Training in progress, step 1960, 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 80013120
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6f6a966a7b6dc94fce248a3fd714b53cfa8886f737dc508e97110b7be08da6a8
|
3 |
size 80013120
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 41120084
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8d94daeaa571d8aaf1be97bc957cf7397e7c5a38f958d70f544c4173058fd7bb
|
3 |
size 41120084
|
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 sha256:29bb1cdc1cbe9d42402cc945935c11cb9d50132de7df60daee28fe9ac618e7e9
|
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:cce9e9bb68fed6beb84e222761997e8c01b8a4cf8f587619d50a53df07c9686c
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": 0.646575927734375,
|
3 |
"best_model_checkpoint": "miner_id_24/checkpoint-1840",
|
4 |
-
"epoch": 2.
|
5 |
"eval_steps": 40,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -532,6 +532,14 @@
|
|
532 |
"eval_samples_per_second": 32.5,
|
533 |
"eval_steps_per_second": 1.13,
|
534 |
"step": 1920
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
535 |
}
|
536 |
],
|
537 |
"logging_steps": 100,
|
@@ -546,7 +554,7 @@
|
|
546 |
"early_stopping_threshold": 0.0
|
547 |
},
|
548 |
"attributes": {
|
549 |
-
"early_stopping_patience_counter":
|
550 |
}
|
551 |
},
|
552 |
"TrainerControl": {
|
@@ -555,12 +563,12 @@
|
|
555 |
"should_evaluate": false,
|
556 |
"should_log": false,
|
557 |
"should_save": true,
|
558 |
-
"should_training_stop":
|
559 |
},
|
560 |
"attributes": {}
|
561 |
}
|
562 |
},
|
563 |
-
"total_flos": 3.
|
564 |
"train_batch_size": 4,
|
565 |
"trial_name": null,
|
566 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": 0.646575927734375,
|
3 |
"best_model_checkpoint": "miner_id_24/checkpoint-1840",
|
4 |
+
"epoch": 2.798001427551749,
|
5 |
"eval_steps": 40,
|
6 |
+
"global_step": 1960,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
532 |
"eval_samples_per_second": 32.5,
|
533 |
"eval_steps_per_second": 1.13,
|
534 |
"step": 1920
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 2.798001427551749,
|
538 |
+
"eval_loss": 0.6539962887763977,
|
539 |
+
"eval_runtime": 3.4712,
|
540 |
+
"eval_samples_per_second": 33.13,
|
541 |
+
"eval_steps_per_second": 1.152,
|
542 |
+
"step": 1960
|
543 |
}
|
544 |
],
|
545 |
"logging_steps": 100,
|
|
|
554 |
"early_stopping_threshold": 0.0
|
555 |
},
|
556 |
"attributes": {
|
557 |
+
"early_stopping_patience_counter": 3
|
558 |
}
|
559 |
},
|
560 |
"TrainerControl": {
|
|
|
563 |
"should_evaluate": false,
|
564 |
"should_log": false,
|
565 |
"should_save": true,
|
566 |
+
"should_training_stop": true
|
567 |
},
|
568 |
"attributes": {}
|
569 |
}
|
570 |
},
|
571 |
+
"total_flos": 3.3002531516841984e+17,
|
572 |
"train_batch_size": 4,
|
573 |
"trial_name": null,
|
574 |
"trial_params": null
|