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 sha256:08e0005225b3dbaf55dd13ac62926cc7e02c1025d66fa375e6fb305ff79cd4f9
+oid sha256:dcba8cb26f5ac1b26555b07a6ae8873581075aaf0702c9f393e0a2f53f9c3eb2
 size 4993448880

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:630ca774672856d2e0e39a702e590f635a1cfc5726a64b6578ab46dd367369a9
+oid sha256:dbc291761a468b6236109acedacb3b0017f00895057c15820b0027e778fc5fb6
 size 1180663192

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e8bac954a7913d692fd50a482d47de48625e368c8e5f3d3f3302acd1428ff12
+oid sha256:5c1c504281f4a5cf99152635854cf2e5735ca337bddd2ea93b8da624f6203ed2
 size 12333625252

trainer_state.json

@@ -11,250 +11,250 @@
     {
       "epoch": 0.01,
       "learning_rate": 1.25e-08,
-      "loss": 0.6602,
+      "loss": 0.5815,
       "step": 25
     },
     {
       "epoch": 0.01,
       "learning_rate": 2.5e-08,
-      "loss": 1.0487,
+      "loss": 0.9607,
       "step": 50
     },
     {
       "epoch": 0.02,
       "learning_rate": 3.75e-08,
-      "loss": 0.6436,
+      "loss": 0.5678,
       "step": 75
     },
     {
       "epoch": 0.02,
       "learning_rate": 5e-08,
-      "loss": 1.0184,
+      "loss": 0.9329,
       "step": 100
     },
     {
       "epoch": 0.03,
       "learning_rate": 6.25e-08,
-      "loss": 0.6427,
+      "loss": 0.5937,
       "step": 125
     },
     {
       "epoch": 0.03,
       "learning_rate": 7.5e-08,
-      "loss": 0.9576,
+      "loss": 0.9153,
       "step": 150
     },
     {
       "epoch": 0.04,
       "learning_rate": 8.75e-08,
-      "loss": 0.5878,
+      "loss": 0.5232,
       "step": 175
     },
     {
       "epoch": 0.04,
       "learning_rate": 1e-07,
-      "loss": 0.9261,
+      "loss": 0.8711,
       "step": 200
     },
     {
       "epoch": 0.05,
       "learning_rate": 1.125e-07,
-      "loss": 0.5172,
+      "loss": 0.4636,
       "step": 225
     },
     {
       "epoch": 0.05,
       "learning_rate": 1.25e-07,
-      "loss": 0.7859,
+      "loss": 0.6875,
       "step": 250
     },
     {
       "epoch": 0.06,
       "learning_rate": 1.375e-07,
-      "loss": 0.4913,
+      "loss": 0.3447,
       "step": 275
     },
     {
       "epoch": 0.06,
       "learning_rate": 1.5e-07,
-      "loss": 0.6184,
+      "loss": 0.4347,
       "step": 300
     },
     {
       "epoch": 0.07,
       "learning_rate": 1.625e-07,
-      "loss": 0.3088,
+      "loss": 0.2261,
       "step": 325
     },
     {
       "epoch": 0.07,
       "learning_rate": 1.75e-07,
-      "loss": 0.3973,
+      "loss": 0.3323,
       "step": 350
     },
     {
       "epoch": 0.08,
       "learning_rate": 1.875e-07,
-      "loss": 0.2386,
+      "loss": 0.2093,
       "step": 375
     },
     {
       "epoch": 0.08,
       "learning_rate": 2e-07,
-      "loss": 0.2516,
+      "loss": 0.2357,
       "step": 400
     },
     {
       "epoch": 0.09,
       "learning_rate": 2.1249999999999998e-07,
-      "loss": 0.168,
+      "loss": 0.1632,
       "step": 425
     },
     {
       "epoch": 0.1,
       "learning_rate": 2.25e-07,
-      "loss": 0.2036,
+      "loss": 0.2114,
       "step": 450
     },
     {
       "epoch": 0.1,
       "learning_rate": 2.3749999999999998e-07,
-      "loss": 0.1564,
+      "loss": 0.1587,
       "step": 475
     },
     {
       "epoch": 0.11,
       "learning_rate": 2.5e-07,
-      "loss": 0.2491,
+      "loss": 0.2634,
       "step": 500
     },
     {
       "epoch": 0.11,
       "learning_rate": 2.625e-07,
-      "loss": 0.1817,
+      "loss": 0.1897,
       "step": 525
     },
     {
       "epoch": 0.12,
       "learning_rate": 2.75e-07,
-      "loss": 0.236,
+      "loss": 0.2373,
       "step": 550
     },
     {
       "epoch": 0.12,
       "learning_rate": 2.8749999999999995e-07,
-      "loss": 0.1117,
+      "loss": 0.1154,
       "step": 575
     },
     {
       "epoch": 0.13,
       "learning_rate": 3e-07,
-      "loss": 0.1665,
+      "loss": 0.1733,
       "step": 600
     },
     {
       "epoch": 0.13,
       "learning_rate": 3.1249999999999997e-07,
-      "loss": 0.1533,
+      "loss": 0.1558,
       "step": 625
     },
     {
       "epoch": 0.14,
       "learning_rate": 3.25e-07,
-      "loss": 0.2006,
+      "loss": 0.2124,
       "step": 650
     },
     {
       "epoch": 0.14,
       "learning_rate": 3.375e-07,
-      "loss": 0.1425,
+      "loss": 0.1478,
       "step": 675
     },
     {
       "epoch": 0.15,
       "learning_rate": 3.5e-07,
-      "loss": 0.1769,
+      "loss": 0.1925,
       "step": 700
     },
     {
       "epoch": 0.15,
       "learning_rate": 3.6249999999999997e-07,
-      "loss": 0.1259,
+      "loss": 0.1349,
       "step": 725
     },
     {
       "epoch": 0.16,
       "learning_rate": 3.75e-07,
-      "loss": 0.2038,
+      "loss": 0.2101,
       "step": 750
     },
     {
       "epoch": 0.16,
       "learning_rate": 3.875e-07,
-      "loss": 0.1431,
+      "loss": 0.1556,
       "step": 775
     },
     {
       "epoch": 0.17,
       "learning_rate": 4e-07,
-      "loss": 0.1459,
+      "loss": 0.1572,
       "step": 800
     },
     {
       "epoch": 0.17,
       "learning_rate": 4.1249999999999997e-07,
-      "loss": 0.1219,
+      "loss": 0.1339,
       "step": 825
     },
     {
       "epoch": 0.18,
       "learning_rate": 4.2499999999999995e-07,
-      "loss": 0.2224,
+      "loss": 0.2275,
       "step": 850
     },
     {
       "epoch": 0.19,
       "learning_rate": 4.375e-07,
-      "loss": 0.1409,
+      "loss": 0.1529,
       "step": 875
     },
     {
       "epoch": 0.19,
       "learning_rate": 4.5e-07,
-      "loss": 0.1993,
+      "loss": 0.2102,
       "step": 900
     },
     {
       "epoch": 0.2,
       "learning_rate": 4.625e-07,
-      "loss": 0.1486,
+      "loss": 0.1567,
       "step": 925
     },
     {
       "epoch": 0.2,
       "learning_rate": 4.7499999999999995e-07,
-      "loss": 0.1924,
+      "loss": 0.2087,
       "step": 950
     },
     {
       "epoch": 0.21,
       "learning_rate": 4.875e-07,
-      "loss": 0.107,
+      "loss": 0.1155,
       "step": 975
     },
     {
       "epoch": 0.21,
       "learning_rate": 5e-07,
-      "loss": 0.1534,
+      "loss": 0.163,
       "step": 1000
     },
     {
       "epoch": 0.21,
-      "eval_loss": 0.1283227652311325,
-      "eval_runtime": 271898.2411,
-      "eval_samples_per_second": 0.035,
-      "eval_steps_per_second": 0.004,
-      "eval_wer": 0.08386096256684492,
+      "eval_loss": 0.13766534626483917,
+      "eval_runtime": 257216.5334,
+      "eval_samples_per_second": 0.037,
+      "eval_steps_per_second": 0.005,
+      "eval_wer": 0.0962566844919786,
       "step": 1000
     }
   ],

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a1e93ebb1bba8a2558c7f365f093b9b295c6a74c892c2fd0cc31018e0c5f485
+oid sha256:8b160490c443b161f18bd788ec020faaa217e6d7db5a6b0cf1b1be6e6ea1a968
 size 4856