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 sha256:7d88d32075310057b782ee49feb21ea7135a3773bbafa6698fb3a52694c71da4
+oid sha256:2fcc8161bffaa776c36d0bf716f4d9f51343742505a8ec6e761925c605d343e9
 size 14176064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f4af295acab05c9b709544b2d95aebf7cbe98d7c71d1ef6587176e2441646f6
-size 4832890
+oid sha256:2faaedeca429e56c53308b4544dd0629e2b969cef4e149360e7d203cbebd9bf7
+size 4832762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03cd9de6ee2a65932ad2fb6094dfd18e75c7e402f88bba702657f50ca5a09f4c
+oid sha256:8fd34c05f32915cfddb244845f306181a1764de738fcce7d4ddb675210c64c1c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30ee3ca470c4d31872c3879402fa37a65e88eac48e4a7fb0671df0eafcffb412
+oid sha256:c4dcd0406e202df2a3c65a5d416d9b75e9f9f16a0af78526a7608fc8a266c503
 size 1064

last-checkpoint/trainer_state.json

@@ -1,99 +1,35 @@
 {
-  "best_metric": 78.03590285110876,
-  "best_model_checkpoint": "../openai/whisper-small-finetuned/checkpoint-500",
-  "epoch": 31.008,
-  "eval_steps": 100,
-  "global_step": 500,
+  "best_metric": 86.20689655172413,
+  "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": 6.008,
-      "grad_norm": 1.1062548160552979,
+      "epoch": 9.05,
+      "grad_norm": 3.4064078330993652,
       "learning_rate": 0.0001,
-      "loss": 2.2203,
-      "step": 100
+      "loss": 3.95,
+      "step": 10
     },
     {
-      "epoch": 6.008,
-      "eval_loss": 2.724890947341919,
-      "eval_runtime": 331.0923,
-      "eval_samples_per_second": 0.302,
-      "eval_steps_per_second": 0.012,
-      "eval_wer": 96.09292502639916,
-      "step": 100
-    },
-    {
-      "epoch": 12.016,
-      "grad_norm": 3.7120275497436523,
-      "learning_rate": 0.0001,
-      "loss": 1.4989,
-      "step": 200
-    },
-    {
-      "epoch": 12.016,
-      "eval_loss": 2.2445077896118164,
-      "eval_runtime": 331.3447,
-      "eval_samples_per_second": 0.302,
-      "eval_steps_per_second": 0.012,
-      "eval_wer": 92.08025343189018,
-      "step": 200
-    },
-    {
-      "epoch": 18.024,
-      "grad_norm": 2.7632181644439697,
-      "learning_rate": 0.0001,
-      "loss": 0.9049,
-      "step": 300
-    },
-    {
-      "epoch": 18.024,
-      "eval_loss": 2.2876439094543457,
-      "eval_runtime": 338.7944,
-      "eval_samples_per_second": 0.295,
-      "eval_steps_per_second": 0.012,
-      "eval_wer": 84.58289334741288,
-      "step": 300
-    },
-    {
-      "epoch": 24.032,
-      "grad_norm": 3.781102180480957,
-      "learning_rate": 0.0001,
-      "loss": 0.6953,
-      "step": 400
-    },
-    {
-      "epoch": 24.032,
-      "eval_loss": 2.42946720123291,
-      "eval_runtime": 336.5888,
-      "eval_samples_per_second": 0.297,
-      "eval_steps_per_second": 0.012,
-      "eval_wer": 87.11721224920802,
-      "step": 400
-    },
-    {
-      "epoch": 31.008,
-      "grad_norm": 1.3651665449142456,
-      "learning_rate": 0.0001,
-      "loss": 0.5138,
-      "step": 500
-    },
-    {
-      "epoch": 31.008,
-      "eval_loss": 2.5180132389068604,
-      "eval_runtime": 333.0055,
-      "eval_samples_per_second": 0.3,
-      "eval_steps_per_second": 0.012,
-      "eval_wer": 78.03590285110876,
-      "step": 500
+      "epoch": 9.05,
+      "eval_loss": 4.568088531494141,
+      "eval_runtime": 19.5829,
+      "eval_samples_per_second": 0.511,
+      "eval_steps_per_second": 0.051,
+      "eval_wer": 86.20689655172413,
+      "step": 10
     }
   ],
-  "logging_steps": 100,
-  "max_steps": 500,
+  "logging_steps": 10,
+  "max_steps": 20,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 9223372036854775807,
-  "save_steps": 100,
+  "save_steps": 10,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {
@@ -101,12 +37,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 4.58965416443904e+18,
+  "total_flos": 5.8736295936e+16,
   "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 sha256:0d78f1c80a7f597bc652f6906f996f83ceebff67856d88e00606bfa4ac987241
+oid sha256:0a8867a5cd2e51decccd6a3078781ed396b55c1f60f54d4610df595db10f9abe
 size 5368