Training in progress, epoch 78, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5ab75838ed7afe0c288b3631cba017faa548802aa5787f848080d63a4faa88d
+oid sha256:21c9f69a173a892667d6dee7aaad371f40e7baf8cb3e9d969f1b6dcde4a515f1
 size 559424792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b09965c1441b1cd1585c57f2d17e8d0e016910d7c90ad54c3a3afac8664c3bfd
+oid sha256:2b013c178fe9fdbc20f357d276fbc376ffeb5ae200d4656a25c0840d60905025
 size 1118926970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eddd447be293e64952cf96e8afe87fbb852cea08cd9ba63106be57df271d8556
+oid sha256:325b7db62095a95388ccc4086fa74938caa1cf51efa7e26a65d55b88f9c20149
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc365eae5b467a6c47056a0e754f854a75cac7f154e6d27e155fce16f2e6ebd0
+oid sha256:43652567e6245845fba84f7f23bb5bb43e6dfe5f4e79e8b80a87c4194eca0dd2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 12.716951370239258,
   "best_model_checkpoint": "/kaggle/working/output/checkpoint-88740",
-  "epoch": 77.0,
+  "epoch": 78.0,
   "eval_steps": 500,
-  "global_step": 100485,
+  "global_step": 101790,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7651,6 +7651,105 @@
       "eval_samples_per_second": 29.542,
       "eval_steps_per_second": 3.712,
       "step": 100485
+    },
+    {
+      "epoch": 77.01149425287356,
+      "grad_norm": 1.5276216268539429,
+      "learning_rate": 1.8869731800766285e-06,
+      "loss": 12.0855,
+      "step": 100500
+    },
+    {
+      "epoch": 77.08812260536398,
+      "grad_norm": 1.6150214672088623,
+      "learning_rate": 1.839080459770115e-06,
+      "loss": 12.0257,
+      "step": 100600
+    },
+    {
+      "epoch": 77.16475095785441,
+      "grad_norm": 1.33854341506958,
+      "learning_rate": 1.7911877394636015e-06,
+      "loss": 11.8612,
+      "step": 100700
+    },
+    {
+      "epoch": 77.24137931034483,
+      "grad_norm": 3.1214921474456787,
+      "learning_rate": 1.7432950191570881e-06,
+      "loss": 11.8497,
+      "step": 100800
+    },
+    {
+      "epoch": 77.31800766283524,
+      "grad_norm": 1.6240577697753906,
+      "learning_rate": 1.695402298850575e-06,
+      "loss": 11.7641,
+      "step": 100900
+    },
+    {
+      "epoch": 77.39463601532567,
+      "grad_norm": 1.1317625045776367,
+      "learning_rate": 1.6475095785440615e-06,
+      "loss": 11.846,
+      "step": 101000
+    },
+    {
+      "epoch": 77.47126436781609,
+      "grad_norm": 1.294534683227539,
+      "learning_rate": 1.599616858237548e-06,
+      "loss": 11.7364,
+      "step": 101100
+    },
+    {
+      "epoch": 77.5478927203065,
+      "grad_norm": 1.099564790725708,
+      "learning_rate": 1.5517241379310346e-06,
+      "loss": 11.8554,
+      "step": 101200
+    },
+    {
+      "epoch": 77.62452107279694,
+      "grad_norm": 1.1482292413711548,
+      "learning_rate": 1.503831417624521e-06,
+      "loss": 11.9346,
+      "step": 101300
+    },
+    {
+      "epoch": 77.70114942528735,
+      "grad_norm": 1.198670506477356,
+      "learning_rate": 1.4559386973180077e-06,
+      "loss": 11.8685,
+      "step": 101400
+    },
+    {
+      "epoch": 77.77777777777777,
+      "grad_norm": 2.162407159805298,
+      "learning_rate": 1.4080459770114944e-06,
+      "loss": 11.8622,
+      "step": 101500
+    },
+    {
+      "epoch": 77.8544061302682,
+      "grad_norm": 1.3662519454956055,
+      "learning_rate": 1.3601532567049808e-06,
+      "loss": 11.9364,
+      "step": 101600
+    },
+    {
+      "epoch": 77.93103448275862,
+      "grad_norm": 1.1566288471221924,
+      "learning_rate": 1.3122605363984675e-06,
+      "loss": 11.7345,
+      "step": 101700
+    },
+    {
+      "epoch": 78.0,
+      "eval_loss": 12.726273536682129,
+      "eval_runtime": 44.1782,
+      "eval_samples_per_second": 29.539,
+      "eval_steps_per_second": 3.712,
+      "step": 101790
     }
   ],
   "logging_steps": 100,
@@ -7665,7 +7764,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 9
+        "early_stopping_patience_counter": 10
       }
     },
     "TrainerControl": {
@@ -7674,12 +7773,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4.681650983960218e+16,
+  "total_flos": 4.742440753614336e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null