Femboyuwu2000
commited on
Commit
•
5b52b3c
1
Parent(s):
7afc73b
Training in progress, step 7240, 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 13982248
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f9f04251e463450f35446dc22e021f6c9044fcdc00275a99ce69fc6afd696a20
|
3 |
size 13982248
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 7062522
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5419bb4aaab7e0dd3ffd695a7210671fdaf57f5ee5535e99d1328b186ac853c3
|
3 |
size 7062522
|
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 sha256:13dea0908d6d2c4a230edba574b9ef1b909b1f3e549fde10d325fea8eadf947f
|
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 sha256:957eed2d1d64bc3d33fd608918e084dfadc6685aa1ba1a370b937a7f5aa867a5
|
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,
|
@@ -2534,6 +2534,13 @@
|
|
2534 |
"learning_rate": 2.217516409129699e-05,
|
2535 |
"loss": 3.5408,
|
2536 |
"step": 7220
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2537 |
}
|
2538 |
],
|
2539 |
"logging_steps": 20,
|
@@ -2541,7 +2548,7 @@
|
|
2541 |
"num_input_tokens_seen": 0,
|
2542 |
"num_train_epochs": 2,
|
2543 |
"save_steps": 20,
|
2544 |
-
"total_flos": 1.
|
2545 |
"train_batch_size": 8,
|
2546 |
"trial_name": null,
|
2547 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.5792,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 7240,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
2534 |
"learning_rate": 2.217516409129699e-05,
|
2535 |
"loss": 3.5408,
|
2536 |
"step": 7220
|
2537 |
+
},
|
2538 |
+
{
|
2539 |
+
"epoch": 0.58,
|
2540 |
+
"grad_norm": 42.050819396972656,
|
2541 |
+
"learning_rate": 2.2132463751155815e-05,
|
2542 |
+
"loss": 3.4422,
|
2543 |
+
"step": 7240
|
2544 |
}
|
2545 |
],
|
2546 |
"logging_steps": 20,
|
|
|
2548 |
"num_input_tokens_seen": 0,
|
2549 |
"num_train_epochs": 2,
|
2550 |
"save_steps": 20,
|
2551 |
+
"total_flos": 1.7108381826121728e+16,
|
2552 |
"train_batch_size": 8,
|
2553 |
"trial_name": null,
|
2554 |
"trial_params": null
|