Commit
•
ddd7d11
1
Parent(s):
67828d4
Training in progress, step 1000, 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 sha256:4cc0e03b9e41c36bebd5290c036c6ab8219fc845aed5c0fa6e9fcd25304615e4
|
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 sha256:6b25ff21c077ced998e166c13b16ca46c3928f2a8dec143c1e29895bcf0ed63e
|
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 sha256:437c777924390da1dedc2bce8c9e0b6f4eb89d30ea814cea3a93ff7b5d5fae05
|
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 sha256:89ee446e7e0c91089e5e6b7b626fa10c97dc177ed58fc09c887e3e9c3cd58b38
|
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,
|
@@ -35,6 +35,13 @@
|
|
35 |
"learning_rate": 1.999999931524823e-05,
|
36 |
"loss": 1.5416,
|
37 |
"step": 800
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
38 |
}
|
39 |
],
|
40 |
"logging_steps": 200,
|
@@ -42,7 +49,7 @@
|
|
42 |
"num_input_tokens_seen": 0,
|
43 |
"num_train_epochs": 5,
|
44 |
"save_steps": 200,
|
45 |
-
"total_flos":
|
46 |
"train_batch_size": 1,
|
47 |
"trial_name": null,
|
48 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.0007436630611402585,
|
5 |
"eval_steps": 2000,
|
6 |
+
"global_step": 1000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
35 |
"learning_rate": 1.999999931524823e-05,
|
36 |
"loss": 1.5416,
|
37 |
"step": 800
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.0,
|
41 |
+
"grad_norm": 2.783194065093994,
|
42 |
+
"learning_rate": 1.999999892574807e-05,
|
43 |
+
"loss": 1.5775,
|
44 |
+
"step": 1000
|
45 |
}
|
46 |
],
|
47 |
"logging_steps": 200,
|
|
|
49 |
"num_input_tokens_seen": 0,
|
50 |
"num_train_epochs": 5,
|
51 |
"save_steps": 200,
|
52 |
+
"total_flos": 1.2689424120840192e+16,
|
53 |
"train_batch_size": 1,
|
54 |
"trial_name": null,
|
55 |
"trial_params": null
|