Training in progress, epoch 21, 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 2610104820
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8e62f21c2524fbe6fa35e7771d7a0f174a91d2590b39bd6f6aeb7cdccfd0659c
|
| 3 |
size 2610104820
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5210004271
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6bccecaf037aa026fb3aeecf97033588a8b734ad77c6f3316f4d4d4665be6d75
|
| 3 |
size 5210004271
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15006
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:70145026e21afc6ea2717a18ed89206163fc726fb3040617116c08c85b455de2
|
| 3 |
size 15006
|
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 sha256:2da52fce13790b5d54928ad82a11cde2bbdaabd941b9375b0d9e259039c539e5
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.8495596647262573,
|
| 3 |
"best_model_checkpoint": "mgh6/HTH_prob/checkpoint-4636",
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -322,6 +322,21 @@
|
|
| 322 |
"eval_samples_per_second": 32.578,
|
| 323 |
"eval_steps_per_second": 16.289,
|
| 324 |
"step": 5124
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 325 |
}
|
| 326 |
],
|
| 327 |
"logging_steps": 500,
|
|
@@ -336,7 +351,7 @@
|
|
| 336 |
"early_stopping_threshold": 0.0
|
| 337 |
},
|
| 338 |
"attributes": {
|
| 339 |
-
"early_stopping_patience_counter":
|
| 340 |
}
|
| 341 |
},
|
| 342 |
"TrainerControl": {
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.8495596647262573,
|
| 3 |
"best_model_checkpoint": "mgh6/HTH_prob/checkpoint-4636",
|
| 4 |
+
"epoch": 21.996045413955862,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 5368,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 322 |
"eval_samples_per_second": 32.578,
|
| 323 |
"eval_steps_per_second": 16.289,
|
| 324 |
"step": 5124
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 21.996045413955862,
|
| 328 |
+
"grad_norm": 0.033235229551792145,
|
| 329 |
+
"learning_rate": 6.333333333333333e-05,
|
| 330 |
+
"loss": 0.8128,
|
| 331 |
+
"step": 5368
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 21.996045413955862,
|
| 335 |
+
"eval_loss": 0.8513291478157043,
|
| 336 |
+
"eval_runtime": 25.3035,
|
| 337 |
+
"eval_samples_per_second": 32.644,
|
| 338 |
+
"eval_steps_per_second": 16.322,
|
| 339 |
+
"step": 5368
|
| 340 |
}
|
| 341 |
],
|
| 342 |
"logging_steps": 500,
|
|
|
|
| 351 |
"early_stopping_threshold": 0.0
|
| 352 |
},
|
| 353 |
"attributes": {
|
| 354 |
+
"early_stopping_patience_counter": 3
|
| 355 |
}
|
| 356 |
},
|
| 357 |
"TrainerControl": {
|