Training in progress, epoch 15, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3dc2253f6a705d4581a259cf35a73237854fffb23cfd63c819297d468b440f4
+oid sha256:811ccfaa8e3c84f8eb2939ce96631f3ec49f0f3099b1b0e60ca7c519a45c98e0
 size 1227009528

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:834b487b2e27a2a0a519304d2774ed6f8a3bc0bf00c5ec3f97eb6a666a2f12df
+oid sha256:727366cbef486a57fc5b65e236bc10bb55ca8dff9e286c2204c706e7a3b6d855
 size 2454133690

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b337fd52d1f50e0cc3a5fd860e091b39657ac975bbe77a94898d8354c966157f
+oid sha256:f6106dbeee05b0c02d6a33db47221a3364be09d497bc2812c14de2fc90515255
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:099df6d11185a7212be93e879fb321f1e41d7aa7efedf5f52a9ceeb4b4dffb4b
+oid sha256:04e18aa381d7c2401ed38f210463d64263e7586c0355129a12549e48c017c1be
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 34.700294494628906,
   "best_model_checkpoint": "/kaggle/working/output/checkpoint-13050",
-  "epoch": 14.0,
+  "epoch": 15.0,
   "eval_steps": 500,
-  "global_step": 18270,
+  "global_step": 19575,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1393,6 +1393,105 @@
       "eval_samples_per_second": 26.492,
       "eval_steps_per_second": 3.329,
       "step": 18270
+    },
+    {
+      "epoch": 14.022988505747126,
+      "grad_norm": 3.0625782012939453,
+      "learning_rate": 4.1239463601532566e-05,
+      "loss": 33.4482,
+      "step": 18300
+    },
+    {
+      "epoch": 14.099616858237548,
+      "grad_norm": 2.5372705459594727,
+      "learning_rate": 4.119157088122605e-05,
+      "loss": 33.284,
+      "step": 18400
+    },
+    {
+      "epoch": 14.17624521072797,
+      "grad_norm": 2.9518911838531494,
+      "learning_rate": 4.114367816091954e-05,
+      "loss": 33.4866,
+      "step": 18500
+    },
+    {
+      "epoch": 14.25287356321839,
+      "grad_norm": 2.1386337280273438,
+      "learning_rate": 4.109578544061303e-05,
+      "loss": 33.653,
+      "step": 18600
+    },
+    {
+      "epoch": 14.329501915708812,
+      "grad_norm": 2.1180756092071533,
+      "learning_rate": 4.1047892720306514e-05,
+      "loss": 34.3663,
+      "step": 18700
+    },
+    {
+      "epoch": 14.406130268199234,
+      "grad_norm": 3.0451836585998535,
+      "learning_rate": 4.1e-05,
+      "loss": 32.7698,
+      "step": 18800
+    },
+    {
+      "epoch": 14.482758620689655,
+      "grad_norm": 3.8517203330993652,
+      "learning_rate": 4.0952107279693494e-05,
+      "loss": 33.3581,
+      "step": 18900
+    },
+    {
+      "epoch": 14.559386973180077,
+      "grad_norm": 2.322065830230713,
+      "learning_rate": 4.0904214559386974e-05,
+      "loss": 33.3386,
+      "step": 19000
+    },
+    {
+      "epoch": 14.636015325670499,
+      "grad_norm": 2.604886054992676,
+      "learning_rate": 4.085632183908046e-05,
+      "loss": 33.8964,
+      "step": 19100
+    },
+    {
+      "epoch": 14.71264367816092,
+      "grad_norm": 3.6753382682800293,
+      "learning_rate": 4.080842911877395e-05,
+      "loss": 32.9918,
+      "step": 19200
+    },
+    {
+      "epoch": 14.789272030651341,
+      "grad_norm": 3.1375985145568848,
+      "learning_rate": 4.07610153256705e-05,
+      "loss": 33.5981,
+      "step": 19300
+    },
+    {
+      "epoch": 14.865900383141762,
+      "grad_norm": 3.9305307865142822,
+      "learning_rate": 4.071312260536399e-05,
+      "loss": 34.0074,
+      "step": 19400
+    },
+    {
+      "epoch": 14.942528735632184,
+      "grad_norm": 3.2952847480773926,
+      "learning_rate": 4.0665229885057473e-05,
+      "loss": 33.0554,
+      "step": 19500
+    },
+    {
+      "epoch": 15.0,
+      "eval_loss": 34.7192268371582,
+      "eval_runtime": 49.2319,
+      "eval_samples_per_second": 26.507,
+      "eval_steps_per_second": 3.331,
+      "step": 19575
     }
   ],
   "logging_steps": 100,
@@ -1407,7 +1506,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 4
+        "early_stopping_patience_counter": 5
       }
     },
     "TrainerControl": {
@@ -1421,7 +1520,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.970235264266035e+16,
+  "total_flos": 2.110966354570752e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null