Training in progress, step 8000

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df50b8a580ea8526eb0730d57704938f14070df067dee66888ec8693240b765e
+oid sha256:0fac5a6f55f232c4fa9d6549a6328f337a2b19680eb125c0fea7538df9c7926c
 size 775678032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70f7d3b78174d39a051eed76d8320425f35b61b8e514ef8fa78ad89b56058daa
+oid sha256:5eca38b61a90273520ce4023b3b85dcc51e6f53ebe3dc341ee434151989a26ee
 size 1551478091

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbc54541e34cc6c91587f50da9686f8a5be0ae75dc1de77ad5b0281a4cac3417
+oid sha256:d11306c827003ca872f3dbb7eff94c18246ba935b4c57aadab9bda8e1ac77df7
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be40a03f70bb2a35bb567114fb5ceb05ce1222c8df24b1e1100746c617c5be10
+oid sha256:82ad8990572ad11a824b7db276c8af49c179ca7e7724b4e6906cd0ae480a80a8
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:107200a3f1a502221a7c14f8e3e5d0e068ccb8b9560c663ad037aaf4dd16cd04
+oid sha256:2253d135196644bbe0b3e20f4c763c557a93f595b853f202dd6200feeeb354db
 size 1465

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 7000,
-  "best_metric": 4.834552764892578,
-  "best_model_checkpoint": "/kaggle/working/MASRIBERTv3_ckpts/checkpoint-7000",
-  "epoch": 1.0521628020594536,
+  "best_global_step": 5000,
+  "best_metric": 5.109297752380371,
+  "best_model_checkpoint": "/kaggle/working/MASRIBERTv3_ckpts/checkpoint-5000",
+  "epoch": 0.751625389905671,
   "eval_steps": 1000,
-  "global_step": 7000,
+  "global_step": 5000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -188,78 +188,6 @@
       "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
-    },
-    {
-      "epoch": 0.9395317373820887,
-      "grad_norm": 82.08615112304688,
-      "learning_rate": 4.350034814072887e-05,
-      "loss": 41.38473828125,
-      "step": 6250
-    },
-    {
-      "epoch": 0.9771130068773723,
-      "grad_norm": 86.85932922363281,
-      "learning_rate": 4.299611001338994e-05,
-      "loss": 41.04867578125,
-      "step": 6500
-    },
-    {
-      "epoch": 1.01458153256417,
-      "grad_norm": 91.38688659667969,
-      "learning_rate": 4.2476198174524166e-05,
-      "loss": 40.55618359375,
-      "step": 6750
-    },
-    {
-      "epoch": 1.0521628020594536,
-      "grad_norm": 87.19780731201172,
-      "learning_rate": 4.194106544133346e-05,
-      "loss": 40.355609375,
-      "step": 7000
-    },
-    {
-      "epoch": 1.0521628020594536,
-      "eval_loss": 4.834552764892578,
-      "eval_runtime": 239.8672,
-      "eval_samples_per_second": 71.715,
-      "eval_steps_per_second": 1.121,
-      "step": 7000
     }
   ],
   "logging_steps": 250,
@@ -288,7 +216,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.180529011439447e+17,
+  "total_flos": 8.433343070208e+16,
   "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:efefbcb0e8b57f988b34f042db56f28887d1f06d14ec2b11a9e87dc1b7486213
 size 5201

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df50b8a580ea8526eb0730d57704938f14070df067dee66888ec8693240b765e
+oid sha256:6e506b28af94c9f67ed9877547aca9647b078ad697e757ce9d0fd58f033848a2
 size 775678032