Upload 12 files

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ce1c5bd165ec5ca53857b9d7b59912fbe5653166759de25bd6b3048a81f6a65
+oid sha256:2562f261a4279d150fb41bbb139aa96e35e5721fe402195883b5e3b8ff63a3ca
 size 2490593669

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c4dbbc30d1114bb2167d1c9cb24177bbade4756b03975b42f15a284bb295a72
+oid sha256:23a7c99361dfd5d77b4f7a17ee0b7f5d9398b7395d260c0cea57248c1f0bc835
 size 1262168365

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa692d58d87b134abdf35e16693d21461e181be7686a78e8ec7fa4295965fef9
-size 14575
+oid sha256:fa979f8862d268a53bbc225d9e0f19f63dd983c7a03270746ffd06f961eafeb4
+size 14639

scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7dbbfbece2fede2a53cc80ae296080e69d39722b90afa9ebeb253ed2579b6c4
+oid sha256:914aa322c289af86f9b6a108a871358989b3fdfbd0f18319ba11f7d41c957932
 size 557

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7917745a50f1b899678479a0f5b593ca09d00c5948587dbf077566894c88951a
+oid sha256:2cf61d578f3b4486b40d15325e4d129b551cd728360ff3910d43ff297db9beb4
 size 627

trainer_state.json

@@ -1,76 +1,181 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.0767754318618041,
-  "global_step": 140,
+  "epoch": 0.1689059500959693,
+  "global_step": 22,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.27,
-      "learning_rate": 3.5e-05,
-      "loss": 0.0793,
-      "step": 35
+      "epoch": 0.02,
+      "learning_rate": 1e-05,
+      "loss": 0.0334,
+      "step": 2
     },
     {
-      "epoch": 0.27,
-      "eval_loss": 0.2476252019405365,
-      "eval_runtime": 215.5237,
-      "eval_samples_per_second": 17.237,
-      "eval_steps_per_second": 2.158,
-      "eval_wer": 0.22721730371626994,
-      "step": 35
+      "epoch": 0.02,
+      "eval_loss": 0.2293393462896347,
+      "eval_runtime": 224.0102,
+      "eval_samples_per_second": 16.584,
+      "eval_steps_per_second": 2.076,
+      "eval_wer": 0.19440173885384085,
+      "step": 2
     },
     {
-      "epoch": 0.54,
+      "epoch": 0.03,
+      "learning_rate": 2e-05,
+      "loss": 0.0317,
+      "step": 4
+    },
+    {
+      "epoch": 0.03,
+      "eval_loss": 0.22871321439743042,
+      "eval_runtime": 145.1175,
+      "eval_samples_per_second": 25.6,
+      "eval_steps_per_second": 3.204,
+      "eval_wer": 0.19392461432433866,
+      "step": 4
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 3e-05,
+      "loss": 0.0283,
+      "step": 6
+    },
+    {
+      "epoch": 0.05,
+      "eval_loss": 0.22772984206676483,
+      "eval_runtime": 146.336,
+      "eval_samples_per_second": 25.387,
+      "eval_steps_per_second": 3.178,
+      "eval_wer": 0.19371255897789322,
+      "step": 6
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 4e-05,
+      "loss": 0.0292,
+      "step": 8
+    },
+    {
+      "epoch": 0.06,
+      "eval_loss": 0.22647994756698608,
+      "eval_runtime": 143.8382,
+      "eval_samples_per_second": 25.828,
+      "eval_steps_per_second": 3.233,
+      "eval_wer": 0.19408365583417272,
+      "step": 8
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 5e-05,
+      "loss": 0.0377,
+      "step": 10
+    },
+    {
+      "epoch": 0.08,
+      "eval_loss": 0.22489991784095764,
+      "eval_runtime": 141.406,
+      "eval_samples_per_second": 26.272,
+      "eval_steps_per_second": 3.288,
+      "eval_wer": 0.1942426973440068,
+      "step": 10
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 6e-05,
+      "loss": 0.0292,
+      "step": 12
+    },
+    {
+      "epoch": 0.09,
+      "eval_loss": 0.22301970422267914,
+      "eval_runtime": 144.1564,
+      "eval_samples_per_second": 25.771,
+      "eval_steps_per_second": 3.226,
+      "eval_wer": 0.1938716004877273,
+      "step": 12
+    },
+    {
+      "epoch": 0.11,
       "learning_rate": 7e-05,
-      "loss": 0.0421,
-      "step": 70
+      "loss": 0.0324,
+      "step": 14
+    },
+    {
+      "epoch": 0.11,
+      "eval_loss": 0.22123068571090698,
+      "eval_runtime": 143.996,
+      "eval_samples_per_second": 25.799,
+      "eval_steps_per_second": 3.229,
+      "eval_wer": 0.1925462545724434,
+      "step": 14
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 8e-05,
+      "loss": 0.0298,
+      "step": 16
+    },
+    {
+      "epoch": 0.12,
+      "eval_loss": 0.21999792754650116,
+      "eval_runtime": 154.2033,
+      "eval_samples_per_second": 24.092,
+      "eval_steps_per_second": 3.015,
+      "eval_wer": 0.1928113237555002,
+      "step": 16
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 9e-05,
+      "loss": 0.0437,
+      "step": 18
     },
     {
-      "epoch": 0.54,
-      "eval_loss": 0.22333967685699463,
-      "eval_runtime": 146.1566,
-      "eval_samples_per_second": 25.418,
-      "eval_steps_per_second": 3.182,
-      "eval_wer": 0.20049833006414675,
-      "step": 70
+      "epoch": 0.14,
+      "eval_loss": 0.21752925217151642,
+      "eval_runtime": 145.9518,
+      "eval_samples_per_second": 25.454,
+      "eval_steps_per_second": 3.186,
+      "eval_wer": 0.1933944759582251,
+      "step": 18
     },
     {
-      "epoch": 0.81,
-      "learning_rate": 9.999615088529639e-05,
-      "loss": 0.0367,
-      "step": 105
+      "epoch": 0.15,
+      "learning_rate": 0.0001,
+      "loss": 0.0388,
+      "step": 20
     },
     {
-      "epoch": 0.81,
-      "eval_loss": 0.22262878715991974,
-      "eval_runtime": 146.9473,
-      "eval_samples_per_second": 25.281,
-      "eval_steps_per_second": 3.164,
-      "eval_wer": 0.19588612627895882,
-      "step": 105
+      "epoch": 0.15,
+      "eval_loss": 0.21424689888954163,
+      "eval_runtime": 147.9688,
+      "eval_samples_per_second": 25.107,
+      "eval_steps_per_second": 3.143,
+      "eval_wer": 0.19275830991888884,
+      "step": 20
     },
     {
-      "epoch": 1.08,
-      "learning_rate": 9.996920708237106e-05,
-      "loss": 0.0344,
-      "step": 140
+      "epoch": 0.17,
+      "learning_rate": 9.999846130173874e-05,
+      "loss": 0.0272,
+      "step": 22
     },
     {
-      "epoch": 1.08,
-      "eval_loss": 0.22949478030204773,
-      "eval_runtime": 150.3329,
-      "eval_samples_per_second": 24.712,
-      "eval_steps_per_second": 3.093,
-      "eval_wer": 0.19413666967078408,
-      "step": 140
+      "epoch": 0.17,
+      "eval_loss": 0.21252387762069702,
+      "eval_runtime": 148.2602,
+      "eval_samples_per_second": 25.057,
+      "eval_steps_per_second": 3.136,
+      "eval_wer": 0.19270529608227746,
+      "step": 22
     }
   ],
   "max_steps": 130000,
   "num_train_epochs": 1000,
-  "total_flos": 3.2610548660980367e+18,
+  "total_flos": 5.772040752900557e+17,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5763ec6ea3d1a101893ba7b2ffb1be0c16e4e9c79f48d980304d9a3e0e94a179
+oid sha256:cf5a514c7f06be424cdf63b8e52aaa76409e571965a94e25a81a7b6bbc99d8b6
 size 3323