bhuvanmdev
commited on
Training in progress, step 840, 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 sha256:2bd269f9603e3fe38017dedc2c25f29d5956ffac0a0680ff4be53723cc230308
|
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 sha256:169e61d06045c7d645f7845cd193774033d2c62e8074bc7f3bcd8b429da9c1ff
|
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:cebdc5bb99a062fec3bff67f2ffff14c060d2d591a43384bf4d1c5af4cf78ddb
|
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:d27f27dc8317758e5054e3267c676ecc55b2a293cbb2708d11be857eb327f7ee
|
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,
|
@@ -663,14 +663,30 @@
|
|
663 |
"loss": 0.4142,
|
664 |
"num_input_tokens_seen": 548183,
|
665 |
"step": 820
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
666 |
}
|
667 |
],
|
668 |
"logging_steps": 10,
|
669 |
"max_steps": 2795,
|
670 |
-
"num_input_tokens_seen":
|
671 |
"num_train_epochs": 1,
|
672 |
"save_steps": 20,
|
673 |
-
"total_flos": 1.
|
674 |
"train_batch_size": 1,
|
675 |
"trial_name": null,
|
676 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.3005366726296959,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 840,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
663 |
"loss": 0.4142,
|
664 |
"num_input_tokens_seen": 548183,
|
665 |
"step": 820
|
666 |
+
},
|
667 |
+
{
|
668 |
+
"epoch": 0.29695885509839,
|
669 |
+
"grad_norm": 0.4515162408351898,
|
670 |
+
"learning_rate": 0.00014060822898032203,
|
671 |
+
"loss": 0.404,
|
672 |
+
"num_input_tokens_seen": 553861,
|
673 |
+
"step": 830
|
674 |
+
},
|
675 |
+
{
|
676 |
+
"epoch": 0.3005366726296959,
|
677 |
+
"grad_norm": 0.3883764147758484,
|
678 |
+
"learning_rate": 0.00013989266547406083,
|
679 |
+
"loss": 0.4159,
|
680 |
+
"num_input_tokens_seen": 559943,
|
681 |
+
"step": 840
|
682 |
}
|
683 |
],
|
684 |
"logging_steps": 10,
|
685 |
"max_steps": 2795,
|
686 |
+
"num_input_tokens_seen": 559943,
|
687 |
"num_train_epochs": 1,
|
688 |
"save_steps": 20,
|
689 |
+
"total_flos": 1.2591140691769344e+16,
|
690 |
"train_batch_size": 1,
|
691 |
"trial_name": null,
|
692 |
"trial_params": null
|