Training in progress, step 13000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c0c81bef5323115b0ca05b31867d900bc610eb0358e60008f6de9ef2fc1702d
+oid sha256:a57123bd504f020542f459e0b2d2ba4180fc0578d6dd7ad276fb7a208091e378
 size 775678032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb8afa5bf990f864aad355cd5c12dab1726add3a6caffba51fa87e06fba5ccc7
+oid sha256:a19a21b645fdd05fb9151a733862d8d8c2a0d6c853bb69f24756b80a0f6fbe33
 size 1551478091

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed2c793e8f016051f230cda481bd489c6a6e08fcb8a1ee25a5731e69a8424766
+oid sha256:bdafb4730dcdce2ef1bd6bdaf3661baf8f043f766d4a640ed55b11dce576c094
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae029a8e6af9f014c9ef8b713fcd28cef1f184648ddde977ce75efc89ca9a242
+oid sha256:12e40c044fc20b06edb62b2decf2bd7a9ba13eb66fc4f9a7e953a32ef0d2f361
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c320e3d9186dfabeb03caa6a27e31ade5586ed070e0c2b54d3b3d43b885980e1
+oid sha256:cf5019ea016aa58b369c6fb99a06bd2f7068344e725284d5390e74749b8ec08a
 size 1465

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 12000,
-  "best_metric": 4.493417263031006,
-  "best_model_checkpoint": "/kaggle/working/MASRIBERTv3_ckpts/checkpoint-12000",
-  "epoch": 1.8037881919651246,
+  "best_global_step": 13000,
+  "best_metric": 4.470274925231934,
+  "best_model_checkpoint": "/kaggle/working/MASRIBERTv3_ckpts/checkpoint-13000",
+  "epoch": 1.9541132699462587,
   "eval_steps": 1000,
-  "global_step": 12000,
+  "global_step": 13000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -440,6 +440,42 @@
       "eval_samples_per_second": 71.411,
       "eval_steps_per_second": 1.117,
       "step": 12000
+    },
+    {
+      "epoch": 1.8413694614604081,
+      "grad_norm": 79.44371032714844,
+      "learning_rate": 2.8111428020033515e-05,
+      "loss": 37.55409375,
+      "step": 12250
+    },
+    {
+      "epoch": 1.8789507309556917,
+      "grad_norm": 74.53401947021484,
+      "learning_rate": 2.7378092612326463e-05,
+      "loss": 37.37219140625,
+      "step": 12500
+    },
+    {
+      "epoch": 1.9165320004509754,
+      "grad_norm": 84.87117767333984,
+      "learning_rate": 2.6642686004923362e-05,
+      "loss": 37.2856171875,
+      "step": 12750
+    },
+    {
+      "epoch": 1.9541132699462587,
+      "grad_norm": 82.84407806396484,
+      "learning_rate": 2.590584870018894e-05,
+      "loss": 37.37483984375,
+      "step": 13000
+    },
+    {
+      "epoch": 1.9541132699462587,
+      "eval_loss": 4.470274925231934,
+      "eval_runtime": 211.1559,
+      "eval_samples_per_second": 81.466,
+      "eval_steps_per_second": 1.274,
+      "step": 13000
     }
   ],
   "logging_steps": 250,
@@ -468,7 +504,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.023863318460247e+17,
+  "total_flos": 2.192530179864407e+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 sha256:0d8537015b69c60e2c29af27ee6860531dfc4207cede0d753719b984b2c5e39a
+oid sha256:37035eb47da31ff856a20e153427690aa44fd0ebded4ddc3cd23f44d3d4a7fa9
 size 5201