Training in progress, epoch 23, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6753c78b7c0ef33c0e06df98fc2b17af826195a3d977ff76dfe9dc01bc829d36
+oid sha256:042139fdd65771f5b0b7308a2f417f55545abb2e4526ac63abae75562bc1ba38
 size 1227009528

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:017a44d3ac93ea4bfa9fd21994bffd93889bffa070c7758ab5420752aaad3c5b
+oid sha256:dfff17389b523f38117b38d88e821ea6445c02dd357105f6f1ae677afbba8082
 size 2454133690

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd02ebed0dfeff533894ca511f1b34ff916fe512d4945de5b16f69750a67af48
+oid sha256:757d904eb6af9ff171fa4920de86211e4579188ed035d00ce1124e203a605855
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4565350eeb4b76edcdc222b4a803476b9ee67ea5c3c110e2c10f3af6e808474b
+oid sha256:8963a103756502091940dcb6256fb47e583c349918f9cb8e5f151486ec5304af
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 34.53865432739258,
   "best_model_checkpoint": "/kaggle/working/output/checkpoint-28710",
-  "epoch": 22.0,
+  "epoch": 23.0,
   "eval_steps": 500,
-  "global_step": 28710,
+  "global_step": 30015,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2192,6 +2192,105 @@
       "eval_samples_per_second": 26.454,
       "eval_steps_per_second": 3.324,
       "step": 28710
+    },
+    {
+      "epoch": 22.06896551724138,
+      "grad_norm": 2.77984356880188,
+      "learning_rate": 3.6213122605363986e-05,
+      "loss": 33.6688,
+      "step": 28800
+    },
+    {
+      "epoch": 22.1455938697318,
+      "grad_norm": 3.427570104598999,
+      "learning_rate": 3.616522988505747e-05,
+      "loss": 33.2569,
+      "step": 28900
+    },
+    {
+      "epoch": 22.22222222222222,
+      "grad_norm": 2.060288429260254,
+      "learning_rate": 3.611733716475096e-05,
+      "loss": 33.4445,
+      "step": 29000
+    },
+    {
+      "epoch": 22.298850574712645,
+      "grad_norm": 3.7918601036071777,
+      "learning_rate": 3.6069444444444446e-05,
+      "loss": 34.2303,
+      "step": 29100
+    },
+    {
+      "epoch": 22.375478927203066,
+      "grad_norm": 3.412705659866333,
+      "learning_rate": 3.602155172413793e-05,
+      "loss": 33.5679,
+      "step": 29200
+    },
+    {
+      "epoch": 22.452107279693486,
+      "grad_norm": 4.111233711242676,
+      "learning_rate": 3.597365900383142e-05,
+      "loss": 32.9136,
+      "step": 29300
+    },
+    {
+      "epoch": 22.52873563218391,
+      "grad_norm": 2.1312243938446045,
+      "learning_rate": 3.592576628352491e-05,
+      "loss": 32.8361,
+      "step": 29400
+    },
+    {
+      "epoch": 22.60536398467433,
+      "grad_norm": 2.0618536472320557,
+      "learning_rate": 3.587835249042146e-05,
+      "loss": 33.8499,
+      "step": 29500
+    },
+    {
+      "epoch": 22.68199233716475,
+      "grad_norm": 2.7332096099853516,
+      "learning_rate": 3.5830459770114946e-05,
+      "loss": 33.5899,
+      "step": 29600
+    },
+    {
+      "epoch": 22.75862068965517,
+      "grad_norm": 4.264729022979736,
+      "learning_rate": 3.578256704980843e-05,
+      "loss": 33.194,
+      "step": 29700
+    },
+    {
+      "epoch": 22.835249042145595,
+      "grad_norm": 4.755107402801514,
+      "learning_rate": 3.573467432950192e-05,
+      "loss": 33.2129,
+      "step": 29800
+    },
+    {
+      "epoch": 22.911877394636015,
+      "grad_norm": 3.751232147216797,
+      "learning_rate": 3.56867816091954e-05,
+      "loss": 33.2948,
+      "step": 29900
+    },
+    {
+      "epoch": 22.988505747126435,
+      "grad_norm": 3.3150830268859863,
+      "learning_rate": 3.5638888888888886e-05,
+      "loss": 32.452,
+      "step": 30000
+    },
+    {
+      "epoch": 23.0,
+      "eval_loss": 34.624755859375,
+      "eval_runtime": 49.3378,
+      "eval_samples_per_second": 26.45,
+      "eval_steps_per_second": 3.324,
+      "step": 30015
     }
   ],
   "logging_steps": 100,
@@ -2206,7 +2305,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -2220,7 +2319,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.0960839867037696e+16,
+  "total_flos": 3.2368150770084864e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null