Training in progress, epoch 19, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:984c4064387b5d2acb50bbb73550ab8e59284bb7304c8ae2481fd6b52ff38e6a
+oid sha256:ca9c0fa45ca737106eab6be7425caef617a753946ed0508c1aef1f3a4291004d
 size 1227009528

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69dce8d19e012dd3ce3e9993c52659d81190417ccecc2e0abd73083314d194c9
+oid sha256:acbe2b1c3985ee1c5128707c924ffa1b789c4d55f3b36a9e00d5043900ec85eb
 size 2454133690

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50b8fc98da5c711399560346c0f91ffc2f6dec6609f8c3720258169ba848b497
+oid sha256:9f0baebfc08807f25c4a6326e1681bcfbdd8c24e4c42d43ef5df074269e679b0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b8e678712001404d086acc835dbbf2d80efd02cf92f10187d53131141ee5f90
+oid sha256:0854ef6140ae5c2ba277188e63d5e8a4b0a0fea517aba028586326cadbf26b4b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 34.54485321044922,
   "best_model_checkpoint": "/kaggle/working/output/checkpoint-20880",
-  "epoch": 18.0,
+  "epoch": 19.0,
   "eval_steps": 500,
-  "global_step": 23490,
+  "global_step": 24795,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1789,6 +1789,105 @@
       "eval_samples_per_second": 26.492,
       "eval_steps_per_second": 3.329,
       "step": 23490
+    },
+    {
+      "epoch": 18.007662835249043,
+      "grad_norm": 2.500631809234619,
+      "learning_rate": 3.8750478927203065e-05,
+      "loss": 33.3219,
+      "step": 23500
+    },
+    {
+      "epoch": 18.084291187739463,
+      "grad_norm": 3.90655255317688,
+      "learning_rate": 3.870258620689655e-05,
+      "loss": 33.4211,
+      "step": 23600
+    },
+    {
+      "epoch": 18.160919540229884,
+      "grad_norm": 2.702497720718384,
+      "learning_rate": 3.865469348659004e-05,
+      "loss": 33.2414,
+      "step": 23700
+    },
+    {
+      "epoch": 18.237547892720308,
+      "grad_norm": 1.9609768390655518,
+      "learning_rate": 3.8606800766283525e-05,
+      "loss": 34.0671,
+      "step": 23800
+    },
+    {
+      "epoch": 18.314176245210728,
+      "grad_norm": 2.072951316833496,
+      "learning_rate": 3.855890804597702e-05,
+      "loss": 33.6311,
+      "step": 23900
+    },
+    {
+      "epoch": 18.39080459770115,
+      "grad_norm": 3.249264717102051,
+      "learning_rate": 3.85110153256705e-05,
+      "loss": 32.9968,
+      "step": 24000
+    },
+    {
+      "epoch": 18.467432950191572,
+      "grad_norm": 4.439345359802246,
+      "learning_rate": 3.8463122605363986e-05,
+      "loss": 33.1314,
+      "step": 24100
+    },
+    {
+      "epoch": 18.544061302681992,
+      "grad_norm": 3.9109508991241455,
+      "learning_rate": 3.841522988505747e-05,
+      "loss": 33.3908,
+      "step": 24200
+    },
+    {
+      "epoch": 18.620689655172413,
+      "grad_norm": 2.539151668548584,
+      "learning_rate": 3.836733716475096e-05,
+      "loss": 33.5031,
+      "step": 24300
+    },
+    {
+      "epoch": 18.697318007662837,
+      "grad_norm": 2.6246118545532227,
+      "learning_rate": 3.831944444444445e-05,
+      "loss": 33.6923,
+      "step": 24400
+    },
+    {
+      "epoch": 18.773946360153257,
+      "grad_norm": 3.5379223823547363,
+      "learning_rate": 3.8271551724137934e-05,
+      "loss": 32.9198,
+      "step": 24500
+    },
+    {
+      "epoch": 18.850574712643677,
+      "grad_norm": 3.673536539077759,
+      "learning_rate": 3.822365900383142e-05,
+      "loss": 33.5072,
+      "step": 24600
+    },
+    {
+      "epoch": 18.9272030651341,
+      "grad_norm": 3.9377758502960205,
+      "learning_rate": 3.817576628352491e-05,
+      "loss": 32.8486,
+      "step": 24700
+    },
+    {
+      "epoch": 19.0,
+      "eval_loss": 34.617279052734375,
+      "eval_runtime": 49.3115,
+      "eval_samples_per_second": 26.464,
+      "eval_steps_per_second": 3.326,
+      "step": 24795
     }
   ],
   "logging_steps": 100,
@@ -1803,7 +1902,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 2
+        "early_stopping_patience_counter": 3
       }
     },
     "TrainerControl": {
@@ -1817,7 +1916,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.5331596254849024e+16,
+  "total_flos": 2.673890715789619e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null