Training in progress, step 6000

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.3033297657966614,
+    "eval_runtime": 395.7148,
+    "eval_samples": 4297,
+    "eval_samples_per_second": 10.859,
+    "eval_steps_per_second": 0.341,
+    "eval_wer": 0.19506011201512932,
+    "train_loss": 0.46717894900821066,
+    "train_runtime": 42700.8803,
+    "train_samples": 240334,
+    "train_samples_per_second": 16.885,
+    "train_steps_per_second": 0.132
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.3033297657966614,
+    "eval_runtime": 395.7148,
+    "eval_samples": 4297,
+    "eval_samples_per_second": 10.859,
+    "eval_steps_per_second": 0.341,
+    "eval_wer": 0.19506011201512932
+}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10b8e1e4605fca290d5637f77478cc5de89067a6e3dd236781ad3c3d70de68cb
+oid sha256:69b8c3e5a25929fe5518b2db2fc0b10d4c584f3b4511f4b9ec2bc19eb7f1d4a4
 size 1262112241

runs/Jan28_20-45-33_job-336a688f-553a-4e6e-83b3-ad5d10274b51/events.out.tfevents.1643412482.job-336a688f-553a-4e6e-83b3-ad5d10274b51.1189245.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c6b6d036c28f99ebb382382b8e2848d070749fe09cbc17a490b427cad92ce44
-size 6645
+oid sha256:6e29e7542794e6d9f43f9b278d28a04e7ff23e188392a22e6a077259111cbb7d
+size 6999

runs/Jan28_20-45-33_job-336a688f-553a-4e6e-83b3-ad5d10274b51/events.out.tfevents.1643455581.job-336a688f-553a-4e6e-83b3-ad5d10274b51.1189245.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ad1ae5576bd3416a35b021fb919dad4e371ae9403e741e829e575ec56203db5
+size 358

runs/Jan29_11-55-18_job-336a688f-553a-4e6e-83b3-ad5d10274b51/1643460077.0405679/events.out.tfevents.1643460077.job-336a688f-553a-4e6e-83b3-ad5d10274b51.1539029.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5f8d5820deac48bf643fdd77bbb1bd465f636a90796b1c2628810308ca62348
+size 4814

runs/Jan29_11-55-18_job-336a688f-553a-4e6e-83b3-ad5d10274b51/events.out.tfevents.1643460077.job-336a688f-553a-4e6e-83b3-ad5d10274b51.1539029.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7b03f34331375aed60c773aca2e4e4c67953313085ef60c3bd9c0aba81ffc68
+size 5220

special_tokens_map.json

@@ -1 +1 @@
-{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]", "additional_special_tokens": [{"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]", "additional_special_tokens": [{"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.46717894900821066,
+    "train_runtime": 42700.8803,
+    "train_samples": 240334,
+    "train_samples_per_second": 16.885,
+    "train_steps_per_second": 0.132
+}

trainer_state.json

@@ -0,0 +1,190 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9996005858074826,
+  "global_step": 5631,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.8712499999999997e-05,
+      "loss": 6.2099,
+      "step": 500
+    },
+    {
+      "epoch": 0.09,
+      "eval_loss": 3.41253662109375,
+      "eval_runtime": 1358.074,
+      "eval_samples_per_second": 14.868,
+      "eval_steps_per_second": 0.465,
+      "eval_wer": 1.0,
+      "step": 500
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 3.7462499999999996e-05,
+      "loss": 2.9961,
+      "step": 1000
+    },
+    {
+      "epoch": 0.18,
+      "eval_loss": 2.9223873615264893,
+      "eval_runtime": 1361.8836,
+      "eval_samples_per_second": 14.827,
+      "eval_steps_per_second": 0.463,
+      "eval_wer": 1.0,
+      "step": 1000
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 5.62125e-05,
+      "loss": 2.2147,
+      "step": 1500
+    },
+    {
+      "epoch": 0.26,
+      "eval_loss": 0.6520791053771973,
+      "eval_runtime": 1355.9385,
+      "eval_samples_per_second": 14.892,
+      "eval_steps_per_second": 0.465,
+      "eval_wer": 0.5567824255052013,
+      "step": 1500
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 7.49625e-05,
+      "loss": 1.3017,
+      "step": 2000
+    },
+    {
+      "epoch": 0.35,
+      "eval_loss": 0.31525641679763794,
+      "eval_runtime": 1371.0684,
+      "eval_samples_per_second": 14.727,
+      "eval_steps_per_second": 0.46,
+      "eval_wer": 0.27607269814249236,
+      "step": 2000
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 7.431581352833637e-05,
+      "loss": 1.1196,
+      "step": 2500
+    },
+    {
+      "epoch": 0.44,
+      "eval_loss": 0.24444133043289185,
+      "eval_runtime": 1363.4869,
+      "eval_samples_per_second": 14.809,
+      "eval_steps_per_second": 0.463,
+      "eval_wer": 0.23673497683411066,
+      "step": 2500
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 7.363162705667275e-05,
+      "loss": 1.0712,
+      "step": 3000
+    },
+    {
+      "epoch": 0.53,
+      "eval_loss": 0.23236490786075592,
+      "eval_runtime": 1368.4487,
+      "eval_samples_per_second": 14.755,
+      "eval_steps_per_second": 0.461,
+      "eval_wer": 0.21321861436015543,
+      "step": 3000
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 7.294606946983546e-05,
+      "loss": 1.052,
+      "step": 3500
+    },
+    {
+      "epoch": 0.62,
+      "eval_loss": 0.21734564006328583,
+      "eval_runtime": 1358.6503,
+      "eval_samples_per_second": 14.862,
+      "eval_steps_per_second": 0.464,
+      "eval_wer": 0.20317428528513493,
+      "step": 3500
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 3.375103277334068e-05,
+      "loss": 1.2813,
+      "step": 4000
+    },
+    {
+      "epoch": 2.13,
+      "eval_loss": 0.332599401473999,
+      "eval_runtime": 393.989,
+      "eval_samples_per_second": 10.906,
+      "eval_steps_per_second": 0.343,
+      "eval_wer": 0.20989847979467358,
+      "step": 4000
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 2.3423299366565682e-05,
+      "loss": 1.2365,
+      "step": 4500
+    },
+    {
+      "epoch": 2.4,
+      "eval_loss": 0.3223731815814972,
+      "eval_runtime": 391.7507,
+      "eval_samples_per_second": 10.969,
+      "eval_steps_per_second": 0.345,
+      "eval_wer": 0.2003283560376986,
+      "step": 4500
+    },
+    {
+      "epoch": 2.66,
+      "learning_rate": 1.309556595979069e-05,
+      "loss": 1.2193,
+      "step": 5000
+    },
+    {
+      "epoch": 2.66,
+      "eval_loss": 0.31981074810028076,
+      "eval_runtime": 402.4439,
+      "eval_samples_per_second": 10.677,
+      "eval_steps_per_second": 0.335,
+      "eval_wer": 0.19565239980464894,
+      "step": 5000
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 2.767832553015698e-06,
+      "loss": 1.2072,
+      "step": 5500
+    },
+    {
+      "epoch": 2.93,
+      "eval_loss": 0.3063456118106842,
+      "eval_runtime": 396.6525,
+      "eval_samples_per_second": 10.833,
+      "eval_steps_per_second": 0.34,
+      "eval_wer": 0.19327285763271923,
+      "step": 5500
+    },
+    {
+      "epoch": 3.0,
+      "step": 5631,
+      "total_flos": 1.4549289807228204e+20,
+      "train_loss": 0.46717894900821066,
+      "train_runtime": 42700.8803,
+      "train_samples_per_second": 16.885,
+      "train_steps_per_second": 0.132
+    }
+  ],
+  "max_steps": 5631,
+  "num_train_epochs": 3,
+  "total_flos": 1.4549289807228204e+20,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:900730258ef5ba01c3771eb89400d63447160b6a533e2bc89e44d21af9e331f2
+oid sha256:d5c09474639eff781a9fbbd58d81fc04a95748d863d0d33f663b0592e8c64a21
 size 3055