Training in progress, epoch 28, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6578b9c4d75748b6280cbd87cff77c51810b19211f34f787c2c20a45bba7f69a
+oid sha256:d7192af0b20e9ae92f8d286a2da65a9c5747ee4020c50c48aa473a3e43703773
 size 1227009528

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebfa5e3b95d0b2043f86b91a91689cd4bbf2940ae6a300f2f266d892b9b6aa2a
+oid sha256:ff33db56d63c67d85cfa088d479ea506d59eff9e087bf55d1971168fc3e3f331
 size 2454133690

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:701bb29f6de724269b66c860403f8e84b96f5ac92e54ca67ad415c85cf650a00
+oid sha256:28a85b72b009dea1edbe23a0bf87db6524c747b48f4861eabc329f71b30d8145
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf4aead81b9bf3b888621453ce55acb21aa6ea9c3c6f5c0de4c20591eb5cb4b1
+oid sha256:0a5b99942864785620ec565d7775aff86fb1bb9970466bd2d05892314489a53a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 34.47444152832031,
-  "best_model_checkpoint": "/kaggle/working/output/checkpoint-35235",
-  "epoch": 27.0,
+  "best_metric": 34.4583740234375,
+  "best_model_checkpoint": "/kaggle/working/output/checkpoint-36540",
+  "epoch": 28.0,
   "eval_steps": 500,
-  "global_step": 35235,
+  "global_step": 36540,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2687,6 +2687,105 @@
       "eval_samples_per_second": 26.478,
       "eval_steps_per_second": 3.328,
       "step": 35235
+    },
+    {
+      "epoch": 27.049808429118773,
+      "grad_norm": 2.2080352306365967,
+      "learning_rate": 3.310201149425288e-05,
+      "loss": 33.0059,
+      "step": 35300
+    },
+    {
+      "epoch": 27.126436781609197,
+      "grad_norm": 3.0985817909240723,
+      "learning_rate": 3.3054118773946366e-05,
+      "loss": 33.8201,
+      "step": 35400
+    },
+    {
+      "epoch": 27.203065134099617,
+      "grad_norm": 3.165069103240967,
+      "learning_rate": 3.300622605363985e-05,
+      "loss": 33.7343,
+      "step": 35500
+    },
+    {
+      "epoch": 27.279693486590038,
+      "grad_norm": 3.2427308559417725,
+      "learning_rate": 3.295833333333333e-05,
+      "loss": 32.8829,
+      "step": 35600
+    },
+    {
+      "epoch": 27.35632183908046,
+      "grad_norm": 2.973548412322998,
+      "learning_rate": 3.291044061302682e-05,
+      "loss": 33.2656,
+      "step": 35700
+    },
+    {
+      "epoch": 27.43295019157088,
+      "grad_norm": 2.892834424972534,
+      "learning_rate": 3.2862547892720306e-05,
+      "loss": 33.085,
+      "step": 35800
+    },
+    {
+      "epoch": 27.509578544061302,
+      "grad_norm": 2.4037787914276123,
+      "learning_rate": 3.281465517241379e-05,
+      "loss": 32.7549,
+      "step": 35900
+    },
+    {
+      "epoch": 27.586206896551722,
+      "grad_norm": 3.7890052795410156,
+      "learning_rate": 3.276676245210728e-05,
+      "loss": 33.4256,
+      "step": 36000
+    },
+    {
+      "epoch": 27.662835249042146,
+      "grad_norm": 3.4910600185394287,
+      "learning_rate": 3.271886973180077e-05,
+      "loss": 33.3707,
+      "step": 36100
+    },
+    {
+      "epoch": 27.739463601532567,
+      "grad_norm": 2.895573854446411,
+      "learning_rate": 3.2670977011494254e-05,
+      "loss": 32.699,
+      "step": 36200
+    },
+    {
+      "epoch": 27.816091954022987,
+      "grad_norm": 4.670979022979736,
+      "learning_rate": 3.262308429118774e-05,
+      "loss": 33.5898,
+      "step": 36300
+    },
+    {
+      "epoch": 27.89272030651341,
+      "grad_norm": 2.362605571746826,
+      "learning_rate": 3.257519157088123e-05,
+      "loss": 33.4235,
+      "step": 36400
+    },
+    {
+      "epoch": 27.96934865900383,
+      "grad_norm": 4.695677280426025,
+      "learning_rate": 3.2527298850574715e-05,
+      "loss": 33.9318,
+      "step": 36500
+    },
+    {
+      "epoch": 28.0,
+      "eval_loss": 34.4583740234375,
+      "eval_runtime": 49.3101,
+      "eval_samples_per_second": 26.465,
+      "eval_steps_per_second": 3.326,
+      "step": 36540
     }
   ],
   "logging_steps": 100,
@@ -2715,7 +2814,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.799739438227354e+16,
+  "total_flos": 3.94047052853207e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null