Training in progress, step 10, 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:f604dc87057072c6ea75e2256a7f52b189a3910b55463bc71f46b0594487ac55
+oid sha256:f7b748f132f1b007b4b46c29b79576b9032a654e0c44680137c558710f38b8ea
 size 14176064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e864ba831a16c7c9cb6a577948f8294a6b9956b437893e1b91868d8acdd201fb
+oid sha256:7da4a13f61129710c3e65e3794c64c276377cf47bba8ecc7b5ff65663120f31f
 size 4832762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfb3811b63313489c6bb7fbbd93a86fcbb2760116919b75cb163af7587926db5
+oid sha256:8fd34c05f32915cfddb244845f306181a1764de738fcce7d4ddb675210c64c1c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df73be84f0c00f13e358d00950761edb4aec7bfdee9e97f169f67cba14d6b4b5
+oid sha256:c4dcd0406e202df2a3c65a5d416d9b75e9f9f16a0af78526a7608fc8a266c503
 size 1064

last-checkpoint/trainer_state.json

@@ -1,83 +1,35 @@
 {
-  "best_metric": 81.60919540229885,
-  "best_model_checkpoint": "../openai/whisper-small-finetuned/checkpoint-100",
-  "epoch": 99.01,
-  "eval_steps": 25,
-  "global_step": 100,
+  "best_metric": 85.0574712643678,
+  "best_model_checkpoint": "../openai/whisper-small-finetuned/checkpoint-10",
+  "epoch": 9.05,
+  "eval_steps": 10,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 24.01,
-      "grad_norm": 0.658126711845398,
+      "epoch": 9.05,
+      "grad_norm": 3.5340542793273926,
       "learning_rate": 0.0001,
-      "loss": 1.5717,
-      "step": 25
+      "loss": 3.955,
+      "step": 10
     },
     {
-      "epoch": 24.01,
-      "eval_loss": 3.452148675918579,
-      "eval_runtime": 18.355,
-      "eval_samples_per_second": 0.545,
-      "eval_steps_per_second": 0.054,
-      "eval_wer": 89.65517241379311,
-      "step": 25
-    },
-    {
-      "epoch": 49.01,
-      "grad_norm": 0.2500029504299164,
-      "learning_rate": 0.0001,
-      "loss": 0.8875,
-      "step": 50
-    },
-    {
-      "epoch": 49.01,
-      "eval_loss": 3.3323276042938232,
-      "eval_runtime": 18.862,
-      "eval_samples_per_second": 0.53,
-      "eval_steps_per_second": 0.053,
-      "eval_wer": 83.9080459770115,
-      "step": 50
-    },
-    {
-      "epoch": 74.01,
-      "grad_norm": 25.93928337097168,
-      "learning_rate": 0.0001,
-      "loss": 0.6714,
-      "step": 75
-    },
-    {
-      "epoch": 74.01,
-      "eval_loss": 3.3124895095825195,
-      "eval_runtime": 19.825,
-      "eval_samples_per_second": 0.504,
-      "eval_steps_per_second": 0.05,
-      "eval_wer": 82.75862068965517,
-      "step": 75
-    },
-    {
-      "epoch": 99.01,
-      "grad_norm": 0.16914552450180054,
-      "learning_rate": 0.0001,
-      "loss": 0.5819,
-      "step": 100
-    },
-    {
-      "epoch": 99.01,
-      "eval_loss": 3.2785234451293945,
-      "eval_runtime": 20.2621,
-      "eval_samples_per_second": 0.494,
-      "eval_steps_per_second": 0.049,
-      "eval_wer": 81.60919540229885,
-      "step": 100
+      "epoch": 9.05,
+      "eval_loss": 4.58884334564209,
+      "eval_runtime": 20.8147,
+      "eval_samples_per_second": 0.48,
+      "eval_steps_per_second": 0.048,
+      "eval_wer": 85.0574712643678,
+      "step": 10
     }
   ],
-  "logging_steps": 25,
-  "max_steps": 100,
+  "logging_steps": 10,
+  "max_steps": 20,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 9223372036854775807,
-  "save_steps": 25,
+  "save_steps": 10,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {
@@ -85,12 +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": 5.8736295936e+16,
   "train_batch_size": 64,
   "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:d09de538d839ccb79e7d7b0f42cfd620c304edae9ecd58357e0e446b3b151f24
+oid sha256:85cb21ac25d27f454ad5e322f2dfdf92f2e016f1413497c1f02b2aa3d8ef540a
 size 5368