Training in progress, step 500, checkpoint

last-checkpoint/README.md

@@ -1,6 +1,6 @@
 ---
-base_model: openai/whisper-small
 library_name: peft
+base_model: openai/whisper-small
 ---
 
 # Model Card for Model ID

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 sha256:5bf48bc81f22ed4a3d63abaf440f475fd90680f94f87ba2e5965161c5aac2e45
+oid sha256:8a81e82bda9dcd00b0e1c33cfe6f1fdaf3e89ae5aec7b7e43b6645ca7b2c6dc9
 size 14176064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a927dd4e6fd6ed7a110258e3d8e0cdbe0ebce7f7847a0294bc7c468330b8b979
+oid sha256:dc954ae19af7f7676fdaf86e1bbd134ba266d9a7226e99b400d544d8eeba6358
 size 4832890

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47586dfc0afc6cfec360e3d39632c4aee9a22a56ca08f36766bb611ed8e4e252
+oid sha256:fb8290f7060f840c0e94500ccf61924054dd37481a06525cc06c6a3905e66f47
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:647072c6e45e0dfca80c8b6481afc718d32502c5b24237edb51c87996b591c22
+oid sha256:df6b5589c1af5c61bb3bbb4c1c654a8cc71368279b069213acf87ffc7febc71c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,115 +1,35 @@
 {
-  "best_metric": 92.05103042198233,
-  "best_model_checkpoint": "../openai/whisper-small-finetuned/checkpoint-200",
-  "epoch": 18.024,
-  "eval_steps": 100,
-  "global_step": 600,
+  "best_metric": 94.3081452404318,
+  "best_model_checkpoint": "../openai/whisper-small-finetuned/checkpoint-500",
+  "epoch": 0.25,
+  "eval_steps": 500,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 3.004,
-      "grad_norm": 16.915180206298828,
-      "learning_rate": 9.214285714285714e-05,
-      "loss": 3.4928,
-      "step": 100
-    },
-    {
-      "epoch": 3.004,
-      "eval_loss": 3.5212297439575195,
-      "eval_runtime": 254.3007,
-      "eval_samples_per_second": 0.983,
-      "eval_steps_per_second": 0.031,
-      "eval_wer": 96.4180569185476,
-      "step": 100
-    },
-    {
-      "epoch": 6.008,
-      "grad_norm": 1.997205376625061,
-      "learning_rate": 8.19387755102041e-05,
-      "loss": 2.4572,
-      "step": 200
-    },
-    {
-      "epoch": 6.008,
-      "eval_loss": 3.190507411956787,
-      "eval_runtime": 192.1727,
-      "eval_samples_per_second": 1.301,
-      "eval_steps_per_second": 0.042,
-      "eval_wer": 92.05103042198233,
-      "step": 200
-    },
-    {
-      "epoch": 9.012,
-      "grad_norm": 1.6556462049484253,
-      "learning_rate": 7.173469387755103e-05,
-      "loss": 1.7435,
-      "step": 300
-    },
-    {
-      "epoch": 9.012,
-      "eval_loss": 2.6634905338287354,
-      "eval_runtime": 241.7692,
-      "eval_samples_per_second": 1.034,
-      "eval_steps_per_second": 0.033,
-      "eval_wer": 99.06771344455349,
-      "step": 300
-    },
-    {
-      "epoch": 12.016,
-      "grad_norm": 2.3752479553222656,
-      "learning_rate": 6.153061224489797e-05,
-      "loss": 1.4418,
-      "step": 400
-    },
-    {
-      "epoch": 12.016,
-      "eval_loss": 2.67608642578125,
-      "eval_runtime": 188.8586,
-      "eval_samples_per_second": 1.324,
-      "eval_steps_per_second": 0.042,
-      "eval_wer": 101.66830225711483,
-      "step": 400
-    },
-    {
-      "epoch": 15.02,
-      "grad_norm": 3.0957250595092773,
-      "learning_rate": 5.132653061224491e-05,
-      "loss": 1.2986,
+      "epoch": 0.25,
+      "grad_norm": 1.1737864017486572,
+      "learning_rate": 0.000759090909090909,
+      "loss": 1.6334,
       "step": 500
     },
     {
-      "epoch": 15.02,
-      "eval_loss": 2.6544599533081055,
-      "eval_runtime": 243.0171,
-      "eval_samples_per_second": 1.029,
-      "eval_steps_per_second": 0.033,
-      "eval_wer": 105.59371933267909,
+      "epoch": 0.25,
+      "eval_loss": 2.2990105152130127,
+      "eval_runtime": 602.9832,
+      "eval_samples_per_second": 0.415,
+      "eval_steps_per_second": 0.053,
+      "eval_wer": 94.3081452404318,
       "step": 500
-    },
-    {
-      "epoch": 18.024,
-      "grad_norm": 2.199568510055542,
-      "learning_rate": 4.112244897959184e-05,
-      "loss": 1.1683,
-      "step": 600
-    },
-    {
-      "epoch": 18.024,
-      "eval_loss": 2.682807683944702,
-      "eval_runtime": 190.2924,
-      "eval_samples_per_second": 1.314,
-      "eval_steps_per_second": 0.042,
-      "eval_wer": 92.98331697742886,
-      "step": 600
     }
   ],
-  "logging_steps": 100,
-  "max_steps": 1000,
+  "logging_steps": 500,
+  "max_steps": 2000,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 9223372036854775807,
-  "save_steps": 100,
+  "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {
@@ -122,7 +42,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.51181401063424e+18,
+  "total_flos": 4.69890367488e+18,
   "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 sha256:3acbf58c4f322256ef2a28a4429e1ca55f9f5c1504873d96c73ffd64cb4852d0
+oid sha256:a3d8d8c7c3bad7ca67b09ea445b40e35b02fcb6febd1b6e09fc11cc8930ec4da
 size 5368