Femboyuwu2000
commited on
Commit
•
d7c7222
1
Parent(s):
bad397e
Training in progress, step 7300, 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 sha256:3a52d3aebc745997444b80e72ec09e226afd5a99557d76e34a1b13969cf5d61d
|
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 sha256:52bbd26c212eea59edc5f649f9001603135f658009db370b17972f35f1abb4da
|
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 sha256:48e8df376ed8ca40f750413e4fc0d09be8b4d3f7406bb14ff346d7809ea7d2d4
|
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:e78c9cc3d7149ab8bfd36f96fc8ce484bf89881c8836070f722c74f3d3664117
|
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,
|
@@ -2555,6 +2555,13 @@
|
|
2555 |
"learning_rate": 2.2046839071055436e-05,
|
2556 |
"loss": 3.3627,
|
2557 |
"step": 7280
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2558 |
}
|
2559 |
],
|
2560 |
"logging_steps": 20,
|
@@ -2562,7 +2569,7 @@
|
|
2562 |
"num_input_tokens_seen": 0,
|
2563 |
"num_train_epochs": 2,
|
2564 |
"save_steps": 20,
|
2565 |
-
"total_flos": 1.
|
2566 |
"train_batch_size": 8,
|
2567 |
"trial_name": null,
|
2568 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.584,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 7300,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
2555 |
"learning_rate": 2.2046839071055436e-05,
|
2556 |
"loss": 3.3627,
|
2557 |
"step": 7280
|
2558 |
+
},
|
2559 |
+
{
|
2560 |
+
"epoch": 0.58,
|
2561 |
+
"grad_norm": 33.21296310424805,
|
2562 |
+
"learning_rate": 2.2003915629258607e-05,
|
2563 |
+
"loss": 3.383,
|
2564 |
+
"step": 7300
|
2565 |
}
|
2566 |
],
|
2567 |
"logging_steps": 20,
|
|
|
2569 |
"num_input_tokens_seen": 0,
|
2570 |
"num_train_epochs": 2,
|
2571 |
"save_steps": 20,
|
2572 |
+
"total_flos": 1.7258600099807232e+16,
|
2573 |
"train_batch_size": 8,
|
2574 |
"trial_name": null,
|
2575 |
"trial_params": null
|