Training in progress, step 100, 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 sha256:238874a7c1f3a0d95cf127928afcb8064e03764b5ea560cd5a7154a34c6d6ece
|
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 sha256:7f6978693864a4b8baa45c117112ec279465a1238e1cac5e31f98fd275b91340
|
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:b20dacc2d1ffe71a94325f753506d607adcd45dfdc17110510d9d2aac2ab363b
|
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:df73be84f0c00f13e358d00950761edb4aec7bfdee9e97f169f67cba14d6b4b5
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,51 +1,35 @@
|
|
1 |
{
|
2 |
-
"best_metric":
|
3 |
-
"best_model_checkpoint": "../KevinKibe/whisper-small-finetuned-finetuned/checkpoint-
|
4 |
-
"epoch":
|
5 |
-
"eval_steps":
|
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":
|
13 |
-
"grad_norm":
|
14 |
-
"learning_rate":
|
15 |
-
"loss": 3.
|
16 |
-
"step":
|
17 |
},
|
18 |
{
|
19 |
-
"epoch":
|
20 |
-
"eval_loss":
|
21 |
-
"eval_runtime":
|
22 |
-
"eval_samples_per_second": 0.
|
23 |
-
"eval_steps_per_second": 0.
|
24 |
-
"eval_wer":
|
25 |
-
"step":
|
26 |
-
},
|
27 |
-
{
|
28 |
-
"epoch": 19.05,
|
29 |
-
"grad_norm": 1.8751825094223022,
|
30 |
-
"learning_rate": 5e-06,
|
31 |
-
"loss": 2.7253,
|
32 |
-
"step": 20
|
33 |
-
},
|
34 |
-
{
|
35 |
-
"epoch": 19.05,
|
36 |
-
"eval_loss": 4.21867561340332,
|
37 |
-
"eval_runtime": 37.2641,
|
38 |
-
"eval_samples_per_second": 0.268,
|
39 |
-
"eval_steps_per_second": 0.027,
|
40 |
-
"eval_wer": 277.01149425287355,
|
41 |
-
"step": 20
|
42 |
}
|
43 |
],
|
44 |
-
"logging_steps":
|
45 |
-
"max_steps":
|
46 |
"num_input_tokens_seen": 0,
|
47 |
"num_train_epochs": 9223372036854775807,
|
48 |
-
"save_steps":
|
49 |
"stateful_callbacks": {
|
50 |
"TrainerControl": {
|
51 |
"args": {
|
@@ -53,13 +37,13 @@
|
|
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":
|
63 |
"trial_name": null,
|
64 |
"trial_params": null
|
65 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 101.37741046831957,
|
3 |
+
"best_model_checkpoint": "../KevinKibe/whisper-small-finetuned-finetuned/checkpoint-100",
|
4 |
+
"epoch": 6.008,
|
5 |
+
"eval_steps": 100,
|
6 |
+
"global_step": 100,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
+
"epoch": 6.008,
|
13 |
+
"grad_norm": 1.6481244564056396,
|
14 |
+
"learning_rate": 0.0001,
|
15 |
+
"loss": 3.3817,
|
16 |
+
"step": 100
|
17 |
},
|
18 |
{
|
19 |
+
"epoch": 6.008,
|
20 |
+
"eval_loss": 3.438847780227661,
|
21 |
+
"eval_runtime": 370.6019,
|
22 |
+
"eval_samples_per_second": 0.27,
|
23 |
+
"eval_steps_per_second": 0.011,
|
24 |
+
"eval_wer": 101.37741046831957,
|
25 |
+
"step": 100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
26 |
}
|
27 |
],
|
28 |
+
"logging_steps": 100,
|
29 |
+
"max_steps": 500,
|
30 |
"num_input_tokens_seen": 0,
|
31 |
"num_train_epochs": 9223372036854775807,
|
32 |
+
"save_steps": 100,
|
33 |
"stateful_callbacks": {
|
34 |
"TrainerControl": {
|
35 |
"args": {
|
|
|
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": 9.1863566843904e+17,
|
46 |
+
"train_batch_size": 32,
|
47 |
"trial_name": null,
|
48 |
"trial_params": null
|
49 |
}
|
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 sha256:5d1d91f42f6df8e0b260ae742d516a51f97376b47ff68d5641128af6dccda434
|
3 |
size 5368
|