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 |
+
"q_proj",
|
27 |
+
"v_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 sha256:594276723c64b04e968b8136e50797045a2fd81affccbc403804789798325491
|
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:ba8d1bf6d57df86c1f4891cdcec76e988bae42c723e48d87bf796db11ca562ba
|
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 sha256:04efbc6f9ffd7b199a7f87885642c493f089d3e20dfb5e636ceca3298853a739
|
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 sha256:6a3d18e607a27cfab9cec7cfaa7384cdb877a2330c4bcd4e1efcae25be9908cb
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,66 +1,34 @@
|
|
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": 2.
|
13 |
-
"grad_norm":
|
14 |
-
"learning_rate":
|
15 |
-
"loss":
|
16 |
"step": 10
|
17 |
},
|
18 |
{
|
19 |
-
"epoch": 2.
|
20 |
-
"eval_loss":
|
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": 5.0,
|
29 |
-
"grad_norm": 2.3013181686401367,
|
30 |
-
"learning_rate": 0.0001,
|
31 |
-
"loss": 3.3483,
|
32 |
-
"step": 20
|
33 |
-
},
|
34 |
-
{
|
35 |
-
"epoch": 5.0,
|
36 |
-
"eval_loss": 2.877688407897949,
|
37 |
-
"eval_runtime": 7.453,
|
38 |
-
"eval_samples_per_second": 0.805,
|
39 |
-
"eval_steps_per_second": 0.134,
|
40 |
-
"eval_wer": 160.0,
|
41 |
-
"step": 20
|
42 |
-
},
|
43 |
-
{
|
44 |
-
"epoch": 7.5,
|
45 |
-
"grad_norm": 1.4187573194503784,
|
46 |
-
"learning_rate": 0.0001,
|
47 |
-
"loss": 2.8809,
|
48 |
-
"step": 30
|
49 |
-
},
|
50 |
-
{
|
51 |
-
"epoch": 7.5,
|
52 |
-
"eval_loss": 2.703684091567993,
|
53 |
-
"eval_runtime": 7.2586,
|
54 |
-
"eval_samples_per_second": 0.827,
|
55 |
-
"eval_steps_per_second": 0.138,
|
56 |
-
"eval_wer": 132.5,
|
57 |
-
"step": 30
|
58 |
}
|
59 |
],
|
60 |
"logging_steps": 10,
|
61 |
"max_steps": 30,
|
62 |
"num_input_tokens_seen": 0,
|
63 |
-
"num_train_epochs":
|
64 |
"save_steps": 10,
|
65 |
"stateful_callbacks": {
|
66 |
"TrainerControl": {
|
@@ -69,12 +37,12 @@
|
|
69 |
"should_evaluate": false,
|
70 |
"should_log": false,
|
71 |
"should_save": true,
|
72 |
-
"should_training_stop":
|
73 |
},
|
74 |
"attributes": {}
|
75 |
}
|
76 |
},
|
77 |
-
"total_flos":
|
78 |
"train_batch_size": 16,
|
79 |
"trial_name": null,
|
80 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 87.35632183908046,
|
3 |
+
"best_model_checkpoint": "../openai/whisper-small-finetuned/checkpoint-10",
|
4 |
+
"epoch": 2.066666666666667,
|
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": 2.066666666666667,
|
13 |
+
"grad_norm": 10.810166358947754,
|
14 |
+
"learning_rate": 8e-05,
|
15 |
+
"loss": 4.164,
|
16 |
"step": 10
|
17 |
},
|
18 |
{
|
19 |
+
"epoch": 2.066666666666667,
|
20 |
+
"eval_loss": 5.153946399688721,
|
21 |
+
"eval_runtime": 21.4772,
|
22 |
+
"eval_samples_per_second": 0.466,
|
23 |
+
"eval_steps_per_second": 0.047,
|
24 |
+
"eval_wer": 87.35632183908046,
|
25 |
"step": 10
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
26 |
}
|
27 |
],
|
28 |
"logging_steps": 10,
|
29 |
"max_steps": 30,
|
30 |
"num_input_tokens_seen": 0,
|
31 |
+
"num_train_epochs": 9223372036854775807,
|
32 |
"save_steps": 10,
|
33 |
"stateful_callbacks": {
|
34 |
"TrainerControl": {
|
|
|
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": 3.876595531776e+16,
|
46 |
"train_batch_size": 16,
|
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 sha256:258672aba0d0ae4504c51cbe13641b4f74a81f526bf53ae0abdea7fa190c182f
|
3 |
size 5368
|