youdiniplays
commited on
Training in progress, step 32500, 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 242041896
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c43564e930260fa3abbd24ef8bc8e2019043f8ab0ea3f357c88632def606095f
|
3 |
size 242041896
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 484163514
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5157a79613ec248ac8f7d1c8901dc35a0467ddf892a8d4eace27612fd7b9473d
|
3 |
size 484163514
|
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:af796267785b8380aa702da74322c3a84f42d9cab004eb98c1af133c0218d64a
|
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 sha256:5b2103b3ba42c5a974b79f170c6d33390323651972016338595643ea512a6c2b
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 4.
|
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,
|
@@ -431,13 +431,19 @@
|
|
431 |
"learning_rate": 1.820135052179251e-05,
|
432 |
"loss": 0.4563,
|
433 |
"step": 32000
|
|
|
|
|
|
|
|
|
|
|
|
|
434 |
}
|
435 |
],
|
436 |
"logging_steps": 500,
|
437 |
"max_steps": 32580,
|
438 |
"num_train_epochs": 5,
|
439 |
"save_steps": 500,
|
440 |
-
"total_flos": 1.
|
441 |
"trial_name": null,
|
442 |
"trial_params": null
|
443 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 4.987722529158994,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 32500,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
431 |
"learning_rate": 1.820135052179251e-05,
|
432 |
"loss": 0.4563,
|
433 |
"step": 32000
|
434 |
+
},
|
435 |
+
{
|
436 |
+
"epoch": 4.99,
|
437 |
+
"learning_rate": 2.885205647636587e-06,
|
438 |
+
"loss": 0.4527,
|
439 |
+
"step": 32500
|
440 |
}
|
441 |
],
|
442 |
"logging_steps": 500,
|
443 |
"max_steps": 32580,
|
444 |
"num_train_epochs": 5,
|
445 |
"save_steps": 500,
|
446 |
+
"total_flos": 1.7233985138589696e+16,
|
447 |
"trial_name": null,
|
448 |
"trial_params": null
|
449 |
}
|