ramdhanfirdaus
commited on
Commit
•
0a891fb
1
Parent(s):
b65de1d
Training in progress, step 3300, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 75507072
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f9fbac71c01cba7e8118b8c9fab28a8d81e85098d1de0924653bd43c32e500cc
|
3 |
size 75507072
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 151032837
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a80fcc843a3281e0dadf6911b688c69eab2e4b01e06a04cd7cfcd3e066e45ba1
|
3 |
size 151032837
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:268b907a92307342b44ca97f05d9955310c3f825328fc98573f8ff3422c6bc0a
|
3 |
size 14575
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ad85ddedbe158ea4b6f60faba10617b6fb17a69c778e6d7c0a8e4338dd95e31f
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": 1.1677733659744263,
|
3 |
"best_model_checkpoint": "./outputs/checkpoint-3100",
|
4 |
-
"epoch": 2.
|
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,
|
@@ -455,13 +455,27 @@
|
|
455 |
"eval_samples_per_second": 18.492,
|
456 |
"eval_steps_per_second": 2.314,
|
457 |
"step": 3200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
458 |
}
|
459 |
],
|
460 |
"logging_steps": 100,
|
461 |
"max_steps": 4116,
|
462 |
"num_train_epochs": 3,
|
463 |
"save_steps": 100,
|
464 |
-
"total_flos": 1.
|
465 |
"trial_name": null,
|
466 |
"trial_params": null
|
467 |
}
|
|
|
1 |
{
|
2 |
"best_metric": 1.1677733659744263,
|
3 |
"best_model_checkpoint": "./outputs/checkpoint-3100",
|
4 |
+
"epoch": 2.4051001821493623,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 3300,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
455 |
"eval_samples_per_second": 18.492,
|
456 |
"eval_steps_per_second": 2.314,
|
457 |
"step": 3200
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 2.41,
|
461 |
+
"learning_rate": 0.0002,
|
462 |
+
"loss": 1.142,
|
463 |
+
"step": 3300
|
464 |
+
},
|
465 |
+
{
|
466 |
+
"epoch": 2.41,
|
467 |
+
"eval_loss": 1.168481469154358,
|
468 |
+
"eval_runtime": 345.6314,
|
469 |
+
"eval_samples_per_second": 18.152,
|
470 |
+
"eval_steps_per_second": 2.271,
|
471 |
+
"step": 3300
|
472 |
}
|
473 |
],
|
474 |
"logging_steps": 100,
|
475 |
"max_steps": 4116,
|
476 |
"num_train_epochs": 3,
|
477 |
"save_steps": 100,
|
478 |
+
"total_flos": 1.070057571942399e+18,
|
479 |
"trial_name": null,
|
480 |
"trial_params": null
|
481 |
}
|