Upload 11 files

config.json

@@ -43,7 +43,7 @@
   "num_mel_bins": 128,
   "pad_token_id": 50256,
   "scale_embedding": false,
-  "torch_dtype": "float16",
+  "torch_dtype": "float32",
   "transformers_version": "4.37.0.dev0",
   "use_cache": true,
   "use_weighted_layer_sum": false,

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:156e0fd71ba8d6d1a308460a813997db7d653c1f820bd2d5995abd49692f14a1
+oid sha256:f878789c48bcae8bdb738a21db184b61ea25d207190b7a28b1886fd661820964
 size 4993448880

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c05a1c27b9a9a440db979127057f5f66ec41e211bf68bb2ea3a227c4403c8e60
+oid sha256:cebf488a1c5179e1630e18b09c98e0fc49f633401cd2860996acc46e8ce31123
 size 1180663192

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4da10ec2e0bf47d4b44db41bb1bfc93e007a4873e0e2ff5dbc5e667cb0168b4f
+oid sha256:5b881cb7e883293384811c41e69a3af5ab73194ee3fd9c7fc959db40efbb8dce
 size 12333660476

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f584fc46b466d88dd39394bd540717b3bc1053ecc01185f34166047c3442833a
+oid sha256:473904b1f2366db08d341e1d5587ca85e45deb227516e6d83bdef880288fcb69
 size 14244

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd2b4288adefddaec779eef5814fc8113ed6f29d36bcf1119544624d9b84c141
+oid sha256:5a7fed81325cf3d8746c8c8e29722d1ee71a0fee7a7fbd34629d55e97abe774b
 size 1064

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5161290322580645,
+  "epoch": 0.7741935483870968,
   "eval_steps": 1000,
-  "global_step": 2000,
+  "global_step": 3000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -505,6 +505,255 @@
       "eval_steps_per_second": 0.006,
       "eval_wer": 0.10521978021978022,
       "step": 2000
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.923333333333332e-07,
+      "loss": 0.1202,
+      "step": 2025
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.84e-07,
+      "loss": 0.186,
+      "step": 2050
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.756666666666666e-07,
+      "loss": 0.1106,
+      "step": 2075
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.673333333333332e-07,
+      "loss": 0.1926,
+      "step": 2100
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 9.589999999999998e-07,
+      "loss": 0.1178,
+      "step": 2125
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 9.506666666666667e-07,
+      "loss": 0.1744,
+      "step": 2150
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 9.423333333333333e-07,
+      "loss": 0.1263,
+      "step": 2175
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 9.34e-07,
+      "loss": 0.1818,
+      "step": 2200
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 9.256666666666666e-07,
+      "loss": 0.1466,
+      "step": 2225
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 9.173333333333333e-07,
+      "loss": 0.1357,
+      "step": 2250
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 9.09e-07,
+      "loss": 0.148,
+      "step": 2275
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 9.006666666666666e-07,
+      "loss": 0.1684,
+      "step": 2300
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 8.923333333333333e-07,
+      "loss": 0.1368,
+      "step": 2325
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 8.839999999999999e-07,
+      "loss": 0.188,
+      "step": 2350
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 8.756666666666666e-07,
+      "loss": 0.1299,
+      "step": 2375
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 8.673333333333332e-07,
+      "loss": 0.1461,
+      "step": 2400
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 8.59e-07,
+      "loss": 0.1569,
+      "step": 2425
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 8.506666666666667e-07,
+      "loss": 0.1527,
+      "step": 2450
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 8.423333333333334e-07,
+      "loss": 0.1041,
+      "step": 2475
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 8.34e-07,
+      "loss": 0.157,
+      "step": 2500
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 8.256666666666666e-07,
+      "loss": 0.1364,
+      "step": 2525
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 8.173333333333333e-07,
+      "loss": 0.1685,
+      "step": 2550
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 8.09e-07,
+      "loss": 0.1344,
+      "step": 2575
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 8.006666666666666e-07,
+      "loss": 0.1589,
+      "step": 2600
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 7.923333333333333e-07,
+      "loss": 0.1334,
+      "step": 2625
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 7.84e-07,
+      "loss": 0.1297,
+      "step": 2650
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 7.756666666666665e-07,
+      "loss": 0.1326,
+      "step": 2675
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 7.673333333333332e-07,
+      "loss": 0.179,
+      "step": 2700
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 7.59e-07,
+      "loss": 0.1242,
+      "step": 2725
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 7.506666666666667e-07,
+      "loss": 0.1714,
+      "step": 2750
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 7.423333333333333e-07,
+      "loss": 0.1503,
+      "step": 2775
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 7.34e-07,
+      "loss": 0.131,
+      "step": 2800
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 7.256666666666667e-07,
+      "loss": 0.118,
+      "step": 2825
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 7.173333333333333e-07,
+      "loss": 0.1729,
+      "step": 2850
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 7.089999999999999e-07,
+      "loss": 0.1193,
+      "step": 2875
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 7.006666666666666e-07,
+      "loss": 0.1723,
+      "step": 2900
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 6.923333333333333e-07,
+      "loss": 0.1393,
+      "step": 2925
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 6.84e-07,
+      "loss": 0.1259,
+      "step": 2950
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 6.756666666666666e-07,
+      "loss": 0.1228,
+      "step": 2975
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 6.673333333333334e-07,
+      "loss": 0.1794,
+      "step": 3000
+    },
+    {
+      "epoch": 0.77,
+      "eval_loss": 0.13788852095603943,
+      "eval_runtime": 198193.9708,
+      "eval_samples_per_second": 0.047,
+      "eval_steps_per_second": 0.006,
+      "eval_wer": 0.09970911441499677,
+      "step": 3000
     }
   ],
   "logging_steps": 25,
@@ -512,7 +761,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 1000,
-  "total_flos": 5.435997290496e+19,
+  "total_flos": 8.153995935744e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null