Training in progress, step 14400, checkpoint
Browse files- last-checkpoint/generation_config.json +1 -14
- last-checkpoint/model.safetensors +1 -1
- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scaler.pt +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +43 -6
- last-checkpoint/training_args.bin +1 -1
last-checkpoint/generation_config.json
CHANGED
|
@@ -2,20 +2,7 @@
|
|
| 2 |
"bos_token_id": 50257,
|
| 3 |
"decoder_start_token_id": 50258,
|
| 4 |
"eos_token_id": 50257,
|
| 5 |
-
"input_ids":
|
| 6 |
-
[
|
| 7 |
-
1,
|
| 8 |
-
50272
|
| 9 |
-
],
|
| 10 |
-
[
|
| 11 |
-
2,
|
| 12 |
-
50359
|
| 13 |
-
],
|
| 14 |
-
[
|
| 15 |
-
3,
|
| 16 |
-
50363
|
| 17 |
-
]
|
| 18 |
-
],
|
| 19 |
"max_length": 448,
|
| 20 |
"pad_token_id": 50257,
|
| 21 |
"transformers_version": "4.51.3"
|
|
|
|
| 2 |
"bos_token_id": 50257,
|
| 3 |
"decoder_start_token_id": 50258,
|
| 4 |
"eos_token_id": 50257,
|
| 5 |
+
"input_ids": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
"max_length": 448,
|
| 7 |
"pad_token_id": 50257,
|
| 8 |
"transformers_version": "4.51.3"
|
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 223144592
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:35bf3fcc1c9f858d2fcb65a8eba22aa7bb63ba5498692297455d6d86d9337994
|
| 3 |
size 223144592
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 281574266
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e56d4a55f5092b6c7489de4b87e6abc0943f948bc163c2b9161cc1c8e88b4d42
|
| 3 |
size 281574266
|
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 sha256:8f5fbb8003bf7f1e9e8f97ef16bde9d5de4080b5c976515ae1b0f6faf7bbe4eb
|
| 3 |
size 14244
|
last-checkpoint/scaler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 988
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a52823e3638fa04b21398fcbf87da02f0eac04f592a1235c4d092fb21b164c4e
|
| 3 |
size 988
|
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 sha256:47186133a71797512426e32473dabdda2a97359d282cffbb1393371c158706b3
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": 13200,
|
| 3 |
"best_metric": 0.20100206307102858,
|
| 4 |
"best_model_checkpoint": "./distil-whisper/checkpoint-13200",
|
| 5 |
-
"epoch":
|
| 6 |
"eval_steps": 400,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -1303,12 +1303,49 @@
|
|
| 1303 |
"eval_steps_per_second": 0.432,
|
| 1304 |
"eval_wer": 0.20439139404656645,
|
| 1305 |
"step": 14000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1306 |
}
|
| 1307 |
],
|
| 1308 |
"logging_steps": 100,
|
| 1309 |
-
"max_steps":
|
| 1310 |
"num_input_tokens_seen": 0,
|
| 1311 |
-
"num_train_epochs":
|
| 1312 |
"save_steps": 400,
|
| 1313 |
"stateful_callbacks": {
|
| 1314 |
"TrainerControl": {
|
|
@@ -1317,12 +1354,12 @@
|
|
| 1317 |
"should_evaluate": false,
|
| 1318 |
"should_log": false,
|
| 1319 |
"should_save": true,
|
| 1320 |
-
"should_training_stop":
|
| 1321 |
},
|
| 1322 |
"attributes": {}
|
| 1323 |
}
|
| 1324 |
},
|
| 1325 |
-
"total_flos": 1.
|
| 1326 |
"train_batch_size": 8,
|
| 1327 |
"trial_name": null,
|
| 1328 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": 13200,
|
| 3 |
"best_metric": 0.20100206307102858,
|
| 4 |
"best_model_checkpoint": "./distil-whisper/checkpoint-13200",
|
| 5 |
+
"epoch": 10.263673614822732,
|
| 6 |
"eval_steps": 400,
|
| 7 |
+
"global_step": 14400,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1303 |
"eval_steps_per_second": 0.432,
|
| 1304 |
"eval_wer": 0.20439139404656645,
|
| 1305 |
"step": 14000
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 10.049884197398896,
|
| 1309 |
+
"grad_norm": 27.002792358398438,
|
| 1310 |
+
"learning_rate": 4.1822620016273397e-05,
|
| 1311 |
+
"loss": 1.4666,
|
| 1312 |
+
"step": 14100
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 10.121147336540174,
|
| 1316 |
+
"grad_norm": 27.5255069732666,
|
| 1317 |
+
"learning_rate": 4.139437283199863e-05,
|
| 1318 |
+
"loss": 1.58,
|
| 1319 |
+
"step": 14200
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 10.192410475681454,
|
| 1323 |
+
"grad_norm": 29.90217399597168,
|
| 1324 |
+
"learning_rate": 4.096612564772387e-05,
|
| 1325 |
+
"loss": 1.7165,
|
| 1326 |
+
"step": 14300
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 10.263673614822732,
|
| 1330 |
+
"grad_norm": 35.381736755371094,
|
| 1331 |
+
"learning_rate": 4.05378784634491e-05,
|
| 1332 |
+
"loss": 1.5442,
|
| 1333 |
+
"step": 14400
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 10.263673614822732,
|
| 1337 |
+
"eval_loss": 0.09780226647853851,
|
| 1338 |
+
"eval_runtime": 154.9465,
|
| 1339 |
+
"eval_samples_per_second": 3.227,
|
| 1340 |
+
"eval_steps_per_second": 0.407,
|
| 1341 |
+
"eval_wer": 0.20881226053639848,
|
| 1342 |
+
"step": 14400
|
| 1343 |
}
|
| 1344 |
],
|
| 1345 |
"logging_steps": 100,
|
| 1346 |
+
"max_steps": 23851,
|
| 1347 |
"num_input_tokens_seen": 0,
|
| 1348 |
+
"num_train_epochs": 17,
|
| 1349 |
"save_steps": 400,
|
| 1350 |
"stateful_callbacks": {
|
| 1351 |
"TrainerControl": {
|
|
|
|
| 1354 |
"should_evaluate": false,
|
| 1355 |
"should_log": false,
|
| 1356 |
"should_save": true,
|
| 1357 |
+
"should_training_stop": false
|
| 1358 |
},
|
| 1359 |
"attributes": {}
|
| 1360 |
}
|
| 1361 |
},
|
| 1362 |
+
"total_flos": 1.872251976941568e+19,
|
| 1363 |
"train_batch_size": 8,
|
| 1364 |
"trial_name": null,
|
| 1365 |
"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 5496
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6daed3ea50dd3d62fb97def45cee67ca4aa97248ce2785363140f3aadf764b61
|
| 3 |
size 5496
|