Training in progress, step 1000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d76ac46219d8d6464b4275617d85ce9aea730b11a6e0e9fca3eebd3de90fda63
+oid sha256:3edcd0c450189261c882afd547ab8aa2ed8d8d69f6514bdd036f696631191522
 size 62969640

last-checkpoint/adapter_model/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d76ac46219d8d6464b4275617d85ce9aea730b11a6e0e9fca3eebd3de90fda63
+oid sha256:3edcd0c450189261c882afd547ab8aa2ed8d8d69f6514bdd036f696631191522
 size 62969640

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cb556ea2c9b9b10fca0d9e95927bd0f59def6539e0e5b6fe039e3407785d505
+oid sha256:8c5dcfe80745e49d3dda94c607cdd0c6937698a1eee8f03ccc8d98c943d8860e
 size 84101370

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b27a72f606fe83c400f5cf18fccfbeb6b3aeb5bd692f12d1975d2e9fa01952a
+oid sha256:658a00b68b67cee9ed9e480f0e8e586986ce85df79a4a11fa9577da999c85123
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18b984273ea2d45b7ffb1d047bb359d93111e41fcad70d16a1b453fd38f72636
+oid sha256:9d8fdcd0311eba9854fff738038ed4c1a269832665b4d88ba4e4e3d02a1a7e0e
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c6c3e39e65b038f3305b10302a421e7d2279cc0b6df6c74ce7b9308a8a5cda9
+oid sha256:97a379574c9663f8f6b1e4e8f5372c7153e8ea3e03443c673cf8a63a64a20ef3
 size 1064

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 500,
-  "best_metric": 0.8364643454551697,
-  "best_model_checkpoint": "./whisper-large-v3-lt1/checkpoint-500",
-  "epoch": 0.25,
+  "best_global_step": 1000,
+  "best_metric": 0.6822749972343445,
+  "best_model_checkpoint": "./whisper-large-v3-lt1/checkpoint-1000",
+  "epoch": 0.5,
   "eval_steps": 500,
-  "global_step": 500,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -51,6 +51,49 @@
       "eval_samples_per_second": 2.503,
       "eval_steps_per_second": 0.313,
       "step": 500
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 1.2657830715179443,
+      "learning_rate": 7.373684210526316e-06,
+      "loss": 0.796,
+      "step": 600
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 1.17739737033844,
+      "learning_rate": 6.8473684210526325e-06,
+      "loss": 0.8109,
+      "step": 700
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.271132230758667,
+      "learning_rate": 6.321052631578948e-06,
+      "loss": 0.7474,
+      "step": 800
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 1.3513257503509521,
+      "learning_rate": 5.794736842105264e-06,
+      "loss": 0.7134,
+      "step": 900
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.3304741382598877,
+      "learning_rate": 5.268421052631579e-06,
+      "loss": 0.6847,
+      "step": 1000
+    },
+    {
+      "epoch": 0.5,
+      "eval_loss": 0.6822749972343445,
+      "eval_runtime": 1166.2313,
+      "eval_samples_per_second": 2.504,
+      "eval_steps_per_second": 0.313,
+      "step": 1000
     }
   ],
   "logging_steps": 100,
@@ -70,7 +113,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.746989674496e+19,
+  "total_flos": 5.493979348992e+19,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null