Training in progress, epoch 54, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4eb9214e77b95b667809524bb92ccdb3fe0cddb365e4b97eb893a9763a379ee
+oid sha256:1f10a46ae0fe8faa638b90706116478036c6879ef50efabc16324038a6922abd
 size 559424792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:074561df402564df116cabe74d67d3503d4d9291f0f354cd18856b3b50a776dd
+oid sha256:d3857507fcf0b1aa90bb8f98bc0e08dc71b62dbfd30895ea70043803719aa9e4
 size 1118926970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:818e11e6f0507868aff6bd7e55b412f657c9bb72e9258e1faa9ef9caa4921519
+oid sha256:07e5ac3e26b1d68a09de4fdd68441ef04f1d8303cbf18747cfe94d9d2277b3fb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f11117c239d42e7cdc39bd6698c9cd8e6a9f1fe7f935ac3dc7dbad47e0f7ed4a
+oid sha256:1a76d3c41b3162edd98f18432f4c86854461f58319b2c950d99c6ab0664d88b2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 12.762798309326172,
-  "best_model_checkpoint": "/kaggle/working/output/checkpoint-66555",
-  "epoch": 53.0,
+  "best_metric": 12.753838539123535,
+  "best_model_checkpoint": "/kaggle/working/output/checkpoint-70470",
+  "epoch": 54.0,
   "eval_steps": 500,
-  "global_step": 69165,
+  "global_step": 70470,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5268,6 +5268,105 @@
       "eval_samples_per_second": 29.582,
       "eval_steps_per_second": 3.718,
       "step": 69165
+    },
+    {
+      "epoch": 53.02681992337165,
+      "grad_norm": 1.2087703943252563,
+      "learning_rate": 1.6870689655172413e-05,
+      "loss": 11.8316,
+      "step": 69200
+    },
+    {
+      "epoch": 53.10344827586207,
+      "grad_norm": 1.472959280014038,
+      "learning_rate": 1.68227969348659e-05,
+      "loss": 11.9068,
+      "step": 69300
+    },
+    {
+      "epoch": 53.18007662835249,
+      "grad_norm": 1.2973859310150146,
+      "learning_rate": 1.6774904214559387e-05,
+      "loss": 11.8753,
+      "step": 69400
+    },
+    {
+      "epoch": 53.25670498084291,
+      "grad_norm": 1.3909817934036255,
+      "learning_rate": 1.6727011494252877e-05,
+      "loss": 11.6868,
+      "step": 69500
+    },
+    {
+      "epoch": 53.333333333333336,
+      "grad_norm": 1.1226869821548462,
+      "learning_rate": 1.667911877394636e-05,
+      "loss": 11.7399,
+      "step": 69600
+    },
+    {
+      "epoch": 53.40996168582375,
+      "grad_norm": 1.6086245775222778,
+      "learning_rate": 1.6631226053639847e-05,
+      "loss": 11.9871,
+      "step": 69700
+    },
+    {
+      "epoch": 53.486590038314176,
+      "grad_norm": 5.143097400665283,
+      "learning_rate": 1.65838122605364e-05,
+      "loss": 12.0991,
+      "step": 69800
+    },
+    {
+      "epoch": 53.5632183908046,
+      "grad_norm": 1.1883777379989624,
+      "learning_rate": 1.6535919540229886e-05,
+      "loss": 11.7275,
+      "step": 69900
+    },
+    {
+      "epoch": 53.63984674329502,
+      "grad_norm": 1.152468204498291,
+      "learning_rate": 1.6488026819923373e-05,
+      "loss": 11.9268,
+      "step": 70000
+    },
+    {
+      "epoch": 53.71647509578544,
+      "grad_norm": 1.6981552839279175,
+      "learning_rate": 1.6440134099616856e-05,
+      "loss": 12.0293,
+      "step": 70100
+    },
+    {
+      "epoch": 53.793103448275865,
+      "grad_norm": 1.6067506074905396,
+      "learning_rate": 1.6392241379310347e-05,
+      "loss": 11.9477,
+      "step": 70200
+    },
+    {
+      "epoch": 53.86973180076628,
+      "grad_norm": 3.569709539413452,
+      "learning_rate": 1.6344348659003834e-05,
+      "loss": 11.8055,
+      "step": 70300
+    },
+    {
+      "epoch": 53.946360153256705,
+      "grad_norm": 2.3322157859802246,
+      "learning_rate": 1.629645593869732e-05,
+      "loss": 12.027,
+      "step": 70400
+    },
+    {
+      "epoch": 54.0,
+      "eval_loss": 12.753838539123535,
+      "eval_runtime": 44.1081,
+      "eval_samples_per_second": 29.586,
+      "eval_steps_per_second": 3.718,
+      "step": 70470
     }
   ],
   "logging_steps": 100,
@@ -5282,7 +5381,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 2
+        "early_stopping_patience_counter": 0
       }
     },
     "TrainerControl": {
@@ -5296,7 +5395,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.222696512261376e+16,
+  "total_flos": 3.2834862819154944e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null