Training in progress, step 6000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fac5a6f55f232c4fa9d6549a6328f337a2b19680eb125c0fea7538df9c7926c
+oid sha256:2fbd17b2ef796ffdb776502b4e54ebe5870575552ecf57a289b06fd09b913987
 size 775678032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5eca38b61a90273520ce4023b3b85dcc51e6f53ebe3dc341ee434151989a26ee
+oid sha256:8c7e919b97730a7da9859d6b1464771915fbe8f95af7a022ba742465a39f96ee
 size 1551478091

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d11306c827003ca872f3dbb7eff94c18246ba935b4c57aadab9bda8e1ac77df7
+oid sha256:508ce3e5b92544d9fea7a56e78a9a3dbbc2ff6650cef6c156b494d8d001ef855
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82ad8990572ad11a824b7db276c8af49c179ca7e7724b4e6906cd0ae480a80a8
+oid sha256:7bb2b51b22f222dc6df63edb791d76de5de25b8bb724e885f8753e34cfb8ae10
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2253d135196644bbe0b3e20f4c763c557a93f595b853f202dd6200feeeb354db
+oid sha256:f2dd5d54f49a7afdfffbf998ae6372fcdee770c6d02602d924eacb55d51a6aa9
 size 1465

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 5000,
-  "best_metric": 5.109297752380371,
-  "best_model_checkpoint": "/kaggle/working/MASRIBERTv3_ckpts/checkpoint-5000",
-  "epoch": 0.751625389905671,
+  "best_global_step": 6000,
+  "best_metric": 4.957474231719971,
+  "best_model_checkpoint": "/kaggle/working/MASRIBERTv3_ckpts/checkpoint-6000",
+  "epoch": 0.9019504678868052,
   "eval_steps": 1000,
-  "global_step": 5000,
+  "global_step": 6000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -188,6 +188,42 @@
       "eval_samples_per_second": 69.793,
       "eval_steps_per_second": 1.091,
       "step": 5000
+    },
+    {
+      "epoch": 0.7892066594009546,
+      "grad_norm": 86.16392517089844,
+      "learning_rate": 4.535199292287709e-05,
+      "loss": 42.626734375,
+      "step": 5250
+    },
+    {
+      "epoch": 0.8267879288962381,
+      "grad_norm": 87.34744262695312,
+      "learning_rate": 4.491469912957297e-05,
+      "loss": 42.33,
+      "step": 5500
+    },
+    {
+      "epoch": 0.8643691983915217,
+      "grad_norm": 79.0370101928711,
+      "learning_rate": 4.4460060629603434e-05,
+      "loss": 41.88755078125,
+      "step": 5750
+    },
+    {
+      "epoch": 0.9019504678868052,
+      "grad_norm": 83.2159423828125,
+      "learning_rate": 4.398847339035767e-05,
+      "loss": 41.65294140625,
+      "step": 6000
+    },
+    {
+      "epoch": 0.9019504678868052,
+      "eval_loss": 4.957474231719971,
+      "eval_runtime": 239.2537,
+      "eval_samples_per_second": 71.899,
+      "eval_steps_per_second": 1.124,
+      "step": 6000
     }
   ],
   "logging_steps": 250,
@@ -216,7 +252,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.433343070208e+16,
+  "total_flos": 1.01200116842496e+17,
   "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:efefbcb0e8b57f988b34f042db56f28887d1f06d14ec2b11a9e87dc1b7486213
+oid sha256:e81ef68ecf6d54adfcba782e86ddd0804ab77ba8d53704fbef9e1dfb6174a6bf
 size 5201