Training in progress, step 500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:942baad3248aff17d2969223a851a03ca2e2211156481b27e98d989e5a5b5d66
+oid sha256:e0b30193824a36c709bf1b88a41e50fbb0617cd72bc4c32c69e7f3d8166d9db0
 size 966995080

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9f830b2ff1ec787cacfc77d47a45f79b45a7c011e7acca074c24da5a46e410c
+oid sha256:0aaea8a52390ec6410bf4f1342c83b170554d6b097830ff1e7bf5cd0dc4d45f0
 size 1934288064

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9a52643118d1a43e9f69b1da3812fab3b002349f2fc47b29ec634ef0b9c3fda
+oid sha256:1c4d8d8c1c3d69d8fa0b9fd40cc21326ed9c94dc9336ac78a25f8f963c13a2d3
 size 14709

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1a8a0720f656bb61b6635c12b3e45a474a9685aaa36936e1fc2c058f399a224
+oid sha256:531d0e14c05dc7d86079219cf37ce59d4989be2690cfb877976eae819dd930c7
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64739e48f6b71c8e5bbfba9473a32f3e22d0eccbeda9df87bac336c6add4fd46
+oid sha256:e3b23f6346fda9bd8a89c90e344b8e7b3670d52746905b4dfd60f006a5a9c1fb
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 300,
   "best_metric": 37.066605839416056,
   "best_model_checkpoint": "/content/huen_small_out/checkpoint-300",
-  "epoch": 5.333333333333333,
+  "epoch": 6.666666666666667,
   "eval_steps": 100,
-  "global_step": 400,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -184,6 +184,50 @@
       "eval_steps_per_second": 0.231,
       "eval_wer": 45.46076642335766,
       "step": 400
+    },
+    {
+      "epoch": 5.6,
+      "grad_norm": 4.537779331207275,
+      "learning_rate": 6.455555555555556e-06,
+      "loss": 0.43266072273254397,
+      "step": 420
+    },
+    {
+      "epoch": 5.866666666666667,
+      "grad_norm": 7.097001075744629,
+      "learning_rate": 6.2333333333333335e-06,
+      "loss": 0.3608577251434326,
+      "step": 440
+    },
+    {
+      "epoch": 6.133333333333334,
+      "grad_norm": 12.410852432250977,
+      "learning_rate": 6.011111111111112e-06,
+      "loss": 0.3355700016021729,
+      "step": 460
+    },
+    {
+      "epoch": 6.4,
+      "grad_norm": 3.269313097000122,
+      "learning_rate": 5.788888888888889e-06,
+      "loss": 0.1836743474006653,
+      "step": 480
+    },
+    {
+      "epoch": 6.666666666666667,
+      "grad_norm": 11.419748306274414,
+      "learning_rate": 5.566666666666667e-06,
+      "loss": 0.2695281744003296,
+      "step": 500
+    },
+    {
+      "epoch": 6.666666666666667,
+      "eval_loss": 0.9547288417816162,
+      "eval_runtime": 104.6839,
+      "eval_samples_per_second": 1.911,
+      "eval_steps_per_second": 0.239,
+      "eval_wer": 43.06569343065693,
+      "step": 500
     }
   ],
   "logging_steps": 20,
@@ -203,7 +247,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.8455036350464e+18,
+  "total_flos": 2.30695169015808e+18,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null