Training in progress, step 9000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e506b28af94c9f67ed9877547aca9647b078ad697e757ce9d0fd58f033848a2
+oid sha256:94866cc75aec33c09133a0fb4fa4dfd49fb0b254b4b6ede67f1805569573438d
 size 775678032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd807cd6d5226dc57760c3eb773655ceee8cf46f2e27dadacc31cbcf814fd8cf
+oid sha256:9296cbf34201bcdb073c905679753552821e4613b2a1709034cff62a6edb2bd8
 size 1551478091

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b5ee8ed6de8ebff1f4e53f6af005a75173401b22aced8e149a6ca7d20e5d75d
+oid sha256:45b7666e8a6f09360daf8a47228bb57f19d338bbc0f88e8d91aa3858a27c844d
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:022915fa8ac65fae0f13853519b8aa7ee79efd632a399c1f64c6b87bab0b057a
+oid sha256:00b4eb0c27b559cfd649f7c80a6d3394a55880d92b3ee2ca98f71b67e7b2333a
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97cf90b08eb246acaa107a6f5e6030cf607ba438f27aa86bb0197faea0282107
+oid sha256:151c5e22bfc2a771646595fb1b1d684f2565cfc37c097b2585cef37a029984c7
 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": 9000,
+  "best_metric": 4.669365406036377,
+  "best_model_checkpoint": "/kaggle/working/MASRIBERTv3_ckpts/checkpoint-9000",
+  "epoch": 1.352812958021722,
   "eval_steps": 1000,
-  "global_step": 8000,
+  "global_step": 9000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -296,6 +296,42 @@
       "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
     }
   ],
   "logging_steps": 250,
@@ -324,7 +360,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.349195872843607e+17,
+  "total_flos": 1.517862734247767e+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