Commit
•
4d19ee6
1
Parent(s):
2984952
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 167832240
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dbc59f60f0b03fc7d848bb49dd337a2c313e7da3137d63d5330c2fd0bf931778
|
3 |
size 167832240
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 84581014
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:674fd7d1b2da8e8b572dcd8c5c60764fe92b223569cb37500fc42668fb9f866e
|
3 |
size 84581014
|
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:b38798aed442913f3edb40ed2e6dd248c47415757a186238aa4d86325b07c484
|
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:f02eb1d87c6e64756c982d23c5194d17c9b128eb05ac315db5c766e38219aacd
|
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": 2000,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -21,6 +21,13 @@
|
|
21 |
"learning_rate": 1.9999999832252933e-05,
|
22 |
"loss": 1.6278,
|
23 |
"step": 400
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
24 |
}
|
25 |
],
|
26 |
"logging_steps": 200,
|
@@ -28,7 +35,7 @@
|
|
28 |
"num_input_tokens_seen": 0,
|
29 |
"num_train_epochs": 5,
|
30 |
"save_steps": 200,
|
31 |
-
"total_flos":
|
32 |
"train_batch_size": 1,
|
33 |
"trial_name": null,
|
34 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.00044619783668415513,
|
5 |
"eval_steps": 2000,
|
6 |
+
"global_step": 600,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
21 |
"learning_rate": 1.9999999832252933e-05,
|
22 |
"loss": 1.6278,
|
23 |
"step": 400
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.0,
|
27 |
+
"grad_norm": 3.7490854263305664,
|
28 |
+
"learning_rate": 1.9999999617416517e-05,
|
29 |
+
"loss": 1.6314,
|
30 |
+
"step": 600
|
31 |
}
|
32 |
],
|
33 |
"logging_steps": 200,
|
|
|
35 |
"num_input_tokens_seen": 0,
|
36 |
"num_train_epochs": 5,
|
37 |
"save_steps": 200,
|
38 |
+
"total_flos": 7590307482550272.0,
|
39 |
"train_batch_size": 1,
|
40 |
"trial_name": null,
|
41 |
"trial_params": null
|