Training in progress, step 3000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c16c9e78ef2042429b8621b93304131003820f12fd969bc192d3c404a71dd032
+oid sha256:22849577bc1ba2840136dfbcc01308c6bf368e9413e14c0615c2b843b7c5f399
 size 1934161157

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:846a6d114ac32bb18f266794a1f073d34691090fcb05478049d5436d9983a2ed
+oid sha256:ea813b036d82fd7c97ac7e0d7a7566c1bf9088683b65db4f18f6f869ae317577
 size 967102729

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11dbcedeb462d624e874b21e47f755022f531a9db8eea64f2e44191aab46241b
+oid sha256:85dcd9588829e28a34b471fbefe47c5b729c37261cb017e050a2c52e69019df0
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cd37dd530bd467817ba99df096031e0ec04862523fd363efae5f40294a6a156
+oid sha256:f375f0ec2d81d3bc0adbea21cfba80dd771ec303d1e16586405d497868a3b309
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "best_metric": 15.986121540094766,
-  "best_model_checkpoint": "./whisper-vietnamese-cntt2/checkpoint-2000",
-  "epoch": 5.730659025787966,
-  "global_step": 2000,
+  "best_metric": 15.753087698402425,
+  "best_model_checkpoint": "./whisper-vietnamese-cntt2/checkpoint-3000",
+  "epoch": 8.595988538681949,
+  "global_step": 3000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -506,11 +506,261 @@
       "eval_steps_per_second": 0.105,
       "eval_wer": 15.986121540094766,
       "step": 2000
+    },
+    {
+      "epoch": 5.8,
+      "learning_rate": 1e-05,
+      "loss": 0.0197,
+      "step": 2025
+    },
+    {
+      "epoch": 5.87,
+      "learning_rate": 1e-05,
+      "loss": 0.023,
+      "step": 2050
+    },
+    {
+      "epoch": 5.95,
+      "learning_rate": 1e-05,
+      "loss": 0.0201,
+      "step": 2075
+    },
+    {
+      "epoch": 6.02,
+      "learning_rate": 1e-05,
+      "loss": 0.0166,
+      "step": 2100
+    },
+    {
+      "epoch": 6.09,
+      "learning_rate": 1e-05,
+      "loss": 0.0114,
+      "step": 2125
+    },
+    {
+      "epoch": 6.16,
+      "learning_rate": 1e-05,
+      "loss": 0.0111,
+      "step": 2150
+    },
+    {
+      "epoch": 6.23,
+      "learning_rate": 1e-05,
+      "loss": 0.0102,
+      "step": 2175
+    },
+    {
+      "epoch": 6.3,
+      "learning_rate": 1e-05,
+      "loss": 0.0122,
+      "step": 2200
+    },
+    {
+      "epoch": 6.38,
+      "learning_rate": 1e-05,
+      "loss": 0.0117,
+      "step": 2225
+    },
+    {
+      "epoch": 6.45,
+      "learning_rate": 1e-05,
+      "loss": 0.0103,
+      "step": 2250
+    },
+    {
+      "epoch": 6.52,
+      "learning_rate": 1e-05,
+      "loss": 0.0113,
+      "step": 2275
+    },
+    {
+      "epoch": 6.59,
+      "learning_rate": 1e-05,
+      "loss": 0.0114,
+      "step": 2300
+    },
+    {
+      "epoch": 6.66,
+      "learning_rate": 1e-05,
+      "loss": 0.0106,
+      "step": 2325
+    },
+    {
+      "epoch": 6.73,
+      "learning_rate": 1e-05,
+      "loss": 0.0143,
+      "step": 2350
+    },
+    {
+      "epoch": 6.81,
+      "learning_rate": 1e-05,
+      "loss": 0.0118,
+      "step": 2375
+    },
+    {
+      "epoch": 6.88,
+      "learning_rate": 1e-05,
+      "loss": 0.0122,
+      "step": 2400
+    },
+    {
+      "epoch": 6.95,
+      "learning_rate": 1e-05,
+      "loss": 0.0124,
+      "step": 2425
+    },
+    {
+      "epoch": 7.02,
+      "learning_rate": 1e-05,
+      "loss": 0.012,
+      "step": 2450
+    },
+    {
+      "epoch": 7.09,
+      "learning_rate": 1e-05,
+      "loss": 0.0065,
+      "step": 2475
+    },
+    {
+      "epoch": 7.16,
+      "learning_rate": 1e-05,
+      "loss": 0.0059,
+      "step": 2500
+    },
+    {
+      "epoch": 7.23,
+      "learning_rate": 1e-05,
+      "loss": 0.0078,
+      "step": 2525
+    },
+    {
+      "epoch": 7.31,
+      "learning_rate": 1e-05,
+      "loss": 0.0076,
+      "step": 2550
+    },
+    {
+      "epoch": 7.38,
+      "learning_rate": 1e-05,
+      "loss": 0.009,
+      "step": 2575
+    },
+    {
+      "epoch": 7.45,
+      "learning_rate": 1e-05,
+      "loss": 0.0066,
+      "step": 2600
+    },
+    {
+      "epoch": 7.52,
+      "learning_rate": 1e-05,
+      "loss": 0.0083,
+      "step": 2625
+    },
+    {
+      "epoch": 7.59,
+      "learning_rate": 1e-05,
+      "loss": 0.008,
+      "step": 2650
+    },
+    {
+      "epoch": 7.66,
+      "learning_rate": 1e-05,
+      "loss": 0.0085,
+      "step": 2675
+    },
+    {
+      "epoch": 7.74,
+      "learning_rate": 1e-05,
+      "loss": 0.0082,
+      "step": 2700
+    },
+    {
+      "epoch": 7.81,
+      "learning_rate": 1e-05,
+      "loss": 0.0081,
+      "step": 2725
+    },
+    {
+      "epoch": 7.88,
+      "learning_rate": 1e-05,
+      "loss": 0.0087,
+      "step": 2750
+    },
+    {
+      "epoch": 7.95,
+      "learning_rate": 1e-05,
+      "loss": 0.0081,
+      "step": 2775
+    },
+    {
+      "epoch": 8.02,
+      "learning_rate": 1e-05,
+      "loss": 0.0063,
+      "step": 2800
+    },
+    {
+      "epoch": 8.09,
+      "learning_rate": 1e-05,
+      "loss": 0.0052,
+      "step": 2825
+    },
+    {
+      "epoch": 8.17,
+      "learning_rate": 1e-05,
+      "loss": 0.0065,
+      "step": 2850
+    },
+    {
+      "epoch": 8.24,
+      "learning_rate": 1e-05,
+      "loss": 0.0056,
+      "step": 2875
+    },
+    {
+      "epoch": 8.31,
+      "learning_rate": 1e-05,
+      "loss": 0.0056,
+      "step": 2900
+    },
+    {
+      "epoch": 8.38,
+      "learning_rate": 1e-05,
+      "loss": 0.0059,
+      "step": 2925
+    },
+    {
+      "epoch": 8.45,
+      "learning_rate": 1e-05,
+      "loss": 0.0053,
+      "step": 2950
+    },
+    {
+      "epoch": 8.52,
+      "learning_rate": 1e-05,
+      "loss": 0.0059,
+      "step": 2975
+    },
+    {
+      "epoch": 8.6,
+      "learning_rate": 1e-05,
+      "loss": 0.0076,
+      "step": 3000
+    },
+    {
+      "epoch": 8.6,
+      "eval_cer": 8.452163206837971,
+      "eval_loss": 0.4291725158691406,
+      "eval_runtime": 658.3899,
+      "eval_samples_per_second": 1.677,
+      "eval_steps_per_second": 0.105,
+      "eval_wer": 15.753087698402425,
+      "step": 3000
     }
   ],
   "max_steps": 4000,
   "num_train_epochs": 12,
-  "total_flos": 9.2174176862208e+18,
+  "total_flos": 1.382439501692928e+19,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:846a6d114ac32bb18f266794a1f073d34691090fcb05478049d5436d9983a2ed
+oid sha256:ea813b036d82fd7c97ac7e0d7a7566c1bf9088683b65db4f18f6f869ae317577
 size 967102729

runs/Aug21_04-31-19_c5e76769b0ca/events.out.tfevents.1692592289.c5e76769b0ca.29.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12bd6fb5de9661b81cd114eba14d6ed85f263ce2b4c3a464cb01a8cf917caa56
-size 19139
+oid sha256:eeec86711318f1799deee27e02c3e9d75de46e6f8cf61abaa1ce89a7cf46af83
+size 25784