bhuvanmdev
commited on
Training in progress, step 600, 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 sha256:7e4aa0619718301c4cee6a46cec390e99f468dbc3294652a09dad80c2c1c52ac
|
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 sha256:2f3f0d6d31265332cf0153ce373f616a507a1b2bdb68c61151d6f231efb64720
|
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 sha256:5a3896f4879562a69571237c21fd91dc0cba3215ed23fb9ae7f0374432fee52f
|
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:a18b7d573288acd75186bfa1799a658370b6b400daf569612aa7a4ba8b0298a1
|
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,
|
@@ -471,14 +471,30 @@
|
|
471 |
"loss": 0.4258,
|
472 |
"num_input_tokens_seen": 386577,
|
473 |
"step": 580
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
474 |
}
|
475 |
],
|
476 |
"logging_steps": 10,
|
477 |
"max_steps": 2795,
|
478 |
-
"num_input_tokens_seen":
|
479 |
"num_train_epochs": 1,
|
480 |
"save_steps": 20,
|
481 |
-
"total_flos":
|
482 |
"train_batch_size": 1,
|
483 |
"trial_name": null,
|
484 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.2146690518783542,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 600,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
471 |
"loss": 0.4258,
|
472 |
"num_input_tokens_seen": 386577,
|
473 |
"step": 580
|
474 |
+
},
|
475 |
+
{
|
476 |
+
"epoch": 0.2110912343470483,
|
477 |
+
"grad_norm": 0.2969113886356354,
|
478 |
+
"learning_rate": 0.00015778175313059035,
|
479 |
+
"loss": 0.433,
|
480 |
+
"num_input_tokens_seen": 392953,
|
481 |
+
"step": 590
|
482 |
+
},
|
483 |
+
{
|
484 |
+
"epoch": 0.2146690518783542,
|
485 |
+
"grad_norm": 0.4132014811038971,
|
486 |
+
"learning_rate": 0.00015706618962432918,
|
487 |
+
"loss": 0.4148,
|
488 |
+
"num_input_tokens_seen": 399368,
|
489 |
+
"step": 600
|
490 |
}
|
491 |
],
|
492 |
"logging_steps": 10,
|
493 |
"max_steps": 2795,
|
494 |
+
"num_input_tokens_seen": 399368,
|
495 |
"num_train_epochs": 1,
|
496 |
"save_steps": 20,
|
497 |
+
"total_flos": 8980375995039744.0,
|
498 |
"train_batch_size": 1,
|
499 |
"trial_name": null,
|
500 |
"trial_params": null
|