Training in progress, step 23851, 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 223144592
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:20a2efcd378e68e5423f165a4a0387d8b6aa67ec332f08647788d627623f31fa
|
| 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 sha256:176a7edca52df7006b6e80fc665209b0d652ed6bacfe9145dd393ff412925b33
|
| 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 sha256:321a7b3921efd300361448b8b38882c468b0bcf30e6ff6ad663ca64abee188fc
|
| 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 sha256:4ee75c828e1283985bb11c2faad94b91c6464933f48be07f74b3cf33715dcf3f
|
| 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 sha256:8012f92ee8a299879e271129e553a031940dd53319002df088c87fb538cd6fb6
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": 18400,
|
| 3 |
"best_metric": 0.19658119658119658,
|
| 4 |
"best_model_checkpoint": "./distil-whisper/checkpoint-18400",
|
| 5 |
-
"epoch": 16.
|
| 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,
|
|
@@ -2191,6 +2191,20 @@
|
|
| 2191 |
"eval_steps_per_second": 0.429,
|
| 2192 |
"eval_wer": 0.19908635425876806,
|
| 2193 |
"step": 23600
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2194 |
}
|
| 2195 |
],
|
| 2196 |
"logging_steps": 100,
|
|
@@ -2205,12 +2219,12 @@
|
|
| 2205 |
"should_evaluate": false,
|
| 2206 |
"should_log": false,
|
| 2207 |
"should_save": true,
|
| 2208 |
-
"should_training_stop":
|
| 2209 |
},
|
| 2210 |
"attributes": {}
|
| 2211 |
}
|
| 2212 |
},
|
| 2213 |
-
"total_flos": 3.
|
| 2214 |
"train_batch_size": 8,
|
| 2215 |
"trial_name": null,
|
| 2216 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": 18400,
|
| 3 |
"best_metric": 0.19658119658119658,
|
| 4 |
"best_model_checkpoint": "./distil-whisper/checkpoint-18400",
|
| 5 |
+
"epoch": 16.995546053803672,
|
| 6 |
"eval_steps": 400,
|
| 7 |
+
"global_step": 23851,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2191 |
"eval_steps_per_second": 0.429,
|
| 2192 |
"eval_wer": 0.19908635425876806,
|
| 2193 |
"step": 23600
|
| 2194 |
+
},
|
| 2195 |
+
{
|
| 2196 |
+
"epoch": 16.88793871370034,
|
| 2197 |
+
"grad_norm": 13.370680809020996,
|
| 2198 |
+
"learning_rate": 7.151727977388549e-07,
|
| 2199 |
+
"loss": 1.1688,
|
| 2200 |
+
"step": 23700
|
| 2201 |
+
},
|
| 2202 |
+
{
|
| 2203 |
+
"epoch": 16.959201852841616,
|
| 2204 |
+
"grad_norm": 11.178988456726074,
|
| 2205 |
+
"learning_rate": 2.869256134640915e-07,
|
| 2206 |
+
"loss": 1.1531,
|
| 2207 |
+
"step": 23800
|
| 2208 |
}
|
| 2209 |
],
|
| 2210 |
"logging_steps": 100,
|
|
|
|
| 2219 |
"should_evaluate": false,
|
| 2220 |
"should_log": false,
|
| 2221 |
"should_save": true,
|
| 2222 |
+
"should_training_stop": true
|
| 2223 |
},
|
| 2224 |
"attributes": {}
|
| 2225 |
}
|
| 2226 |
},
|
| 2227 |
+
"total_flos": 3.100951000645632e+19,
|
| 2228 |
"train_batch_size": 8,
|
| 2229 |
"trial_name": null,
|
| 2230 |
"trial_params": null
|