Femboyuwu2000
commited on
Commit
•
4f959e3
1
Parent(s):
031ccac
Training in progress, step 7320, 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 sha256:9207586f7a1d2ba4556ac81bf96016c6a6bdc9668c406e8e8639d19d9692cdd0
|
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 sha256:4ed2a524baac54ff9e8afed21d2b42af94fa038aef5ded6b599c9e972dd0477d
|
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 sha256:4e665c9777fc69706bdf0b3707a06c85d4cb2b43fbb10521c503874813f13d69
|
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 sha256:2e2282342021370a0027cf32dfaa491c0a05194df75cc08c2cc5453789cc6933
|
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,
|
@@ -2562,6 +2562,13 @@
|
|
2562 |
"learning_rate": 2.2003915629258607e-05,
|
2563 |
"loss": 3.383,
|
2564 |
"step": 7300
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2565 |
}
|
2566 |
],
|
2567 |
"logging_steps": 20,
|
@@ -2569,7 +2576,7 @@
|
|
2569 |
"num_input_tokens_seen": 0,
|
2570 |
"num_train_epochs": 2,
|
2571 |
"save_steps": 20,
|
2572 |
-
"total_flos": 1.
|
2573 |
"train_batch_size": 8,
|
2574 |
"trial_name": null,
|
2575 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.5856,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 7320,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
2562 |
"learning_rate": 2.2003915629258607e-05,
|
2563 |
"loss": 3.383,
|
2564 |
"step": 7300
|
2565 |
+
},
|
2566 |
+
{
|
2567 |
+
"epoch": 0.59,
|
2568 |
+
"grad_norm": 34.35666275024414,
|
2569 |
+
"learning_rate": 2.196091871970103e-05,
|
2570 |
+
"loss": 3.5508,
|
2571 |
+
"step": 7320
|
2572 |
}
|
2573 |
],
|
2574 |
"logging_steps": 20,
|
|
|
2576 |
"num_input_tokens_seen": 0,
|
2577 |
"num_train_epochs": 2,
|
2578 |
"save_steps": 20,
|
2579 |
+
"total_flos": 1.7308825951961088e+16,
|
2580 |
"train_batch_size": 8,
|
2581 |
"trial_name": null,
|
2582 |
"trial_params": null
|