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 25473712
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fc822dff1982f7d56120f362c9db37c59de6e97757d8301827f9db8f73b3770b
|
3 |
size 25473712
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 13328068
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3fa71d2d9ee1bb1cce46b928d8bdd7ae78bba15fc203c0a817b4fb0798333f1b
|
3 |
size 13328068
|
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 sha256:26f3aba3ce70121145a8f61996f81668c3c3398077f34293a779f925f46c95df
|
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:a2972d8cacb091bd0e98bfff54b2e4933301753087ce149a9bf9a205a5e2d795
|
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": 1,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -22,6 +22,21 @@
|
|
22 |
"eval_samples_per_second": 11.644,
|
23 |
"eval_steps_per_second": 11.644,
|
24 |
"step": 1
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
25 |
}
|
26 |
],
|
27 |
"logging_steps": 1,
|
@@ -36,12 +51,12 @@
|
|
36 |
"should_evaluate": false,
|
37 |
"should_log": false,
|
38 |
"should_save": true,
|
39 |
-
"should_training_stop":
|
40 |
},
|
41 |
"attributes": {}
|
42 |
}
|
43 |
},
|
44 |
-
"total_flos":
|
45 |
"train_batch_size": 1,
|
46 |
"trial_name": null,
|
47 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.0004344048653344917,
|
5 |
"eval_steps": 1,
|
6 |
+
"global_step": 2,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
22 |
"eval_samples_per_second": 11.644,
|
23 |
"eval_steps_per_second": 11.644,
|
24 |
"step": 1
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 0.0004344048653344917,
|
28 |
+
"grad_norm": 0.2792477011680603,
|
29 |
+
"learning_rate": 4e-05,
|
30 |
+
"loss": 2.0684,
|
31 |
+
"step": 2
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"epoch": 0.0004344048653344917,
|
35 |
+
"eval_loss": 1.896620273590088,
|
36 |
+
"eval_runtime": 18.3609,
|
37 |
+
"eval_samples_per_second": 13.235,
|
38 |
+
"eval_steps_per_second": 13.235,
|
39 |
+
"step": 2
|
40 |
}
|
41 |
],
|
42 |
"logging_steps": 1,
|
|
|
51 |
"should_evaluate": false,
|
52 |
"should_log": false,
|
53 |
"should_save": true,
|
54 |
+
"should_training_stop": true
|
55 |
},
|
56 |
"attributes": {}
|
57 |
}
|
58 |
},
|
59 |
+
"total_flos": 20462162411520.0,
|
60 |
"train_batch_size": 1,
|
61 |
"trial_name": null,
|
62 |
"trial_params": null
|