Training in progress, epoch 29, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7192af0b20e9ae92f8d286a2da65a9c5747ee4020c50c48aa473a3e43703773
+oid sha256:daef4e55ad3f9cac7476db8fc6c0558852fa9a93b615790669d2f15c7a8efc1b
 size 1227009528

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff33db56d63c67d85cfa088d479ea506d59eff9e087bf55d1971168fc3e3f331
+oid sha256:f4d1575be4a450eb389f45ccce71c57c7f233f5a2b6bd3384717eae5a12f344b
 size 2454133690

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28a85b72b009dea1edbe23a0bf87db6524c747b48f4861eabc329f71b30d8145
+oid sha256:dd4ea3a90506cd06614bd07f48e2ae5e6d0bcae66d2c1234c0b2b3e5e6f04045
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a5b99942864785620ec565d7775aff86fb1bb9970466bd2d05892314489a53a
+oid sha256:7ca503ac3f6a648f00e869d6e43b6905f33cfb3af705d6edf930285c1fae1c03
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 34.4583740234375,
   "best_model_checkpoint": "/kaggle/working/output/checkpoint-36540",
-  "epoch": 28.0,
+  "epoch": 29.0,
   "eval_steps": 500,
-  "global_step": 36540,
+  "global_step": 37845,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2786,6 +2786,105 @@
       "eval_samples_per_second": 26.465,
       "eval_steps_per_second": 3.326,
       "step": 36540
+    },
+    {
+      "epoch": 28.04597701149425,
+      "grad_norm": 6.301197052001953,
+      "learning_rate": 3.24794061302682e-05,
+      "loss": 33.1986,
+      "step": 36600
+    },
+    {
+      "epoch": 28.122605363984675,
+      "grad_norm": 3.1395254135131836,
+      "learning_rate": 3.243151340996169e-05,
+      "loss": 32.8468,
+      "step": 36700
+    },
+    {
+      "epoch": 28.199233716475096,
+      "grad_norm": 2.673875331878662,
+      "learning_rate": 3.2383620689655175e-05,
+      "loss": 32.7804,
+      "step": 36800
+    },
+    {
+      "epoch": 28.275862068965516,
+      "grad_norm": 3.807201862335205,
+      "learning_rate": 3.233572796934866e-05,
+      "loss": 34.128,
+      "step": 36900
+    },
+    {
+      "epoch": 28.35249042145594,
+      "grad_norm": 3.2160332202911377,
+      "learning_rate": 3.228783524904215e-05,
+      "loss": 33.0419,
+      "step": 37000
+    },
+    {
+      "epoch": 28.42911877394636,
+      "grad_norm": 3.2508413791656494,
+      "learning_rate": 3.2239942528735636e-05,
+      "loss": 33.3642,
+      "step": 37100
+    },
+    {
+      "epoch": 28.50574712643678,
+      "grad_norm": 4.088146209716797,
+      "learning_rate": 3.219204980842912e-05,
+      "loss": 33.1516,
+      "step": 37200
+    },
+    {
+      "epoch": 28.582375478927204,
+      "grad_norm": 3.4091460704803467,
+      "learning_rate": 3.214415708812261e-05,
+      "loss": 33.5824,
+      "step": 37300
+    },
+    {
+      "epoch": 28.659003831417625,
+      "grad_norm": 3.113368034362793,
+      "learning_rate": 3.209626436781609e-05,
+      "loss": 33.2279,
+      "step": 37400
+    },
+    {
+      "epoch": 28.735632183908045,
+      "grad_norm": 3.7009544372558594,
+      "learning_rate": 3.2048371647509577e-05,
+      "loss": 33.0744,
+      "step": 37500
+    },
+    {
+      "epoch": 28.81226053639847,
+      "grad_norm": 2.046365261077881,
+      "learning_rate": 3.2000478927203063e-05,
+      "loss": 33.1949,
+      "step": 37600
+    },
+    {
+      "epoch": 28.88888888888889,
+      "grad_norm": 3.8142659664154053,
+      "learning_rate": 3.195258620689655e-05,
+      "loss": 33.3156,
+      "step": 37700
+    },
+    {
+      "epoch": 28.96551724137931,
+      "grad_norm": 3.120384454727173,
+      "learning_rate": 3.190469348659004e-05,
+      "loss": 32.828,
+      "step": 37800
+    },
+    {
+      "epoch": 29.0,
+      "eval_loss": 34.519615173339844,
+      "eval_runtime": 49.3498,
+      "eval_samples_per_second": 26.444,
+      "eval_steps_per_second": 3.323,
+      "step": 37845
     }
   ],
   "logging_steps": 100,
@@ -2800,7 +2899,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -2814,7 +2913,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.94047052853207e+16,
+  "total_flos": 4.081201618836787e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null