End of training

README.md

@@ -1,21 +1,24 @@
 ---
+language:
+- id
 license: apache-2.0
 base_model: openai/whisper-tiny
 tags:
+- whisper-event
 - generated_from_trainer
 datasets:
-- common_voice_16_0
+- mozilla-foundation/common_voice_16_0
 metrics:
 - wer
 model-index:
-- name: breeze-dsw-tiny-id
+- name: Breeze DSW Indonesian - tiny
   results:
   - task:
       name: Automatic Speech Recognition
       type: automatic-speech-recognition
     dataset:
-      name: common_voice_16_0
-      type: common_voice_16_0
+      name: mozilla-foundation/common_voice_16_0 id
+      type: mozilla-foundation/common_voice_16_0
       config: id
       split: test
       args: id
@@ -28,9 +31,9 @@ model-index:
 <!-- 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. -->
 
-# breeze-dsw-tiny-id
+# Breeze DSW Indonesian - tiny
 
-This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the common_voice_16_0 dataset.
+This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the mozilla-foundation/common_voice_16_0 id dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.7109
 - Wer: 45.2434

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 3.03,
+    "eval_loss": 0.7109375,
+    "eval_runtime": 1120.9908,
+    "eval_samples_per_second": 3.249,
+    "eval_steps_per_second": 0.203,
+    "eval_wer": 45.243352654338025,
+    "train_loss": 0.0,
+    "train_runtime": 66.1004,
+    "train_samples_per_second": 968.225,
+    "train_steps_per_second": 30.257
+}

breeze-dsw-tiny-id.log

@@ -480,3 +480,17 @@ Config: alpha=0.000010, betas=(0.900000, 0.999000), weight_decay=0.000000, adam_
 [2024-01-12 23:22:07,279] [INFO] [engine.py:2988:_get_all_zero_checkpoint_state_dicts] successfully read 1 ZeRO state_dicts for rank 0
 [2024-01-12 23:22:07,313] [INFO] [engine.py:2920:_load_zero_checkpoint] loading 1 zero partition checkpoints for rank 0
 {'train_runtime': 66.1004, 'train_samples_per_second': 968.225, 'train_steps_per_second': 30.257, 'train_loss': 0.0, 'epoch': 3.03}
+***** train metrics *****
+  epoch                    =       3.03
+  train_loss               =        0.0
+  train_runtime            = 0:01:06.10
+  train_samples_per_second =    968.225
+  train_steps_per_second   =     30.257
+01/12/2024 23:22:15 - INFO - __main__ - *** Evaluate ***
+***** eval metrics *****
+  epoch                   =       3.03
+  eval_loss               =     0.7109
+  eval_runtime            = 0:18:40.99
+  eval_samples_per_second =      3.249
+  eval_steps_per_second   =      0.203
+  eval_wer                =    45.2434

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.03,
+    "eval_loss": 0.7109375,
+    "eval_runtime": 1120.9908,
+    "eval_samples_per_second": 3.249,
+    "eval_steps_per_second": 0.203,
+    "eval_wer": 45.243352654338025
+}

runs/Jan12_23-20-08_knight/events.out.tfevents.1705099256.knight.5818.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0909b3b36e5be95af082409d55b57c9ca0f9cb13e34f4ff5ebfc90660ada541c
+size 406

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 3.03,
+    "train_loss": 0.0,
+    "train_runtime": 66.1004,
+    "train_samples_per_second": 968.225,
+    "train_steps_per_second": 30.257
+}

trainer_state.json

@@ -0,0 +1,195 @@
+{
+  "best_metric": 45.243352654338025,
+  "best_model_checkpoint": "/cosmos/home/sp-operator/ai/training/models/huggingface/scripts/../breeze-dsw-tiny-id/checkpoint-500",
+  "epoch": 3.032,
+  "eval_steps": 100,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.898977360288234e-06,
+      "loss": 1.7847,
+      "step": 25
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 6.160712527409633e-06,
+      "loss": 1.3566,
+      "step": 50
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 6.85912902234906e-06,
+      "loss": 1.1407,
+      "step": 75
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 7.344547104469332e-06,
+      "loss": 0.99,
+      "step": 100
+    },
+    {
+      "epoch": 0.1,
+      "eval_loss": 0.8486328125,
+      "eval_runtime": 1294.216,
+      "eval_samples_per_second": 2.814,
+      "eval_steps_per_second": 0.176,
+      "eval_wer": 54.17241696568221,
+      "step": 100
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 7.716963756434345e-06,
+      "loss": 0.765,
+      "step": 125
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 8.019180844200955e-06,
+      "loss": 0.5849,
+      "step": 150
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 8.27351214279797e-06,
+      "loss": 0.7834,
+      "step": 175
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 8.49307723936858e-06,
+      "loss": 0.7896,
+      "step": 200
+    },
+    {
+      "epoch": 1.04,
+      "eval_loss": 0.7578125,
+      "eval_runtime": 1161.7981,
+      "eval_samples_per_second": 3.135,
+      "eval_steps_per_second": 0.196,
+      "eval_wer": 48.339313644309506,
+      "step": 200
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 8.686247975778677e-06,
+      "loss": 0.8413,
+      "step": 225
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 8.858694625217149e-06,
+      "loss": 0.68,
+      "step": 250
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 9.014436199608479e-06,
+      "loss": 0.5851,
+      "step": 275
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 9.156425255148058e-06,
+      "loss": 0.4164,
+      "step": 300
+    },
+    {
+      "epoch": 1.14,
+      "eval_loss": 0.73876953125,
+      "eval_runtime": 1191.6636,
+      "eval_samples_per_second": 3.056,
+      "eval_steps_per_second": 0.191,
+      "eval_wer": 49.25936148679732,
+      "step": 300
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 9.28689473531776e-06,
+      "loss": 0.5102,
+      "step": 325
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 9.407574351377137e-06,
+      "loss": 0.602,
+      "step": 350
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 9.519831289296397e-06,
+      "loss": 0.6399,
+      "step": 375
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 9.624764935335318e-06,
+      "loss": 0.5456,
+      "step": 400
+    },
+    {
+      "epoch": 2.09,
+      "eval_loss": 0.7177734375,
+      "eval_runtime": 1169.8926,
+      "eval_samples_per_second": 3.113,
+      "eval_steps_per_second": 0.195,
+      "eval_wer": 46.126598583126324,
+      "step": 400
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 9.723272550712454e-06,
+      "loss": 0.48,
+      "step": 425
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 9.816095971633122e-06,
+      "loss": 0.3325,
+      "step": 450
+    },
+    {
+      "epoch": 3.01,
+      "learning_rate": 9.90385555539545e-06,
+      "loss": 0.3389,
+      "step": 475
+    },
+    {
+      "epoch": 3.03,
+      "learning_rate": 9.987075336738768e-06,
+      "loss": 0.476,
+      "step": 500
+    },
+    {
+      "epoch": 3.03,
+      "eval_loss": 0.7109375,
+      "eval_runtime": 1126.9534,
+      "eval_samples_per_second": 3.232,
+      "eval_steps_per_second": 0.202,
+      "eval_wer": 45.243352654338025,
+      "step": 500
+    },
+    {
+      "epoch": 3.03,
+      "step": 500,
+      "total_flos": 3.922034448169697e+17,
+      "train_loss": 0.0,
+      "train_runtime": 66.1004,
+      "train_samples_per_second": 968.225,
+      "train_steps_per_second": 30.257
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 2000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9223372036854775807,
+  "save_steps": 100,
+  "total_flos": 3.922034448169697e+17,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}