Training in progress, step 1500

README.md

@@ -8,19 +8,19 @@ tags:
 datasets:
 - mozilla-foundation/common_voice_16_1
 model-index:
-- name: Wisper-Small-zh_test
+- name: Wisper-Small-zh
   results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# Wisper-Small-zh_test
+# Wisper-Small-zh
 
 This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 16.1 dataset.
 It achieves the following results on the evaluation set:
-- Cer: 33.3994
 - Loss: 0.6020
+- Cer: 33.3994
 
 ## Model description
 
@@ -51,10 +51,10 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch  | Step | Cer      | Validation Loss |
-|:-------------:|:------:|:----:|:--------:|:---------------:|
-| 2.9388        | 0.6623 | 500  | 102.7090 | 2.9818          |
-| 0.5492        | 1.3245 | 1000 | 33.3994  | 0.6020          |
+| Training Loss | Epoch  | Step | Validation Loss | Cer      |
+|:-------------:|:------:|:----:|:---------------:|:--------:|
+| 2.9388        | 0.6623 | 500  | 2.9818          | 102.7090 |
+| 0.5492        | 1.3245 | 1000 | 0.6020          | 33.3994  |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:524602c80ff594d2d365501dce64a850c7efd7f01df64cca55fb5cb68a859cef
+oid sha256:82a6569cd11941057fd9f437f3535b31efc53e18041474cb96e6bbd0d13fae99
 size 974076256

runs/Aug03_02-05-33_da41efab0859/events.out.tfevents.1722651014.da41efab0859.34.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f33e67f47d3554277bc36968b7269eae45489919338e8c726200b12ba3e761a0
+size 11189

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 33.39944765252322,
   "best_model_checkpoint": "/kaggle/working/whisper-small/checkpoint-1000",
-  "epoch": 1.3258278145695364,
+  "epoch": 1.3245033112582782,
   "eval_steps": 500,
-  "global_step": 1001,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -307,13 +307,13 @@
       "step": 1000
     },
     {
-      "epoch": 1.3258278145695364,
-      "step": 1001,
-      "total_flos": 4.66193748381696e+18,
-      "train_loss": 0.0006697479780618246,
-      "train_runtime": 25.0038,
-      "train_samples_per_second": 639.904,
-      "train_steps_per_second": 39.994
+      "epoch": 1.3245033112582782,
+      "step": 1000,
+      "total_flos": 4.65727933108224e+18,
+      "train_loss": 2.47559251499176,
+      "train_runtime": 12073.0146,
+      "train_samples_per_second": 1.325,
+      "train_steps_per_second": 0.083
     }
   ],
   "logging_steps": 25,
@@ -333,7 +333,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.66193748381696e+18,
+  "total_flos": 4.65727933108224e+18,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb88f0fe789f473701fc1eb849990b085024dce0c930792f1b319c440ea3de12
+oid sha256:c46a861890cc51ea597643aa908aa6e687e67b5af88356020c5b6df5d3791db5
 size 5304