Femboyuwu2000
commited on
Commit
•
e9d9f1e
1
Parent(s):
f964374
Training in progress, step 60, 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 4725640
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2c298b8d29721f1a4fd059d2f89a9b9fa32c198dfd1c61a543ce2528f1633521
|
3 |
size 4725640
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2423738
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3cf9bd0d28841e12abecfcec04a14111a498a44744e24011ff450cfc96e35c59
|
3 |
size 2423738
|
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:e422da58c8a0b49f3d386208a0013d612d2dee8f163b4d0b7cbdeec12a9cb276
|
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:b5fd95998f2185221faccede1a4757f84b8410ed13433fcc8caae08a9f81bda9
|
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":
|
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,
|
@@ -21,6 +21,13 @@
|
|
21 |
"learning_rate": 6.666666666666667e-06,
|
22 |
"loss": 3.6917,
|
23 |
"step": 40
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
24 |
}
|
25 |
],
|
26 |
"logging_steps": 20,
|
@@ -28,7 +35,7 @@
|
|
28 |
"num_input_tokens_seen": 0,
|
29 |
"num_train_epochs": 1,
|
30 |
"save_steps": 20,
|
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": 4.669515070859891e-05,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 60,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
21 |
"learning_rate": 6.666666666666667e-06,
|
22 |
"loss": 3.6917,
|
23 |
"step": 40
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.0,
|
27 |
+
"grad_norm": 0.9262466430664062,
|
28 |
+
"learning_rate": 1e-05,
|
29 |
+
"loss": 3.5828,
|
30 |
+
"step": 60
|
31 |
}
|
32 |
],
|
33 |
"logging_steps": 20,
|
|
|
35 |
"num_input_tokens_seen": 0,
|
36 |
"num_train_epochs": 1,
|
37 |
"save_steps": 20,
|
38 |
+
"total_flos": 362851299717120.0,
|
39 |
"train_batch_size": 1,
|
40 |
"trial_name": null,
|
41 |
"trial_params": null
|