Training in progress, step 500, checkpoint

last-checkpoint/README.md

@@ -1,5 +1,5 @@
 ---
-base_model: KevinKibe/whisper-medium-finetuned
+base_model: openai/whisper-medium
 library_name: peft
 ---
 

last-checkpoint/adapter_config.json

@@ -4,7 +4,7 @@
     "base_model_class": "WhisperForConditionalGeneration",
     "parent_library": "transformers.models.whisper.modeling_whisper"
   },
-  "base_model_name_or_path": "KevinKibe/whisper-medium-finetuned",
+  "base_model_name_or_path": "openai/whisper-medium",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -23,8 +23,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "q_proj"
+    "q_proj",
+    "v_proj"
   ],
   "task_type": null,
   "use_dora": false,

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dad58bb931d9189bca63983c26d895b242c8ed4b633805e855e35ae2505f1a1b
+oid sha256:91bfd41a240d5f46e27df0fa8eaa4cba9b7ea12286c752f0cde6a821798de512
 size 37789960

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:638b41e99e1609cbcbab8219d0535a4ebcbc92a4099f06b7a52ef07f8639253d
-size 12832890
+oid sha256:0c4726a0216e59e43ea0e92156c263db32490a1766082e0377e6be629da197ae
+size 12833082

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98263ac62587796252c94311cc839dccae0b0ac4d75cd2ea9c2be57da9a15122
+oid sha256:b755517c5034c242c5d4f4c35049633483be35422a424d0ef852154ccb995195
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1986de5c7599722c0bc658aca1f6e53d646d865cffaac945a2d942205bc9fb1a
+oid sha256:301b42e14f9709962c5351dead598e91b2add26553420de0920fa3b6e19b882a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,85 +1,49 @@
 {
-  "best_metric": 77.23864137626819,
-  "best_model_checkpoint": "../KevinKibe/whisper-medium-finetuned-finetuned/checkpoint-100",
-  "epoch": 1.37,
-  "eval_steps": 25,
-  "global_step": 100,
+  "best_metric": 103.4838076545633,
+  "best_model_checkpoint": "../KevinKibe/whisper-medium-finetuned-finetuned/checkpoint-500",
+  "epoch": 0.25,
+  "eval_steps": 500,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.25,
-      "grad_norm": 1.408146858215332,
-      "learning_rate": 7.7e-05,
-      "loss": 3.9076,
-      "step": 25
+      "grad_norm": 1.5150429010391235,
+      "learning_rate": 0.0007601010101010101,
+      "loss": 5.7804,
+      "step": 500
     },
     {
       "epoch": 0.25,
-      "eval_loss": 3.914597749710083,
-      "eval_runtime": 411.8208,
-      "eval_samples_per_second": 0.607,
-      "eval_steps_per_second": 0.039,
-      "eval_wer": 106.30789589766212,
-      "step": 25
-    },
-    {
-      "epoch": 0.5,
-      "grad_norm": 2.0066428184509277,
-      "learning_rate": 5.2000000000000004e-05,
-      "loss": 2.8203,
-      "step": 50
-    },
-    {
-      "epoch": 0.5,
-      "eval_loss": 3.4905786514282227,
-      "eval_runtime": 441.2692,
-      "eval_samples_per_second": 0.567,
-      "eval_steps_per_second": 0.036,
-      "eval_wer": 84.11998235553595,
-      "step": 50
-    },
-    {
-      "epoch": 1.12,
-      "grad_norm": 2.804873466491699,
-      "learning_rate": 2.7000000000000002e-05,
-      "loss": 2.5457,
-      "step": 75
-    },
-    {
-      "epoch": 1.12,
-      "eval_loss": 3.293093204498291,
-      "eval_runtime": 380.5263,
-      "eval_samples_per_second": 0.657,
-      "eval_steps_per_second": 0.042,
-      "eval_wer": 77.63564181737979,
-      "step": 75
-    },
-    {
-      "epoch": 1.37,
-      "grad_norm": 1.4536932706832886,
-      "learning_rate": 2.0000000000000003e-06,
-      "loss": 2.7631,
-      "step": 100
-    },
-    {
-      "epoch": 1.37,
-      "eval_loss": 3.177401065826416,
-      "eval_runtime": 382.2171,
-      "eval_samples_per_second": 0.654,
-      "eval_steps_per_second": 0.042,
-      "eval_wer": 77.23864137626819,
-      "step": 100
+      "eval_loss": 5.4739532470703125,
+      "eval_runtime": 542.8842,
+      "eval_samples_per_second": 0.461,
+      "eval_steps_per_second": 0.059,
+      "eval_wer": 103.4838076545633,
+      "step": 500
     }
   ],
-  "logging_steps": 25,
-  "max_steps": 100,
+  "logging_steps": 500,
+  "max_steps": 2000,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 9223372036854775807,
-  "save_steps": 25,
-  "total_flos": 1.64643756834816e+18,
-  "train_batch_size": 16,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.654711123968e+19,
+  "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null
 }

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70f645ad7125d347ac1e93f576f3d767a1196ab723edf8df4c89a0728bf7d029
-size 5176
+oid sha256:f2da8df2c4627709c71886adfa00d7303e0de97e4f21a222bec7b34d9a9d527d
+size 5368