Training in progress, step 5000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea56500a65560a074ca9ab85e6281dce5baca5e2f1336bc9ca93232b5bc89d90
+oid sha256:0fac5a6f55f232c4fa9d6549a6328f337a2b19680eb125c0fea7538df9c7926c
 size 775678032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:024a31d59f0cff6c5d0a6d61ae47e324de8a830ee1fbf5280bb6cfc82d5516a9
+oid sha256:5eca38b61a90273520ce4023b3b85dcc51e6f53ebe3dc341ee434151989a26ee
 size 1551478091

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa2b146bcd369b1d02f52100689733e474ff192ab87af4ee028609a153d47508
+oid sha256:d11306c827003ca872f3dbb7eff94c18246ba935b4c57aadab9bda8e1ac77df7
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0033c7745b46bdca3ecab5787678834ca68f7f7e1288869dceeb38812abc253
+oid sha256:82ad8990572ad11a824b7db276c8af49c179ca7e7724b4e6906cd0ae480a80a8
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f7d02a0acf38a2c254c6270baa35a3c72938f51148a14bde80f5a273d0fc711
+oid sha256:2253d135196644bbe0b3e20f4c763c557a93f595b853f202dd6200feeeb354db
 size 1465

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 4000,
-  "best_metric": 5.337510108947754,
-  "best_model_checkpoint": "/kaggle/working/MASRIBERTv3_ckpts/checkpoint-4000",
-  "epoch": 0.6013003119245368,
+  "best_global_step": 5000,
+  "best_metric": 5.109297752380371,
+  "best_model_checkpoint": "/kaggle/working/MASRIBERTv3_ckpts/checkpoint-5000",
+  "epoch": 0.751625389905671,
   "eval_steps": 1000,
-  "global_step": 4000,
+  "global_step": 5000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -152,6 +152,42 @@
       "eval_samples_per_second": 70.099,
       "eval_steps_per_second": 1.096,
       "step": 4000
+    },
+    {
+      "epoch": 0.6388815814198203,
+      "grad_norm": 85.22454833984375,
+      "learning_rate": 4.6920337276199595e-05,
+      "loss": 44.36359375,
+      "step": 4250
+    },
+    {
+      "epoch": 0.6764628509151039,
+      "grad_norm": 89.28252410888672,
+      "learning_rate": 4.6556074961301624e-05,
+      "loss": 43.84180859375,
+      "step": 4500
+    },
+    {
+      "epoch": 0.7140441204103875,
+      "grad_norm": 88.03447723388672,
+      "learning_rate": 4.617303838350222e-05,
+      "loss": 43.3140625,
+      "step": 4750
+    },
+    {
+      "epoch": 0.751625389905671,
+      "grad_norm": 82.08790588378906,
+      "learning_rate": 4.57715611484984e-05,
+      "loss": 42.943515625,
+      "step": 5000
+    },
+    {
+      "epoch": 0.751625389905671,
+      "eval_loss": 5.109297752380371,
+      "eval_runtime": 246.4709,
+      "eval_samples_per_second": 69.793,
+      "eval_steps_per_second": 1.091,
+      "step": 5000
     }
   ],
   "logging_steps": 250,
@@ -180,7 +216,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.7466744561664e+16,
+  "total_flos": 8.433343070208e+16,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b4f316695fa91258ca64377b288abdca2772303c74261f1a0379699703970df
+oid sha256:efefbcb0e8b57f988b34f042db56f28887d1f06d14ec2b11a9e87dc1b7486213
 size 5201