Training in progress, step 25, checkpoint

last-checkpoint/adapter_config.json

@@ -22,8 +22,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "v_proj"
+    "v_proj",
+    "q_proj"
   ],
   "task_type": null,
   "use_dora": false,

last-checkpoint/adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e099098b47f29ededc98d12765b6f56996be704fdb5ae0e1eb30b2097f5133a4
+oid sha256:245f29a897e7c49c00428e860ce4e07d6228260072c910e4328405c8fa1e8df0
 size 14208970

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f7f7bcd2757b29baab587e244e22bd4b461ca74b53ef01aa8743b5a78b17382
+oid sha256:4255fb1905805371ee91d8a954ed9083758d20edd10e4c67fdd6131106c7e34e
 size 4832762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6166d3c12a44bbcfc5050edc1e21540e217631ef414f110d2073dbd4209454c
+oid sha256:be79dc9899c1eff57e53e0613a56d8f2678a4be11294551db60a4f06e44637e3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7d135c69dc5cba3a48b39a10c49b5799e503e4202b7575790c01f57aca74aae
+oid sha256:c80ec05408312bf923dbbdaa282a4b00796cef23355bfe82c237478067ddd661
 size 1064

last-checkpoint/trainer_state.json

@@ -1,76 +1,28 @@
 {
-  "best_metric": 118.39080459770115,
-  "best_model_checkpoint": "../openai/whisper-small-finetuned/checkpoint-75",
-  "epoch": 49.02,
+  "best_metric": 125.62500000000001,
+  "best_model_checkpoint": "../openai/whisper-small-finetuned/checkpoint-25",
+  "epoch": 8.01,
   "eval_steps": 25,
-  "global_step": 100,
+  "global_step": 25,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 12.01,
-      "grad_norm": 11.94140911102295,
-      "learning_rate": 7.600000000000001e-06,
-      "loss": 3.9758,
+      "epoch": 8.01,
+      "grad_norm": 12.496959686279297,
+      "learning_rate": 7.7e-06,
+      "loss": 4.7293,
       "step": 25
     },
     {
-      "epoch": 12.01,
-      "eval_loss": 5.314132213592529,
-      "eval_runtime": 11.7411,
-      "eval_samples_per_second": 0.852,
-      "eval_steps_per_second": 0.085,
-      "eval_wer": 128.73563218390805,
+      "epoch": 8.01,
+      "eval_loss": 5.816229820251465,
+      "eval_runtime": 28.1944,
+      "eval_samples_per_second": 0.709,
+      "eval_steps_per_second": 0.035,
+      "eval_wer": 125.62500000000001,
       "step": 25
-    },
-    {
-      "epoch": 24.02,
-      "grad_norm": 3.9279041290283203,
-      "learning_rate": 5.1e-06,
-      "loss": 3.4485,
-      "step": 50
-    },
-    {
-      "epoch": 24.02,
-      "eval_loss": 4.9484028816223145,
-      "eval_runtime": 12.969,
-      "eval_samples_per_second": 0.771,
-      "eval_steps_per_second": 0.077,
-      "eval_wer": 134.48275862068965,
-      "step": 50
-    },
-    {
-      "epoch": 37.01,
-      "grad_norm": 3.5452747344970703,
-      "learning_rate": 2.6e-06,
-      "loss": 3.1895,
-      "step": 75
-    },
-    {
-      "epoch": 37.01,
-      "eval_loss": 4.7514119148254395,
-      "eval_runtime": 11.8715,
-      "eval_samples_per_second": 0.842,
-      "eval_steps_per_second": 0.084,
-      "eval_wer": 118.39080459770115,
-      "step": 75
-    },
-    {
-      "epoch": 49.02,
-      "grad_norm": 2.8297388553619385,
-      "learning_rate": 1.0000000000000001e-07,
-      "loss": 3.0765,
-      "step": 100
-    },
-    {
-      "epoch": 49.02,
-      "eval_loss": 4.6838202476501465,
-      "eval_runtime": 12.0411,
-      "eval_samples_per_second": 0.83,
-      "eval_steps_per_second": 0.083,
-      "eval_wer": 118.39080459770115,
-      "step": 100
     }
   ],
   "logging_steps": 25,
@@ -78,7 +30,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 9223372036854775807,
   "save_steps": 25,
-  "total_flos": 1.4684073984e+18,
+  "total_flos": 4.9808378953728e+17,
   "train_batch_size": 96,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3035a8bb40e92657c16115ccaf32e1f1aa6c07f6a6ee3edb6ffb5b6f88ce7156
+oid sha256:1cf734b6963f8f73a8ed78acf74b0e5afa35b59bed85b09f6588300413559cfc
 size 5176