Training in progress, step 25, 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.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2377150
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4f6df6d40dfb035fcec155c3cfa4fabc79c7f5264f6601ffac386e91b24fc0d5
|
| 3 |
size 2377150
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 826490
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7e9c3128a5e93efdd5020fb25b025cf9d809e5044e8b33447649b63faa704025
|
| 3 |
size 826490
|
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 sha256:0a4470d1ea49e81453eb7f521785faae83ec370b2823751ff20204b46aff8639
|
| 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:c0f38a2c63d0ec9849191dc1faf9440cf5827dcc6785c8b62720c0320435ae75
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,44 +1,28 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric":
|
| 3 |
"best_model_checkpoint": "../openai/whisper-tiny-finetuned/checkpoint-25",
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 25,
|
| 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": 24.02,
|
| 13 |
-
"grad_norm": 1.
|
| 14 |
"learning_rate": 0.0005,
|
| 15 |
-
"loss": 2.
|
| 16 |
"step": 25
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 24.02,
|
| 20 |
-
"eval_loss": 1.
|
| 21 |
-
"eval_runtime":
|
| 22 |
-
"eval_samples_per_second": 0.
|
| 23 |
-
"eval_steps_per_second": 0.
|
| 24 |
-
"eval_wer":
|
| 25 |
"step": 25
|
| 26 |
-
},
|
| 27 |
-
{
|
| 28 |
-
"epoch": 49.02,
|
| 29 |
-
"grad_norm": 1.2143254280090332,
|
| 30 |
-
"learning_rate": 0.0,
|
| 31 |
-
"loss": 0.9332,
|
| 32 |
-
"step": 50
|
| 33 |
-
},
|
| 34 |
-
{
|
| 35 |
-
"epoch": 49.02,
|
| 36 |
-
"eval_loss": 2.270937442779541,
|
| 37 |
-
"eval_runtime": 9.0793,
|
| 38 |
-
"eval_samples_per_second": 0.441,
|
| 39 |
-
"eval_steps_per_second": 0.11,
|
| 40 |
-
"eval_wer": 240.9090909090909,
|
| 41 |
-
"step": 50
|
| 42 |
}
|
| 43 |
],
|
| 44 |
"logging_steps": 25,
|
|
@@ -46,7 +30,7 @@
|
|
| 46 |
"num_input_tokens_seen": 0,
|
| 47 |
"num_train_epochs": 9223372036854775807,
|
| 48 |
"save_steps": 25,
|
| 49 |
-
"total_flos":
|
| 50 |
"train_batch_size": 32,
|
| 51 |
"trial_name": null,
|
| 52 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 218.18181818181816,
|
| 3 |
"best_model_checkpoint": "../openai/whisper-tiny-finetuned/checkpoint-25",
|
| 4 |
+
"epoch": 24.02,
|
| 5 |
"eval_steps": 25,
|
| 6 |
+
"global_step": 25,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 24.02,
|
| 13 |
+
"grad_norm": 1.7979644536972046,
|
| 14 |
"learning_rate": 0.0005,
|
| 15 |
+
"loss": 2.0191,
|
| 16 |
"step": 25
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 24.02,
|
| 20 |
+
"eval_loss": 1.9223368167877197,
|
| 21 |
+
"eval_runtime": 9.3314,
|
| 22 |
+
"eval_samples_per_second": 0.429,
|
| 23 |
+
"eval_steps_per_second": 0.107,
|
| 24 |
+
"eval_wer": 218.18181818181816,
|
| 25 |
"step": 25
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 26 |
}
|
| 27 |
],
|
| 28 |
"logging_steps": 25,
|
|
|
|
| 30 |
"num_input_tokens_seen": 0,
|
| 31 |
"num_train_epochs": 9223372036854775807,
|
| 32 |
"save_steps": 25,
|
| 33 |
+
"total_flos": 8913881088000000.0,
|
| 34 |
"train_batch_size": 32,
|
| 35 |
"trial_name": null,
|
| 36 |
"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 5176
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0f6f24ab4f1a5d91a536e57d72068e9f99b82360fabe2279efad78a73cedda13
|
| 3 |
size 5176
|