Training in progress, step 10, checkpoint
Browse files
last-checkpoint/adapter_config.json
CHANGED
@@ -23,8 +23,8 @@
|
|
23 |
"rank_pattern": {},
|
24 |
"revision": null,
|
25 |
"target_modules": [
|
26 |
-
"
|
27 |
-
"
|
28 |
],
|
29 |
"task_type": null,
|
30 |
"use_dora": false,
|
|
|
23 |
"rank_pattern": {},
|
24 |
"revision": null,
|
25 |
"target_modules": [
|
26 |
+
"v_proj",
|
27 |
+
"q_proj"
|
28 |
],
|
29 |
"task_type": null,
|
30 |
"use_dora": false,
|
last-checkpoint/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14176064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4249fc60c02d73e11e8bc01e6f01ad69dbfe9504bda27462a4d6a90387c62059
|
3 |
size 14176064
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4832762
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bb82c8112b4ee1108a7a436127991211db14476bea72bf1681b578faa99faa1b
|
3 |
size 4832762
|
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 sha256:2fe5cb724c80f2b5ae778324957df6b558aa4d12a687bff8c88f1d42b2b6f37d
|
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
@@ -1,44 +1,28 @@
|
|
1 |
{
|
2 |
-
"best_metric":
|
3 |
-
"best_model_checkpoint": "../openai/whisper-small-finetuned/checkpoint-
|
4 |
-
"epoch":
|
5 |
"eval_steps": 10,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 9.05,
|
13 |
-
"grad_norm":
|
14 |
"learning_rate": 0.0001,
|
15 |
-
"loss": 3.
|
16 |
"step": 10
|
17 |
},
|
18 |
{
|
19 |
"epoch": 9.05,
|
20 |
-
"eval_loss": 4.
|
21 |
-
"eval_runtime":
|
22 |
-
"eval_samples_per_second": 0.
|
23 |
-
"eval_steps_per_second": 0.
|
24 |
-
"eval_wer":
|
25 |
"step": 10
|
26 |
-
},
|
27 |
-
{
|
28 |
-
"epoch": 19.05,
|
29 |
-
"grad_norm": 1.7581746578216553,
|
30 |
-
"learning_rate": 0.0001,
|
31 |
-
"loss": 2.5488,
|
32 |
-
"step": 20
|
33 |
-
},
|
34 |
-
{
|
35 |
-
"epoch": 19.05,
|
36 |
-
"eval_loss": 3.7888872623443604,
|
37 |
-
"eval_runtime": 20.1621,
|
38 |
-
"eval_samples_per_second": 0.496,
|
39 |
-
"eval_steps_per_second": 0.05,
|
40 |
-
"eval_wer": 80.45977011494253,
|
41 |
-
"step": 20
|
42 |
}
|
43 |
],
|
44 |
"logging_steps": 10,
|
@@ -53,12 +37,12 @@
|
|
53 |
"should_evaluate": false,
|
54 |
"should_log": false,
|
55 |
"should_save": true,
|
56 |
-
"should_training_stop":
|
57 |
},
|
58 |
"attributes": {}
|
59 |
}
|
60 |
},
|
61 |
-
"total_flos":
|
62 |
"train_batch_size": 64,
|
63 |
"trial_name": null,
|
64 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 86.20689655172413,
|
3 |
+
"best_model_checkpoint": "../openai/whisper-small-finetuned/checkpoint-10",
|
4 |
+
"epoch": 9.05,
|
5 |
"eval_steps": 10,
|
6 |
+
"global_step": 10,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 9.05,
|
13 |
+
"grad_norm": 2.856374979019165,
|
14 |
"learning_rate": 0.0001,
|
15 |
+
"loss": 3.8241,
|
16 |
"step": 10
|
17 |
},
|
18 |
{
|
19 |
"epoch": 9.05,
|
20 |
+
"eval_loss": 4.503547668457031,
|
21 |
+
"eval_runtime": 21.6607,
|
22 |
+
"eval_samples_per_second": 0.462,
|
23 |
+
"eval_steps_per_second": 0.046,
|
24 |
+
"eval_wer": 86.20689655172413,
|
25 |
"step": 10
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
26 |
}
|
27 |
],
|
28 |
"logging_steps": 10,
|
|
|
37 |
"should_evaluate": false,
|
38 |
"should_log": false,
|
39 |
"should_save": true,
|
40 |
+
"should_training_stop": false
|
41 |
},
|
42 |
"attributes": {}
|
43 |
}
|
44 |
},
|
45 |
+
"total_flos": 5.8736295936e+16,
|
46 |
"train_batch_size": 64,
|
47 |
"trial_name": null,
|
48 |
"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 5368
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:025352e1b9b0004ec98c8fb41c0f5d7b60ab520385a6d2ce5a8ad7ebc387f3fa
|
3 |
size 5368
|