Training in progress, epoch 68, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1738638521f9a4843483321124591afb8cd853eff3fb997c6951a7c03e588842
+oid sha256:e8d59fbf7f68e18ff6ed68dba45cfb308b0a78dfe6ecdcef3310538dfe85b22a
 size 559424792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c90abc5ad6fe7535a1f6c408439a600f5498042da6139778d9f74392e46e5921
+oid sha256:803b74531b70e3e6ac182008843d0e57caf703c062c626221f746788edcc53e4
 size 1118926970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1dbc56d3679e9d78846ff9c0b6080bfad3bef32349f7e4d5ac89a28c86be4d62
+oid sha256:8941ac58fba0fdf869315ac1cf71b1b228b16ae0ef1bb0999632b7c6e19008b8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81ea66f3b5d641c21b59c1915efa495d5728b8b68ceeac777b921a0b24de76c3
+oid sha256:25661e8c1ec90edb7b4b746e10879475508a67136274d887a1157d439305d2c3
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 12.731040000915527,
-  "best_model_checkpoint": "/kaggle/working/output/checkpoint-75690",
-  "epoch": 67.0,
+  "best_metric": 12.716951370239258,
+  "best_model_checkpoint": "/kaggle/working/output/checkpoint-88740",
+  "epoch": 68.0,
   "eval_steps": 500,
-  "global_step": 87435,
+  "global_step": 88740,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6661,6 +6661,105 @@
       "eval_samples_per_second": 29.56,
       "eval_steps_per_second": 3.715,
       "step": 87435
+    },
+    {
+      "epoch": 67.04980842911877,
+      "grad_norm": 1.7302024364471436,
+      "learning_rate": 8.110632183908045e-06,
+      "loss": 11.8374,
+      "step": 87500
+    },
+    {
+      "epoch": 67.1264367816092,
+      "grad_norm": 0.8793215751647949,
+      "learning_rate": 8.062739463601534e-06,
+      "loss": 11.7415,
+      "step": 87600
+    },
+    {
+      "epoch": 67.20306513409962,
+      "grad_norm": 1.1903204917907715,
+      "learning_rate": 8.014846743295019e-06,
+      "loss": 11.8223,
+      "step": 87700
+    },
+    {
+      "epoch": 67.27969348659003,
+      "grad_norm": 2.025223731994629,
+      "learning_rate": 7.966954022988506e-06,
+      "loss": 11.7065,
+      "step": 87800
+    },
+    {
+      "epoch": 67.35632183908046,
+      "grad_norm": 1.2028359174728394,
+      "learning_rate": 7.919061302681993e-06,
+      "loss": 11.9446,
+      "step": 87900
+    },
+    {
+      "epoch": 67.43295019157088,
+      "grad_norm": 1.56088387966156,
+      "learning_rate": 7.87116858237548e-06,
+      "loss": 12.0176,
+      "step": 88000
+    },
+    {
+      "epoch": 67.5095785440613,
+      "grad_norm": 1.4466462135314941,
+      "learning_rate": 7.823275862068966e-06,
+      "loss": 11.8777,
+      "step": 88100
+    },
+    {
+      "epoch": 67.58620689655173,
+      "grad_norm": 2.2348804473876953,
+      "learning_rate": 7.775383141762453e-06,
+      "loss": 11.8506,
+      "step": 88200
+    },
+    {
+      "epoch": 67.66283524904215,
+      "grad_norm": 1.0889838933944702,
+      "learning_rate": 7.72749042145594e-06,
+      "loss": 11.9706,
+      "step": 88300
+    },
+    {
+      "epoch": 67.73946360153256,
+      "grad_norm": 1.6289935111999512,
+      "learning_rate": 7.679597701149425e-06,
+      "loss": 11.9588,
+      "step": 88400
+    },
+    {
+      "epoch": 67.816091954023,
+      "grad_norm": 1.2480045557022095,
+      "learning_rate": 7.631704980842912e-06,
+      "loss": 11.7933,
+      "step": 88500
+    },
+    {
+      "epoch": 67.89272030651341,
+      "grad_norm": 1.5679010152816772,
+      "learning_rate": 7.583812260536399e-06,
+      "loss": 12.0495,
+      "step": 88600
+    },
+    {
+      "epoch": 67.96934865900383,
+      "grad_norm": 1.2820953130722046,
+      "learning_rate": 7.535919540229885e-06,
+      "loss": 11.8478,
+      "step": 88700
+    },
+    {
+      "epoch": 68.0,
+      "eval_loss": 12.716951370239258,
+      "eval_runtime": 44.1526,
+      "eval_samples_per_second": 29.557,
+      "eval_steps_per_second": 3.714,
+      "step": 88740
     }
   ],
   "logging_steps": 100,
@@ -6675,7 +6774,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 9
+        "early_stopping_patience_counter": 0
       }
     },
     "TrainerControl": {
@@ -6689,7 +6788,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.073753287419034e+16,
+  "total_flos": 4.134543057073152e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null