Training in progress, step 20, checkpoint

last-checkpoint/adapter_config.json

@@ -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:dc753107f460eebedcab37a978dc8f4e376ea7b0a7a6245079a1bec869b47db3
+oid sha256:b41aefecebf602e8b3eb83165cb11ae91e063ef795fcd5382f52b0a4834c8eaf
 size 14176064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63f1cc00fb95d4564acd83c7d51ff7e80f513b3607c768e407fdf3c02d599d6a
+oid sha256:cfec19d66473e683c8c6c8c02124aed3a2badb2fd840f8f887295bbe6b53fb09
 size 4832762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97651e5195311fa83aac8286b9c0a9068e32980aed21ebb08fafd1001eee44d6
+oid sha256:ac57d8346a3be754b4ec98f02712a7da2e74f2ce81326866ad29a9acb7908177
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df73be84f0c00f13e358d00950761edb4aec7bfdee9e97f169f67cba14d6b4b5
+oid sha256:94db20b168116ecb35fae58feadaa8ad67980f0f0db9d75b42e7896ad19770de
 size 1064

last-checkpoint/trainer_state.json

@@ -1,92 +1,28 @@
 {
-  "best_metric": 63.72093023255814,
-  "best_model_checkpoint": "../openai/whisper-small-finetuned/checkpoint-40",
-  "epoch": 99.01,
+  "best_metric": 66.51162790697674,
+  "best_model_checkpoint": "../openai/whisper-small-finetuned/checkpoint-20",
+  "epoch": 19.01,
   "eval_steps": 20,
-  "global_step": 100,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 19.01,
-      "grad_norm": 1.7477251291275024,
+      "grad_norm": 1.7188540697097778,
       "learning_rate": 0.0001,
-      "loss": 4.6928,
+      "loss": 4.6963,
       "step": 20
     },
     {
       "epoch": 19.01,
-      "eval_loss": 3.541473388671875,
-      "eval_runtime": 16.3765,
-      "eval_samples_per_second": 1.221,
-      "eval_steps_per_second": 0.061,
-      "eval_wer": 66.04651162790698,
-      "step": 20
-    },
-    {
-      "epoch": 39.01,
-      "grad_norm": 1.1091852188110352,
-      "learning_rate": 0.0001,
-      "loss": 2.4177,
-      "step": 40
-    },
-    {
-      "epoch": 39.01,
-      "eval_loss": 2.713858127593994,
-      "eval_runtime": 15.3439,
-      "eval_samples_per_second": 1.303,
+      "eval_loss": 3.55057692527771,
+      "eval_runtime": 15.3063,
+      "eval_samples_per_second": 1.307,
       "eval_steps_per_second": 0.065,
-      "eval_wer": 63.72093023255814,
-      "step": 40
-    },
-    {
-      "epoch": 59.01,
-      "grad_norm": 0.5135031342506409,
-      "learning_rate": 0.0001,
-      "loss": 1.1967,
-      "step": 60
-    },
-    {
-      "epoch": 59.01,
-      "eval_loss": 2.546757459640503,
-      "eval_runtime": 16.0308,
-      "eval_samples_per_second": 1.248,
-      "eval_steps_per_second": 0.062,
-      "eval_wer": 66.97674418604652,
-      "step": 60
-    },
-    {
-      "epoch": 79.01,
-      "grad_norm": 0.16271141171455383,
-      "learning_rate": 0.0001,
-      "loss": 0.7102,
-      "step": 80
-    },
-    {
-      "epoch": 79.01,
-      "eval_loss": 2.530426502227783,
-      "eval_runtime": 45.1139,
-      "eval_samples_per_second": 0.443,
-      "eval_steps_per_second": 0.022,
-      "eval_wer": 110.23255813953487,
-      "step": 80
-    },
-    {
-      "epoch": 99.01,
-      "grad_norm": 0.1356694996356964,
-      "learning_rate": 0.0001,
-      "loss": 0.609,
-      "step": 100
-    },
-    {
-      "epoch": 99.01,
-      "eval_loss": 2.4960544109344482,
-      "eval_runtime": 45.3429,
-      "eval_samples_per_second": 0.441,
-      "eval_steps_per_second": 0.022,
-      "eval_wer": 164.65116279069767,
-      "step": 100
+      "eval_wer": 66.51162790697674,
+      "step": 20
     }
   ],
   "logging_steps": 20,
@@ -101,12 +37,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 5.8736295936e+17,
+  "total_flos": 1.17472591872e+17,
   "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 sha256:4e9c0f990cd62c4a314194f8df86f013fa125a968b85201927e1c9b01694c489
+oid sha256:8f857dc0a6b1c734e5acd997e0dfa2bd93ce1b14c193a41b1ec395d28b179cc2
 size 5368