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,

generation_config.json

@@ -260,5 +260,5 @@
     "transcribe": 50360,
     "translate": 50359
   },
-  "transformers_version": "4.36.0.dev0"
+  "transformers_version": "4.37.0.dev0"
 }

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08e0005225b3dbaf55dd13ac62926cc7e02c1025d66fa375e6fb305ff79cd4f9
+oid sha256:3e0b39e4071338e74731a0effa63b1446b76262677e458e296c53e4a9e2d7e17
 size 4993448880

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:630ca774672856d2e0e39a702e590f635a1cfc5726a64b6578ab46dd367369a9
+oid sha256:2a491fb4ca03fcdcad2b02f474a905c161fe140a898b8c657fd1d4efe846b32f
 size 1180663192

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee848402158ac34bd77da476b15335a035ef60e8d19affef08148a06eb616aa0
+size 12333625252

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be24b2b8420b2e62233dac0078a0eaef4fb653235f8f3ed7ac8b73067c134bdf
+size 14054

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1be4d2c14c0b846fa9a00d40df56472a7bedaade8c7be6c4383842a93e02dce1
+size 1064

trainer_state.json

@@ -0,0 +1,270 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.25806451612903225,
+  "eval_steps": 1000,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.5e-08,
+      "loss": 0.7748,
+      "step": 25
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 5e-08,
+      "loss": 1.2926,
+      "step": 50
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 7.5e-08,
+      "loss": 0.7723,
+      "step": 75
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1e-07,
+      "loss": 1.3901,
+      "step": 100
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.25e-07,
+      "loss": 0.7494,
+      "step": 125
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.5e-07,
+      "loss": 1.1551,
+      "step": 150
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.75e-07,
+      "loss": 0.5737,
+      "step": 175
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 2e-07,
+      "loss": 0.7115,
+      "step": 200
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 2.25e-07,
+      "loss": 0.2719,
+      "step": 225
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 2.5e-07,
+      "loss": 0.4535,
+      "step": 250
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 2.75e-07,
+      "loss": 0.2216,
+      "step": 275
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 3e-07,
+      "loss": 0.3218,
+      "step": 300
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 3.25e-07,
+      "loss": 0.1867,
+      "step": 325
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 3.5e-07,
+      "loss": 0.34,
+      "step": 350
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 3.75e-07,
+      "loss": 0.1971,
+      "step": 375
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 4e-07,
+      "loss": 0.2871,
+      "step": 400
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 4.2499999999999995e-07,
+      "loss": 0.1857,
+      "step": 425
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 4.5e-07,
+      "loss": 0.247,
+      "step": 450
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 4.7499999999999995e-07,
+      "loss": 0.167,
+      "step": 475
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 5e-07,
+      "loss": 0.2332,
+      "step": 500
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 5.25e-07,
+      "loss": 0.1908,
+      "step": 525
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 5.5e-07,
+      "loss": 0.2329,
+      "step": 550
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 5.749999999999999e-07,
+      "loss": 0.1589,
+      "step": 575
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 6e-07,
+      "loss": 0.2232,
+      "step": 600
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 6.249999999999999e-07,
+      "loss": 0.166,
+      "step": 625
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 6.5e-07,
+      "loss": 0.2115,
+      "step": 650
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 6.75e-07,
+      "loss": 0.1378,
+      "step": 675
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 7e-07,
+      "loss": 0.1946,
+      "step": 700
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 7.249999999999999e-07,
+      "loss": 0.1553,
+      "step": 725
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 7.5e-07,
+      "loss": 0.2011,
+      "step": 750
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 7.75e-07,
+      "loss": 0.1491,
+      "step": 775
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 8e-07,
+      "loss": 0.1517,
+      "step": 800
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 8.249999999999999e-07,
+      "loss": 0.1266,
+      "step": 825
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 8.499999999999999e-07,
+      "loss": 0.1926,
+      "step": 850
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 8.75e-07,
+      "loss": 0.1404,
+      "step": 875
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 9e-07,
+      "loss": 0.1729,
+      "step": 900
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 9.25e-07,
+      "loss": 0.137,
+      "step": 925
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 9.499999999999999e-07,
+      "loss": 0.1753,
+      "step": 950
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 9.75e-07,
+      "loss": 0.1408,
+      "step": 975
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1e-06,
+      "loss": 0.1819,
+      "step": 1000
+    },
+    {
+      "epoch": 0.26,
+      "eval_loss": 0.14837130904197693,
+      "eval_runtime": 179172.9142,
+      "eval_samples_per_second": 0.052,
+      "eval_steps_per_second": 0.007,
+      "eval_wer": 0.10759534583063995,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 5000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 1000,
+  "total_flos": 2.717998645248e+19,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5dfe0a2d0b841d96b061617209c5507bd50b3d29339aaf4d7f51a05fefb710d2
-size 4399
+oid sha256:8fa887678a8ccbd683868b30e1fa7c6ea0570e0975e9307923e21263be752958
+size 4856