Training in progress, step 100, checkpoint

last-checkpoint/README.md

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

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efef73abb8588e7e4a20c5916ae2fb82670cb01fabc7209d4b6c1fc7e9aa95fb
+oid sha256:0a60f432e42c6f776d59999f121501a1583201a679d8c3db8793d4584a0cb887
 size 14176064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1163d7a9c1d5fdd03b75abf2f0a248b1ec482d3e105056719a0bdb2335d84b01
-size 4832890
+oid sha256:c7dfdc64a80db410a3321f17f5a61c16c2e5343762d60a2ecf33b6a24e20bfbc
+size 4832762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c79694f407c8b34fec70f8f58448c18e86ec8b13274047d470168fd99117ef22
+oid sha256:0ba6c2f0d50b09ba332ede5e78d26a2b049d243564f39ab7379b4e173e564faa
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f17f17271f3b435ef6d1683459b3f439e4795b35f2028e8d831b629678dc9f52
+oid sha256:bdb44de72ad26b6e9c5495c6369934563753532af0c4079339e42ec884246781
 size 1064

last-checkpoint/trainer_state.json

@@ -1,115 +1,35 @@
 {
-  "best_metric": 110.00000000000001,
+  "best_metric": 112.23615784643621,
   "best_model_checkpoint": "../openai/whisper-small-finetuned/checkpoint-100",
-  "epoch": 149.00666666666666,
-  "eval_steps": 50,
-  "global_step": 300,
+  "epoch": 1.1233333333333333,
+  "eval_steps": 100,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 24.006666666666668,
-      "grad_norm": 1.3288557529449463,
-      "learning_rate": 0.00026892857142857144,
-      "loss": 3.2908,
-      "step": 50
-    },
-    {
-      "epoch": 24.006666666666668,
-      "eval_loss": 2.3442695140838623,
-      "eval_runtime": 65.8769,
-      "eval_samples_per_second": 0.091,
-      "eval_steps_per_second": 0.015,
-      "eval_wer": 114.99999999999999,
-      "step": 50
-    },
-    {
-      "epoch": 49.00666666666667,
-      "grad_norm": 0.20936653017997742,
-      "learning_rate": 0.00021535714285714284,
-      "loss": 0.8065,
+      "epoch": 1.1233333333333333,
+      "grad_norm": 1.4843510389328003,
+      "learning_rate": 7.214285714285714e-05,
+      "loss": 3.4293,
       "step": 100
     },
     {
-      "epoch": 49.00666666666667,
-      "eval_loss": 2.699324607849121,
-      "eval_runtime": 35.6683,
-      "eval_samples_per_second": 0.168,
-      "eval_steps_per_second": 0.028,
-      "eval_wer": 110.00000000000001,
-      "step": 100
-    },
-    {
-      "epoch": 74.00666666666666,
-      "grad_norm": 0.09886154532432556,
-      "learning_rate": 0.00016178571428571427,
-      "loss": 0.2445,
-      "step": 150
-    },
-    {
-      "epoch": 74.00666666666666,
-      "eval_loss": 2.929717540740967,
-      "eval_runtime": 36.3546,
-      "eval_samples_per_second": 0.165,
-      "eval_steps_per_second": 0.028,
-      "eval_wer": 117.5,
-      "step": 150
-    },
-    {
-      "epoch": 99.00666666666666,
-      "grad_norm": 0.056343283504247665,
-      "learning_rate": 0.0001082142857142857,
-      "loss": 0.0364,
-      "step": 200
-    },
-    {
-      "epoch": 99.00666666666666,
-      "eval_loss": 3.129232168197632,
-      "eval_runtime": 32.3636,
-      "eval_samples_per_second": 0.185,
-      "eval_steps_per_second": 0.031,
-      "eval_wer": 114.99999999999999,
-      "step": 200
-    },
-    {
-      "epoch": 124.00666666666666,
-      "grad_norm": 0.03805988281965256,
-      "learning_rate": 5.4642857142857135e-05,
-      "loss": 0.0144,
-      "step": 250
-    },
-    {
-      "epoch": 124.00666666666666,
-      "eval_loss": 3.305183172225952,
-      "eval_runtime": 34.8832,
-      "eval_samples_per_second": 0.172,
+      "epoch": 1.1233333333333333,
+      "eval_loss": 3.470705986022949,
+      "eval_runtime": 448.6356,
+      "eval_samples_per_second": 0.892,
       "eval_steps_per_second": 0.029,
-      "eval_wer": 112.5,
-      "step": 250
-    },
-    {
-      "epoch": 149.00666666666666,
-      "grad_norm": 0.03385389223694801,
-      "learning_rate": 1.0714285714285714e-06,
-      "loss": 0.0108,
-      "step": 300
-    },
-    {
-      "epoch": 149.00666666666666,
-      "eval_loss": 3.287505865097046,
-      "eval_runtime": 36.3654,
-      "eval_samples_per_second": 0.165,
-      "eval_steps_per_second": 0.027,
-      "eval_wer": 110.00000000000001,
-      "step": 300
+      "eval_wer": 112.23615784643621,
+      "step": 100
     }
   ],
-  "logging_steps": 50,
+  "logging_steps": 100,
   "max_steps": 300,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 9223372036854775807,
-  "save_steps": 50,
+  "save_steps": 100,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {
@@ -117,12 +37,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.42287220736e+18,
+  "total_flos": 9.3508183130112e+17,
   "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:b625402a7f527e494329513826be1d2936e9c92c62e05bb2287e724674a4c79b
+oid sha256:abde47e545058c9f8627b6b9bd06a10d6ad5246e69db81c99e2d15a0e6a58642
 size 5368