Training in progress, step 4000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1799bf6df59b9cabe550644e08cf07ce0b24df0841a5fbfefce4f7f747519afa
+oid sha256:ea56500a65560a074ca9ab85e6281dce5baca5e2f1336bc9ca93232b5bc89d90
 size 775678032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:baa9db0341cd798159c8bd8e3f7c2b1d85dd1c5f202c85529ff0d13d0da5cd33
+oid sha256:024a31d59f0cff6c5d0a6d61ae47e324de8a830ee1fbf5280bb6cfc82d5516a9
 size 1551478091

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c7cf8bdb7a8af0ab86af3bb9a8474a2af3253160164d2d127a1e242155567b6
+oid sha256:aa2b146bcd369b1d02f52100689733e474ff192ab87af4ee028609a153d47508
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ac1c46a2776d12775d23d0f587efc112188137ce2140da35bc15d301c9f620e
+oid sha256:c0033c7745b46bdca3ecab5787678834ca68f7f7e1288869dceeb38812abc253
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1fc34bde3870031dc03d4ad23ff19ec1e9f2133b7ef8b9d21dccb731feee2eb
+oid sha256:3f7d02a0acf38a2c254c6270baa35a3c72938f51148a14bde80f5a273d0fc711
 size 1465

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 3000,
-  "best_metric": 5.684965133666992,
-  "best_model_checkpoint": "/kaggle/working/MASRIBERTv3_ckpts/checkpoint-3000",
-  "epoch": 0.4509752339434026,
+  "best_global_step": 4000,
+  "best_metric": 5.337510108947754,
+  "best_model_checkpoint": "/kaggle/working/MASRIBERTv3_ckpts/checkpoint-4000",
+  "epoch": 0.6013003119245368,
   "eval_steps": 1000,
-  "global_step": 3000,
+  "global_step": 4000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -116,6 +116,42 @@
       "eval_samples_per_second": 70.091,
       "eval_steps_per_second": 1.096,
       "step": 3000
+    },
+    {
+      "epoch": 0.4885565034386862,
+      "grad_norm": 100.90162658691406,
+      "learning_rate": 4.9925434012594344e-05,
+      "loss": 46.94662109375,
+      "step": 3250
+    },
+    {
+      "epoch": 0.5261377729339697,
+      "grad_norm": 97.686767578125,
+      "learning_rate": 4.9848779106991685e-05,
+      "loss": 46.1941953125,
+      "step": 3500
+    },
+    {
+      "epoch": 0.5637190424292533,
+      "grad_norm": 85.13678741455078,
+      "learning_rate": 4.974540876095457e-05,
+      "loss": 45.45590234375,
+      "step": 3750
+    },
+    {
+      "epoch": 0.6013003119245368,
+      "grad_norm": 88.05296325683594,
+      "learning_rate": 4.9615434110096976e-05,
+      "loss": 44.72342578125,
+      "step": 4000
+    },
+    {
+      "epoch": 0.6013003119245368,
+      "eval_loss": 5.337510108947754,
+      "eval_runtime": 245.395,
+      "eval_samples_per_second": 70.099,
+      "eval_steps_per_second": 1.096,
+      "step": 4000
     }
   ],
   "logging_steps": 250,
@@ -144,7 +180,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.0600058421248e+16,
+  "total_flos": 6.7466744561664e+16,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null