bhuvanmdev
commited on
Commit
•
90fc220
1
Parent(s):
2cafdde
Training in progress, step 720, 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 100697728
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:11e234e6249350439636d7460378ee2b84249d14c6dee3a2c36d73b5ec77f8e5
|
3 |
size 100697728
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 201541754
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b0614d4a3d74c8935ea6bb9dfae42e46c97cd7a85de759de2654b36d6e052287
|
3 |
size 201541754
|
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:b80bcd6f3ab18b8a6e4e1a9815a1a307d56309444ef6ece4e0c9e33db3626434
|
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 sha256:877a12ad1f9d0e7e38bfcb4ffb7f44565110e6cdabfb95d8ce3554269a9604e7
|
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": 0.
|
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,
|
@@ -567,14 +567,30 @@
|
|
567 |
"loss": 0.4111,
|
568 |
"num_input_tokens_seen": 468333,
|
569 |
"step": 700
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
570 |
}
|
571 |
],
|
572 |
"logging_steps": 10,
|
573 |
"max_steps": 2795,
|
574 |
-
"num_input_tokens_seen":
|
575 |
"num_train_epochs": 1,
|
576 |
"save_steps": 20,
|
577 |
-
"total_flos": 1.
|
578 |
"train_batch_size": 1,
|
579 |
"trial_name": null,
|
580 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.25760286225402507,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 720,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
567 |
"loss": 0.4111,
|
568 |
"num_input_tokens_seen": 468333,
|
569 |
"step": 700
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 0.25402504472271914,
|
573 |
+
"grad_norm": 0.35491397976875305,
|
574 |
+
"learning_rate": 0.0001491949910554562,
|
575 |
+
"loss": 0.4215,
|
576 |
+
"num_input_tokens_seen": 476220,
|
577 |
+
"step": 710
|
578 |
+
},
|
579 |
+
{
|
580 |
+
"epoch": 0.25760286225402507,
|
581 |
+
"grad_norm": 0.3560994863510132,
|
582 |
+
"learning_rate": 0.000148479427549195,
|
583 |
+
"loss": 0.4011,
|
584 |
+
"num_input_tokens_seen": 481867,
|
585 |
+
"step": 720
|
586 |
}
|
587 |
],
|
588 |
"logging_steps": 10,
|
589 |
"max_steps": 2795,
|
590 |
+
"num_input_tokens_seen": 481867,
|
591 |
"num_train_epochs": 1,
|
592 |
"save_steps": 20,
|
593 |
+
"total_flos": 1.0835487168731136e+16,
|
594 |
"train_batch_size": 1,
|
595 |
"trial_name": null,
|
596 |
"trial_params": null
|