Training in progress, epoch 75, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:247c9e7997a56e6ef36972946d3715d25909139e8e1b2b5b10915a4123df01a7
+oid sha256:eaef454aca5a90004a1f7fa735006aaf07a09b80a0c6a02c48a5c9954a9c62a8
 size 559424792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d49286b89bfb500306797db40794e7253e16edb2d06759fd7604e13488743981
+oid sha256:6db55a8256108f51c16b7c04a0dda48b0840ae7fedf6f98128494c32336c189e
 size 1118926970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4c49a5f94183d5eea2e85ebecf0920a90a72c6a9d455839a40431ebc99b1b79
+oid sha256:95d7a84ac41b5d0b0849140ed4b55c3d3d4144a4583408c6d56207542a111683
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b9b48a583021dd0f876f8866c9a036b5875c10a77b3bb22134fbf1237d49f01
+oid sha256:e895d61aa04b2cc52d453ad8ef1da3d7dbc854daaaeb69662e0cdbedb748f6ab
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 12.716951370239258,
   "best_model_checkpoint": "/kaggle/working/output/checkpoint-88740",
-  "epoch": 74.0,
+  "epoch": 75.0,
   "eval_steps": 500,
-  "global_step": 96570,
+  "global_step": 97875,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7354,6 +7354,105 @@
       "eval_samples_per_second": 29.56,
       "eval_steps_per_second": 3.715,
       "step": 96570
+    },
+    {
+      "epoch": 74.02298850574712,
+      "grad_norm": 1.6064398288726807,
+      "learning_rate": 3.7543103448275864e-06,
+      "loss": 11.8828,
+      "step": 96600
+    },
+    {
+      "epoch": 74.09961685823755,
+      "grad_norm": 2.088803768157959,
+      "learning_rate": 3.7064176245210733e-06,
+      "loss": 11.7576,
+      "step": 96700
+    },
+    {
+      "epoch": 74.17624521072797,
+      "grad_norm": 1.5417454242706299,
+      "learning_rate": 3.6585249042145593e-06,
+      "loss": 11.9239,
+      "step": 96800
+    },
+    {
+      "epoch": 74.25287356321839,
+      "grad_norm": 1.5983319282531738,
+      "learning_rate": 3.610632183908046e-06,
+      "loss": 11.8119,
+      "step": 96900
+    },
+    {
+      "epoch": 74.32950191570882,
+      "grad_norm": 3.7642099857330322,
+      "learning_rate": 3.5627394636015326e-06,
+      "loss": 11.8259,
+      "step": 97000
+    },
+    {
+      "epoch": 74.40613026819923,
+      "grad_norm": 1.5149072408676147,
+      "learning_rate": 3.5148467432950195e-06,
+      "loss": 11.9898,
+      "step": 97100
+    },
+    {
+      "epoch": 74.48275862068965,
+      "grad_norm": 0.9915036559104919,
+      "learning_rate": 3.4669540229885055e-06,
+      "loss": 11.7665,
+      "step": 97200
+    },
+    {
+      "epoch": 74.55938697318008,
+      "grad_norm": 1.2745176553726196,
+      "learning_rate": 3.4190613026819924e-06,
+      "loss": 11.9657,
+      "step": 97300
+    },
+    {
+      "epoch": 74.6360153256705,
+      "grad_norm": 2.390751600265503,
+      "learning_rate": 3.3711685823754793e-06,
+      "loss": 11.6856,
+      "step": 97400
+    },
+    {
+      "epoch": 74.71264367816092,
+      "grad_norm": 2.2279295921325684,
+      "learning_rate": 3.3232758620689653e-06,
+      "loss": 11.7551,
+      "step": 97500
+    },
+    {
+      "epoch": 74.78927203065135,
+      "grad_norm": 1.8389006853103638,
+      "learning_rate": 3.275383141762452e-06,
+      "loss": 12.0037,
+      "step": 97600
+    },
+    {
+      "epoch": 74.86590038314176,
+      "grad_norm": 1.4288936853408813,
+      "learning_rate": 3.2274904214559387e-06,
+      "loss": 12.0561,
+      "step": 97700
+    },
+    {
+      "epoch": 74.94252873563218,
+      "grad_norm": 1.037800669670105,
+      "learning_rate": 3.1795977011494255e-06,
+      "loss": 11.9257,
+      "step": 97800
+    },
+    {
+      "epoch": 75.0,
+      "eval_loss": 12.724896430969238,
+      "eval_runtime": 44.1538,
+      "eval_samples_per_second": 29.556,
+      "eval_steps_per_second": 3.714,
+      "step": 97875
     }
   ],
   "logging_steps": 100,
@@ -7368,7 +7467,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 6
+        "early_stopping_patience_counter": 7
       }
     },
     "TrainerControl": {
@@ -7382,7 +7481,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.499281674997862e+16,
+  "total_flos": 4.560071444651981e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null