Training in progress, step 2, 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 73911112
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f2adc6f32ee750b5d36ebda3230804d5af98aedd7f023a63a32f8468951fd6c5
|
3 |
size 73911112
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 37430836
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c541a949f194988c45d1cf25c06469a8ca1e34174053d491aefb85c4b9a615c8
|
3 |
size 37430836
|
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:e5b645890a1b67536e13774bde1ab40b573ebb83518805012b5109e6542b9748
|
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": 2.0000000000000003e-06,
|
15 |
"loss": 2.0959,
|
16 |
"step": 1
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
17 |
}
|
18 |
],
|
19 |
"logging_steps": 1,
|
@@ -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": 0.0054869684499314125,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 2,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
14 |
"learning_rate": 2.0000000000000003e-06,
|
15 |
"loss": 2.0959,
|
16 |
"step": 1
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.0054869684499314125,
|
20 |
+
"grad_norm": 1.8936893939971924,
|
21 |
+
"learning_rate": 4.000000000000001e-06,
|
22 |
+
"loss": 2.099,
|
23 |
+
"step": 2
|
24 |
}
|
25 |
],
|
26 |
"logging_steps": 1,
|
|
|
40 |
"attributes": {}
|
41 |
}
|
42 |
},
|
43 |
+
"total_flos": 2467855513350144.0,
|
44 |
"train_batch_size": 4,
|
45 |
"trial_name": null,
|
46 |
"trial_params": null
|