Training in progress, step 1000, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 891558696
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ac0c962a0eda85260ede8e30cc73642b68ebed50669f401f16dbed1ed6777753
|
3 |
size 891558696
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1783272762
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f020998ad3e170323d3dbfe3bb9ca2540dd474cc9e6e6c8fda5c88676dd92211
|
3 |
size 1783272762
|
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 sha256:8a7bccffbe4567a72e1b938cd6f7b1d19b05b0d573111e28fd70761fd6902354
|
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 sha256:076f7297321633aac2a22709539d95124e240b5a9f52d9eadd240f996e114a1c
|
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,
|
@@ -14,6 +14,13 @@
|
|
14 |
"learning_rate": 1.856649395509499e-05,
|
15 |
"loss": 0.8043,
|
16 |
"step": 500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
17 |
}
|
18 |
],
|
19 |
"logging_steps": 500,
|
@@ -33,7 +40,7 @@
|
|
33 |
"attributes": {}
|
34 |
}
|
35 |
},
|
36 |
-
"total_flos":
|
37 |
"train_batch_size": 4,
|
38 |
"trial_name": null,
|
39 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.4317789291882556,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 1000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
14 |
"learning_rate": 1.856649395509499e-05,
|
15 |
"loss": 0.8043,
|
16 |
"step": 500
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.4317789291882556,
|
20 |
+
"grad_norm": 0.8806478977203369,
|
21 |
+
"learning_rate": 1.7127230857800806e-05,
|
22 |
+
"loss": 0.4945,
|
23 |
+
"step": 1000
|
24 |
}
|
25 |
],
|
26 |
"logging_steps": 500,
|
|
|
40 |
"attributes": {}
|
41 |
}
|
42 |
},
|
43 |
+
"total_flos": 2435831562240000.0,
|
44 |
"train_batch_size": 4,
|
45 |
"trial_name": null,
|
46 |
"trial_params": null
|
last-checkpoint/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5432
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d2d71d788b491a41c54d3b024285748be4a2e443d732e96343f48dd9941e304a
|
3 |
size 5432
|