"learning_rate": 8.333333333333334e-06,
|
| 218 |
+
"loss": 0.0152,
|
| 219 |
+
"step": 750
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 1.193,
|
| 223 |
+
"grad_norm": 1.9949597120285034,
|
| 224 |
+
"learning_rate": 8.166666666666668e-06,
|
| 225 |
+
"loss": 0.015,
|
| 226 |
+
"step": 775
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 2.011,
|
| 230 |
+
"grad_norm": 1.2895445823669434,
|
| 231 |
+
"learning_rate": 8.000000000000001e-06,
|
| 232 |
+
"loss": 0.0251,
|
| 233 |
+
"step": 800
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 2.0235,
|
| 237 |
+
"grad_norm": 1.7078819274902344,
|
| 238 |
+
"learning_rate": 7.833333333333333e-06,
|
| 239 |
+
"loss": 0.0159,
|
| 240 |
+
"step": 825
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 2.036,
|
| 244 |
+
"grad_norm": 0.7963767647743225,
|
| 245 |
+
"learning_rate": 7.666666666666667e-06,
|
| 246 |
+
"loss": 0.0158,
|
| 247 |
+
"step": 850
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 2.0485,
|
| 251 |
+
"grad_norm": 1.2390975952148438,
|
| 252 |
+
"learning_rate": 7.500000000000001e-06,
|
| 253 |
+
"loss": 0.0141,
|
| 254 |
+
"step": 875
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 2.061,
|
| 258 |
+
"grad_norm": 1.4780830144882202,
|
| 259 |
+
"learning_rate": 7.333333333333333e-06,
|
| 260 |
+
"loss": 0.0112,
|
| 261 |
+
"step": 900
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 2.0735,
|
| 265 |
+
"grad_norm": 0.7993568778038025,
|
| 266 |
+
"learning_rate": 7.166666666666667e-06,
|
| 267 |
+
"loss": 0.0118,
|
| 268 |
+
"step": 925
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 2.086,
|
| 272 |
+
"grad_norm": 1.1336815357208252,
|
| 273 |
+
"learning_rate": 7e-06,
|
| 274 |
+
"loss": 0.0089,
|
| 275 |
+
"step": 950
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 2.0985,
|
| 279 |
+
"grad_norm": 1.7068537473678589,
|
| 280 |
+
"learning_rate": 6.833333333333334e-06,
|
| 281 |
+
"loss": 0.0107,
|
| 282 |
+
"step": 975
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 2.111,
|
| 286 |
+
"grad_norm": 1.4282974004745483,
|
| 287 |
+
"learning_rate": 6.666666666666667e-06,
|
| 288 |
+
"loss": 0.0117,
|
| 289 |
+
"step": 1000
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 2.111,
|
| 293 |
+
"eval_loss": 0.15551722049713135,
|
| 294 |
+
"eval_runtime": 621.1845,
|
| 295 |
+
"eval_samples_per_second": 1.025,
|
| 296 |
+
"eval_steps_per_second": 0.129,
|
| 297 |
+
"eval_wer": 33.69881109643329,
|
| 298 |
+
"step": 1000
|
| 299 |
}
|
| 300 |
],
|
| 301 |
"logging_steps": 25,
|
| 302 |
"max_steps": 2000,
|
| 303 |
"num_input_tokens_seen": 0,
|
| 304 |
"num_train_epochs": 9223372036854775807,
|
| 305 |
+
"save_steps": 1000,
|
| 306 |
"stateful_callbacks": {
|
| 307 |
"TrainerControl": {
|
| 308 |
"args": {
|
|
|
|
| 315 |
"attributes": {}
|
| 316 |
}
|
| 317 |
},
|
| 318 |
+
"total_flos": 4.61217186791424e+18,
|
| 319 |
"train_batch_size": 16,
|
| 320 |
"trial_name": null,
|
| 321 |
"trial_params": null
|
last-checkpoint/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5304
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b957ee098d1cf296d30a738a9260f12a5262b820dc15dba99580731e2111b99c
|
| 3 |
size 5304
|