Training in progress, epoch 77, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4af379246575accc58f6abfac00aee925ce6b65883c8632448c83ee50ddfd07
+oid sha256:a5ab75838ed7afe0c288b3631cba017faa548802aa5787f848080d63a4faa88d
 size 559424792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:930083a4131ce65cdc8b356487bf1b813c159fa19cc01194a70d602dd9b94b36
+oid sha256:b09965c1441b1cd1585c57f2d17e8d0e016910d7c90ad54c3a3afac8664c3bfd
 size 1118926970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:914809037b3f88a1a2608685ab6ce1391a78e990c3ce33067466cc03d6a8480d
+oid sha256:eddd447be293e64952cf96e8afe87fbb852cea08cd9ba63106be57df271d8556
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f90a182f176031c61cd117d508af79c4ff26bf3b95484e9bbe4017a087414d71
+oid sha256:cc365eae5b467a6c47056a0e754f854a75cac7f154e6d27e155fce16f2e6ebd0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 12.716951370239258,
   "best_model_checkpoint": "/kaggle/working/output/checkpoint-88740",
-  "epoch": 76.0,
+  "epoch": 77.0,
   "eval_steps": 500,
-  "global_step": 99180,
+  "global_step": 100485,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7552,6 +7552,105 @@
       "eval_samples_per_second": 29.555,
       "eval_steps_per_second": 3.714,
       "step": 99180
+    },
+    {
+      "epoch": 76.01532567049809,
+      "grad_norm": 1.737823724746704,
+      "learning_rate": 2.509578544061303e-06,
+      "loss": 11.8981,
+      "step": 99200
+    },
+    {
+      "epoch": 76.0919540229885,
+      "grad_norm": 1.0878353118896484,
+      "learning_rate": 2.4616858237547894e-06,
+      "loss": 11.8443,
+      "step": 99300
+    },
+    {
+      "epoch": 76.16858237547893,
+      "grad_norm": 2.0454564094543457,
+      "learning_rate": 2.413793103448276e-06,
+      "loss": 11.8515,
+      "step": 99400
+    },
+    {
+      "epoch": 76.24521072796935,
+      "grad_norm": 1.3210684061050415,
+      "learning_rate": 2.3659003831417623e-06,
+      "loss": 12.0233,
+      "step": 99500
+    },
+    {
+      "epoch": 76.32183908045977,
+      "grad_norm": 1.1547104120254517,
+      "learning_rate": 2.318007662835249e-06,
+      "loss": 11.7145,
+      "step": 99600
+    },
+    {
+      "epoch": 76.3984674329502,
+      "grad_norm": 1.3948626518249512,
+      "learning_rate": 2.270114942528736e-06,
+      "loss": 11.7098,
+      "step": 99700
+    },
+    {
+      "epoch": 76.47509578544062,
+      "grad_norm": 1.2874501943588257,
+      "learning_rate": 2.2222222222222225e-06,
+      "loss": 11.8953,
+      "step": 99800
+    },
+    {
+      "epoch": 76.55172413793103,
+      "grad_norm": 1.8570905923843384,
+      "learning_rate": 2.174329501915709e-06,
+      "loss": 11.9397,
+      "step": 99900
+    },
+    {
+      "epoch": 76.62835249042146,
+      "grad_norm": 1.3673057556152344,
+      "learning_rate": 2.1264367816091954e-06,
+      "loss": 11.8056,
+      "step": 100000
+    },
+    {
+      "epoch": 76.70498084291188,
+      "grad_norm": 2.1938419342041016,
+      "learning_rate": 2.078544061302682e-06,
+      "loss": 11.9414,
+      "step": 100100
+    },
+    {
+      "epoch": 76.7816091954023,
+      "grad_norm": 1.9171061515808105,
+      "learning_rate": 2.0306513409961687e-06,
+      "loss": 11.8369,
+      "step": 100200
+    },
+    {
+      "epoch": 76.85823754789271,
+      "grad_norm": 1.0486401319503784,
+      "learning_rate": 1.982758620689655e-06,
+      "loss": 11.8322,
+      "step": 100300
+    },
+    {
+      "epoch": 76.93486590038314,
+      "grad_norm": 1.6005215644836426,
+      "learning_rate": 1.934865900383142e-06,
+      "loss": 11.8781,
+      "step": 100400
+    },
+    {
+      "epoch": 77.0,
+      "eval_loss": 12.72097396850586,
+      "eval_runtime": 44.1751,
+      "eval_samples_per_second": 29.542,
+      "eval_steps_per_second": 3.712,
+      "step": 100485
     }
   ],
   "logging_steps": 100,
@@ -7566,7 +7665,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 8
+        "early_stopping_patience_counter": 9
       }
     },
     "TrainerControl": {
@@ -7580,7 +7679,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.620861214306099e+16,
+  "total_flos": 4.681650983960218e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null