Training in progress, step 10, 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 338298
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7f6fea5ad404951ef6a1fae3508ebdd797dc7d0856e4e095dbade4d136af05bb
|
3 |
size 338298
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 418030
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2e75175f411e54f2d45a172225b45542e61e14c9898d23196763485fc6e8cdc2
|
3 |
size 418030
|
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:b8897608d343d62eeb1707c720b184d47499c9ca79a71524526ea1ab75dc3c5d
|
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:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
|
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": 5,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -30,6 +30,28 @@
|
|
30 |
"eval_samples_per_second": 726.735,
|
31 |
"eval_steps_per_second": 94.792,
|
32 |
"step": 5
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
33 |
}
|
34 |
],
|
35 |
"logging_steps": 3,
|
@@ -49,7 +71,7 @@
|
|
49 |
"attributes": {}
|
50 |
}
|
51 |
},
|
52 |
-
"total_flos":
|
53 |
"train_batch_size": 8,
|
54 |
"trial_name": null,
|
55 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.3669724770642202,
|
5 |
"eval_steps": 5,
|
6 |
+
"global_step": 10,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
30 |
"eval_samples_per_second": 726.735,
|
31 |
"eval_steps_per_second": 94.792,
|
32 |
"step": 5
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.22018348623853212,
|
36 |
+
"grad_norm": 0.4511624872684479,
|
37 |
+
"learning_rate": 6e-05,
|
38 |
+
"loss": 6.9388,
|
39 |
+
"step": 6
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.3302752293577982,
|
43 |
+
"grad_norm": 0.44215646386146545,
|
44 |
+
"learning_rate": 9e-05,
|
45 |
+
"loss": 6.9322,
|
46 |
+
"step": 9
|
47 |
+
},
|
48 |
+
{
|
49 |
+
"epoch": 0.3669724770642202,
|
50 |
+
"eval_loss": 6.922896862030029,
|
51 |
+
"eval_runtime": 0.0602,
|
52 |
+
"eval_samples_per_second": 763.509,
|
53 |
+
"eval_steps_per_second": 99.588,
|
54 |
+
"step": 10
|
55 |
}
|
56 |
],
|
57 |
"logging_steps": 3,
|
|
|
71 |
"attributes": {}
|
72 |
}
|
73 |
},
|
74 |
+
"total_flos": 225865089024.0,
|
75 |
"train_batch_size": 8,
|
76 |
"trial_name": null,
|
77 |
"trial_params": null
|