Training in progress, step 11000

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd7a22be120abec7cae4d835d4800211fd1c582dac90b575825986a3f3babf2b
+oid sha256:6e506b28af94c9f67ed9877547aca9647b078ad697e757ce9d0fd58f033848a2
 size 775678032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfa545be0c9d7b43d6549f4f1bf0f2071ca9d4210a9de6d823275e4c73628332
+oid sha256:cd807cd6d5226dc57760c3eb773655ceee8cf46f2e27dadacc31cbcf814fd8cf
 size 1551478091

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73f4b97af2f4a85a98fa4869b40f7b4371fe0109d9dcd77c19217a58c88e458e
+oid sha256:3b5ee8ed6de8ebff1f4e53f6af005a75173401b22aced8e149a6ca7d20e5d75d
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e6fd97f105f8edb4cfe7d5753c1c5716920ac3feb07414e58ddd6a461f2d28f
+oid sha256:022915fa8ac65fae0f13853519b8aa7ee79efd632a399c1f64c6b87bab0b057a
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9807d918a10d1f4568a93321ac8a3b95086950e9354315755af2e5e74af21105
+oid sha256:97cf90b08eb246acaa107a6f5e6030cf607ba438f27aa86bb0197faea0282107
 size 1465

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 10000,
-  "best_metric": 4.5992112159729,
-  "best_model_checkpoint": "/kaggle/working/MASRIBERTv3_ckpts/checkpoint-10000",
-  "epoch": 1.5031380360028561,
+  "best_global_step": 8000,
+  "best_metric": 4.758424758911133,
+  "best_model_checkpoint": "/kaggle/working/MASRIBERTv3_ckpts/checkpoint-8000",
+  "epoch": 1.2024878800405878,
   "eval_steps": 1000,
-  "global_step": 10000,
+  "global_step": 8000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -296,78 +296,6 @@
       "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
     }
   ],
   "logging_steps": 250,
@@ -396,7 +324,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.686529595651927e+17,
+  "total_flos": 1.349195872843607e+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:e81ef68ecf6d54adfcba782e86ddd0804ab77ba8d53704fbef9e1dfb6174a6bf
 size 5201

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd7a22be120abec7cae4d835d4800211fd1c582dac90b575825986a3f3babf2b
+oid sha256:f3c834c79eee72e5f4f4ad464e6fc9b56ed405aea45eae58da5ec83a47059375
 size 775678032