Training in progress, step 12000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e506b28af94c9f67ed9877547aca9647b078ad697e757ce9d0fd58f033848a2
+oid sha256:0c0c81bef5323115b0ca05b31867d900bc610eb0358e60008f6de9ef2fc1702d
 size 775678032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd807cd6d5226dc57760c3eb773655ceee8cf46f2e27dadacc31cbcf814fd8cf
+oid sha256:eb8afa5bf990f864aad355cd5c12dab1726add3a6caffba51fa87e06fba5ccc7
 size 1551478091

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b5ee8ed6de8ebff1f4e53f6af005a75173401b22aced8e149a6ca7d20e5d75d
+oid sha256:ed2c793e8f016051f230cda481bd489c6a6e08fcb8a1ee25a5731e69a8424766
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:022915fa8ac65fae0f13853519b8aa7ee79efd632a399c1f64c6b87bab0b057a
+oid sha256:ae029a8e6af9f014c9ef8b713fcd28cef1f184648ddde977ce75efc89ca9a242
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97cf90b08eb246acaa107a6f5e6030cf607ba438f27aa86bb0197faea0282107
+oid sha256:c320e3d9186dfabeb03caa6a27e31ade5586ed070e0c2b54d3b3d43b885980e1
 size 1465

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 8000,
-  "best_metric": 4.758424758911133,
-  "best_model_checkpoint": "/kaggle/working/MASRIBERTv3_ckpts/checkpoint-8000",
-  "epoch": 1.2024878800405878,
+  "best_global_step": 12000,
+  "best_metric": 4.493417263031006,
+  "best_model_checkpoint": "/kaggle/working/MASRIBERTv3_ckpts/checkpoint-12000",
+  "epoch": 1.8037881919651246,
   "eval_steps": 1000,
-  "global_step": 8000,
+  "global_step": 12000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -296,6 +296,150 @@
       "eval_samples_per_second": 72.134,
       "eval_steps_per_second": 1.128,
       "step": 8000
+    },
+    {
+      "epoch": 1.2400691495358713,
+      "grad_norm": 94.54589080810547,
+      "learning_rate": 3.905384188481714e-05,
+      "loss": 39.47437890625,
+      "step": 8250
+    },
+    {
+      "epoch": 1.2776504190311548,
+      "grad_norm": 84.85308837890625,
+      "learning_rate": 3.843760628720439e-05,
+      "loss": 39.3814765625,
+      "step": 8500
+    },
+    {
+      "epoch": 1.3152316885264383,
+      "grad_norm": 80.48727416992188,
+      "learning_rate": 3.7809667206761164e-05,
+      "loss": 39.18900390625,
+      "step": 8750
+    },
+    {
+      "epoch": 1.352812958021722,
+      "grad_norm": 79.16352844238281,
+      "learning_rate": 3.717057154701251e-05,
+      "loss": 39.15230859375,
+      "step": 9000
+    },
+    {
+      "epoch": 1.352812958021722,
+      "eval_loss": 4.669365406036377,
+      "eval_runtime": 240.8713,
+      "eval_samples_per_second": 71.416,
+      "eval_steps_per_second": 1.117,
+      "step": 9000
+    },
+    {
+      "epoch": 1.3903942275170056,
+      "grad_norm": 81.47567749023438,
+      "learning_rate": 3.6520875928305904e-05,
+      "loss": 38.7915625,
+      "step": 9250
+    },
+    {
+      "epoch": 1.427975497012289,
+      "grad_norm": 79.67969512939453,
+      "learning_rate": 3.58611462030228e-05,
+      "loss": 38.70076953125,
+      "step": 9500
+    },
+    {
+      "epoch": 1.4655567665075726,
+      "grad_norm": 78.06887817382812,
+      "learning_rate": 3.5191956962749483e-05,
+      "loss": 38.5454296875,
+      "step": 9750
+    },
+    {
+      "epoch": 1.5031380360028561,
+      "grad_norm": 81.57176971435547,
+      "learning_rate": 3.4513891037836586e-05,
+      "loss": 38.56761328125,
+      "step": 10000
+    },
+    {
+      "epoch": 1.5031380360028561,
+      "eval_loss": 4.5992112159729,
+      "eval_runtime": 240.6841,
+      "eval_samples_per_second": 71.471,
+      "eval_steps_per_second": 1.118,
+      "step": 10000
+    },
+    {
+      "epoch": 1.5407193054981398,
+      "grad_norm": 76.18035888671875,
+      "learning_rate": 3.382753898978297e-05,
+      "loss": 38.34355859375,
+      "step": 10250
+    },
+    {
+      "epoch": 1.5783005749934231,
+      "grad_norm": 77.42598724365234,
+      "learning_rate": 3.313349859688622e-05,
+      "loss": 38.3613984375,
+      "step": 10500
+    },
+    {
+      "epoch": 1.6158818444887069,
+      "grad_norm": 83.92522430419922,
+      "learning_rate": 3.2432374333607674e-05,
+      "loss": 38.15187890625,
+      "step": 10750
+    },
+    {
+      "epoch": 1.6534631139839904,
+      "grad_norm": 80.59062957763672,
+      "learning_rate": 3.172477684410535e-05,
+      "loss": 38.12749609375,
+      "step": 11000
+    },
+    {
+      "epoch": 1.6534631139839904,
+      "eval_loss": 4.554149150848389,
+      "eval_runtime": 240.8324,
+      "eval_samples_per_second": 71.427,
+      "eval_steps_per_second": 1.117,
+      "step": 11000
+    },
+    {
+      "epoch": 1.6910443834792739,
+      "grad_norm": 84.59385681152344,
+      "learning_rate": 3.1011322410393507e-05,
+      "loss": 38.04288671875,
+      "step": 11250
+    },
+    {
+      "epoch": 1.7286256529745576,
+      "grad_norm": 78.90901947021484,
+      "learning_rate": 3.0292632415591782e-05,
+      "loss": 37.87243359375,
+      "step": 11500
+    },
+    {
+      "epoch": 1.766206922469841,
+      "grad_norm": 82.36697387695312,
+      "learning_rate": 2.95693328027316e-05,
+      "loss": 37.75355859375,
+      "step": 11750
+    },
+    {
+      "epoch": 1.8037881919651246,
+      "grad_norm": 75.0630874633789,
+      "learning_rate": 2.884205352959113e-05,
+      "loss": 37.58091796875,
+      "step": 12000
+    },
+    {
+      "epoch": 1.8037881919651246,
+      "eval_loss": 4.493417263031006,
+      "eval_runtime": 240.8882,
+      "eval_samples_per_second": 71.411,
+      "eval_steps_per_second": 1.117,
+      "step": 12000
     }
   ],
   "logging_steps": 250,
@@ -324,7 +468,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.349195872843607e+17,
+  "total_flos": 2.023863318460247e+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:e81ef68ecf6d54adfcba782e86ddd0804ab77ba8d53704fbef9e1dfb6174a6bf
+oid sha256:0d8537015b69c60e2c29af27ee6860531dfc4207cede0d753719b984b2c5e39a
 size 5201