Training in progress, step 4000, 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:c3e04e8a74af8a0ac2ed332252559dafd950c8cadfaf3f5311093a6e8d2211fd
|
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:ad286a6cda4a8d9f22fc02be708961e36cb9b44e3e3a7c906a9d4ec2238015b9
|
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 sha256:3538b2ade2ffedcaa9b2cf1656897f664162c1a13b8a94e734db708d7277916d
|
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 sha256:16bf3fca7a902d2236e538702f3f6e7b561f71a0c227ad9e7851d8d53e05b385
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": 70.1955074875208,
|
3 |
"best_model_checkpoint": "./whisper-it/checkpoint-300",
|
4 |
-
"epoch": 7.
|
5 |
"eval_steps": 100,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -1261,6 +1261,72 @@
|
|
1261 |
"eval_steps_per_second": 0.115,
|
1262 |
"eval_wer": 194.88352745424294,
|
1263 |
"step": 3800
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1264 |
}
|
1265 |
],
|
1266 |
"logging_steps": 25,
|
@@ -1268,7 +1334,7 @@
|
|
1268 |
"num_input_tokens_seen": 0,
|
1269 |
"num_train_epochs": 8,
|
1270 |
"save_steps": 100,
|
1271 |
-
"total_flos": 3.
|
1272 |
"trial_name": null,
|
1273 |
"trial_params": null
|
1274 |
}
|
|
|
1 |
{
|
2 |
"best_metric": 70.1955074875208,
|
3 |
"best_model_checkpoint": "./whisper-it/checkpoint-300",
|
4 |
+
"epoch": 7.633587786259542,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 4000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
1261 |
"eval_steps_per_second": 0.115,
|
1262 |
"eval_wer": 194.88352745424294,
|
1263 |
"step": 3800
|
1264 |
+
},
|
1265 |
+
{
|
1266 |
+
"epoch": 7.3,
|
1267 |
+
"learning_rate": 5.171428571428572e-07,
|
1268 |
+
"loss": 0.0065,
|
1269 |
+
"step": 3825
|
1270 |
+
},
|
1271 |
+
{
|
1272 |
+
"epoch": 7.35,
|
1273 |
+
"learning_rate": 4.457142857142858e-07,
|
1274 |
+
"loss": 0.0043,
|
1275 |
+
"step": 3850
|
1276 |
+
},
|
1277 |
+
{
|
1278 |
+
"epoch": 7.4,
|
1279 |
+
"learning_rate": 3.7428571428571434e-07,
|
1280 |
+
"loss": 0.0058,
|
1281 |
+
"step": 3875
|
1282 |
+
},
|
1283 |
+
{
|
1284 |
+
"epoch": 7.44,
|
1285 |
+
"learning_rate": 3.028571428571429e-07,
|
1286 |
+
"loss": 0.0052,
|
1287 |
+
"step": 3900
|
1288 |
+
},
|
1289 |
+
{
|
1290 |
+
"epoch": 7.44,
|
1291 |
+
"eval_loss": 0.4545614421367645,
|
1292 |
+
"eval_runtime": 1641.2052,
|
1293 |
+
"eval_samples_per_second": 0.914,
|
1294 |
+
"eval_steps_per_second": 0.115,
|
1295 |
+
"eval_wer": 199.56322795341097,
|
1296 |
+
"step": 3900
|
1297 |
+
},
|
1298 |
+
{
|
1299 |
+
"epoch": 7.49,
|
1300 |
+
"learning_rate": 2.3142857142857144e-07,
|
1301 |
+
"loss": 0.0054,
|
1302 |
+
"step": 3925
|
1303 |
+
},
|
1304 |
+
{
|
1305 |
+
"epoch": 7.54,
|
1306 |
+
"learning_rate": 1.6e-07,
|
1307 |
+
"loss": 0.005,
|
1308 |
+
"step": 3950
|
1309 |
+
},
|
1310 |
+
{
|
1311 |
+
"epoch": 7.59,
|
1312 |
+
"learning_rate": 8.857142857142858e-08,
|
1313 |
+
"loss": 0.0063,
|
1314 |
+
"step": 3975
|
1315 |
+
},
|
1316 |
+
{
|
1317 |
+
"epoch": 7.63,
|
1318 |
+
"learning_rate": 1.7142857142857143e-08,
|
1319 |
+
"loss": 0.0054,
|
1320 |
+
"step": 4000
|
1321 |
+
},
|
1322 |
+
{
|
1323 |
+
"epoch": 7.63,
|
1324 |
+
"eval_loss": 0.45494550466537476,
|
1325 |
+
"eval_runtime": 1747.4976,
|
1326 |
+
"eval_samples_per_second": 0.858,
|
1327 |
+
"eval_steps_per_second": 0.108,
|
1328 |
+
"eval_wer": 200.37437603993345,
|
1329 |
+
"step": 4000
|
1330 |
}
|
1331 |
],
|
1332 |
"logging_steps": 25,
|
|
|
1334 |
"num_input_tokens_seen": 0,
|
1335 |
"num_train_epochs": 8,
|
1336 |
"save_steps": 100,
|
1337 |
+
"total_flos": 3.692479055634432e+19,
|
1338 |
"trial_name": null,
|
1339 |
"trial_params": null
|
1340 |
}
|
last-checkpoint/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4856
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a896ba5f5995d5c123fd1de94ce23a1c985748fcd77d3dd7f2de03541edd270f
|
3 |
size 4856
|