Training in progress, step 10, checkpoint

last-checkpoint/adapter_config.json

@@ -23,8 +23,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "v_proj"
+    "v_proj",
+    "q_proj"
   ],
   "task_type": null,
   "use_dora": false,

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48a2738892776e844e26a0ee6703b1fb99b3618598d0797ad41bb5969dc70b07
+oid sha256:eab84c97625eac5e0880e90af56f69c7ac1c1037c854b22bc5157c6bc30f7fb5
 size 14176064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b5427323a83099922056b799577815d11adbca7043c84179c99c26e81d30a52
+oid sha256:7c58d4f7b9f3ff3ae48c6a6d543cb52233eb7cbd1b55850f8d16d9e523ade094
 size 4832762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b33ed5fc6487acbf6e26dedc64c25e7f851e363e054fc82b98e44babc584391
+oid sha256:a1c7e68895b7eac717d7e4bf5ab2889881ac66b5cbef829d15b86f30725fd17f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7409a3db23ca30d748433633adb25a16b5943f83075d54979b20be428dcaf7c
+oid sha256:1eca0ddb3ec890c90e8e6e7325bec40cdb8b59e4bebf5c0da8473b02809de875
 size 1064

last-checkpoint/trainer_state.json

@@ -1,98 +1,34 @@
 {
-  "best_metric": 142.5,
-  "best_model_checkpoint": "../openai/whisper-small-finetuned/checkpoint-50",
-  "epoch": 12.5,
+  "best_metric": 157.5,
+  "best_model_checkpoint": "../openai/whisper-small-finetuned/checkpoint-10",
+  "epoch": 2.066666666666667,
   "eval_steps": 10,
-  "global_step": 50,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 2.5,
-      "grad_norm": 10.211004257202148,
+      "epoch": 2.066666666666667,
+      "grad_norm": 12.599740982055664,
       "learning_rate": 9e-05,
-      "loss": 5.6632,
+      "loss": 5.9124,
       "step": 10
     },
     {
-      "epoch": 2.5,
-      "eval_loss": 4.246429443359375,
-      "eval_runtime": 6.907,
-      "eval_samples_per_second": 0.869,
-      "eval_steps_per_second": 0.145,
+      "epoch": 2.066666666666667,
+      "eval_loss": 4.316458225250244,
+      "eval_runtime": 6.6642,
+      "eval_samples_per_second": 0.9,
+      "eval_steps_per_second": 0.15,
       "eval_wer": 157.5,
       "step": 10
-    },
-    {
-      "epoch": 5.0,
-      "grad_norm": 2.3187050819396973,
-      "learning_rate": 0.0001,
-      "loss": 4.3134,
-      "step": 20
-    },
-    {
-      "epoch": 5.0,
-      "eval_loss": 3.409444808959961,
-      "eval_runtime": 6.0126,
-      "eval_samples_per_second": 0.998,
-      "eval_steps_per_second": 0.166,
-      "eval_wer": 145.0,
-      "step": 20
-    },
-    {
-      "epoch": 7.5,
-      "grad_norm": 1.6774072647094727,
-      "learning_rate": 0.0001,
-      "loss": 3.5339,
-      "step": 30
-    },
-    {
-      "epoch": 7.5,
-      "eval_loss": 2.968590021133423,
-      "eval_runtime": 6.2596,
-      "eval_samples_per_second": 0.959,
-      "eval_steps_per_second": 0.16,
-      "eval_wer": 145.0,
-      "step": 30
-    },
-    {
-      "epoch": 10.0,
-      "grad_norm": 2.3679263591766357,
-      "learning_rate": 0.0001,
-      "loss": 2.9729,
-      "step": 40
-    },
-    {
-      "epoch": 10.0,
-      "eval_loss": 2.7336347103118896,
-      "eval_runtime": 7.5505,
-      "eval_samples_per_second": 0.795,
-      "eval_steps_per_second": 0.132,
-      "eval_wer": 160.0,
-      "step": 40
-    },
-    {
-      "epoch": 12.5,
-      "grad_norm": 1.7330552339553833,
-      "learning_rate": 0.0001,
-      "loss": 2.6911,
-      "step": 50
-    },
-    {
-      "epoch": 12.5,
-      "eval_loss": 2.5959129333496094,
-      "eval_runtime": 7.3414,
-      "eval_samples_per_second": 0.817,
-      "eval_steps_per_second": 0.136,
-      "eval_wer": 142.5,
-      "step": 50
     }
   ],
   "logging_steps": 10,
-  "max_steps": 50,
+  "max_steps": 30,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 13,
+  "num_train_epochs": 9223372036854775807,
   "save_steps": 10,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -101,12 +37,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.0322758393856e+17,
+  "total_flos": 4.170277011456e+16,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e3463515450077cbaac6ef5248a6cbcde1055cef5783be11b4bd1c11daf2248
+oid sha256:94ef2d56d7f2173783036ac4eb53c992be8cb36de1230bc10392218f27610460
 size 5368