Training in progress, step 500, checkpoint

last-checkpoint/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "biggy-smiley/bert-base-uncased-fibe-v1",
+  "_name_or_path": "biggy-smiley/bert-base-uncased-fibe-v2",
   "architectures": [
     "BertForSequenceClassification"
   ],

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2004ebbab03de74d00c60e27573907a37373fc0055ecb5c433827b13812ce0ed
+oid sha256:30a7148af1b2c111e9a3bb314228e73eb5195ee5f22f77fbde2824a584b8cb1d
 size 438032472

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6458c45bb22e19e9697b93fdf578d5b1611dd3db0c74d9ad1f2cf8625ef5be48
+oid sha256:eca7587deedabd245a1bbc4fbaa8399f189705649a6032380499cb578acd7e1d
 size 876185914

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6b9361df27a0d1575bc9d13b96c3afa7adc7c7aa5590196bb3a80cbc6d4fe17
+oid sha256:0bcc01bf3ed855f7704cc44c730c23da8b2c5cbdb141fc38bacc6e369f90c912
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c049b2e3ea1cce3b5a07099de3f2a7712b4074618db3d2296051173e338de365
+oid sha256:59ca3596845b36ceb40554e9ac681b4f58ff5a427f785c30ed05587a822df839
 size 1064

last-checkpoint/trainer_state.json

@@ -1,102 +1,27 @@
 {
-  "best_metric": 0.5547525882720947,
-  "best_model_checkpoint": "/kaggle/working/results/checkpoint-3000",
-  "epoch": 0.21528525296017223,
+  "best_metric": 0.7613404989242554,
+  "best_model_checkpoint": "/kaggle/working/results/checkpoint-500",
+  "epoch": 0.03588087549336204,
   "eval_steps": 500,
-  "global_step": 3000,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.03588087549336204,
-      "grad_norm": 5.634653091430664,
+      "grad_norm": 5.043849468231201,
       "learning_rate": 3.856476498026552e-05,
-      "loss": 0.5127,
+      "loss": 0.3432,
       "step": 500
     },
     {
       "epoch": 0.03588087549336204,
-      "eval_loss": 0.5660845637321472,
-      "eval_runtime": 163.3238,
-      "eval_samples_per_second": 63.677,
-      "eval_steps_per_second": 0.502,
+      "eval_loss": 0.7613404989242554,
+      "eval_runtime": 151.9935,
+      "eval_samples_per_second": 68.424,
+      "eval_steps_per_second": 0.539,
       "step": 500
-    },
-    {
-      "epoch": 0.07176175098672408,
-      "grad_norm": 5.935914516448975,
-      "learning_rate": 3.7129529960531036e-05,
-      "loss": 0.5172,
-      "step": 1000
-    },
-    {
-      "epoch": 0.07176175098672408,
-      "eval_loss": 0.5715007781982422,
-      "eval_runtime": 162.9037,
-      "eval_samples_per_second": 63.841,
-      "eval_steps_per_second": 0.503,
-      "step": 1000
-    },
-    {
-      "epoch": 0.10764262648008611,
-      "grad_norm": 10.494462966918945,
-      "learning_rate": 3.569429494079656e-05,
-      "loss": 0.5146,
-      "step": 1500
-    },
-    {
-      "epoch": 0.10764262648008611,
-      "eval_loss": 0.6872914433479309,
-      "eval_runtime": 162.5808,
-      "eval_samples_per_second": 63.968,
-      "eval_steps_per_second": 0.504,
-      "step": 1500
-    },
-    {
-      "epoch": 0.14352350197344815,
-      "grad_norm": 7.07112979888916,
-      "learning_rate": 3.425905992106208e-05,
-      "loss": 0.5173,
-      "step": 2000
-    },
-    {
-      "epoch": 0.14352350197344815,
-      "eval_loss": 0.5986515283584595,
-      "eval_runtime": 162.9374,
-      "eval_samples_per_second": 63.828,
-      "eval_steps_per_second": 0.503,
-      "step": 2000
-    },
-    {
-      "epoch": 0.17940437746681018,
-      "grad_norm": 5.930263042449951,
-      "learning_rate": 3.28238249013276e-05,
-      "loss": 0.5222,
-      "step": 2500
-    },
-    {
-      "epoch": 0.17940437746681018,
-      "eval_loss": 0.564910352230072,
-      "eval_runtime": 162.9111,
-      "eval_samples_per_second": 63.839,
-      "eval_steps_per_second": 0.503,
-      "step": 2500
-    },
-    {
-      "epoch": 0.21528525296017223,
-      "grad_norm": 3.9764771461486816,
-      "learning_rate": 3.1388589881593114e-05,
-      "loss": 0.5103,
-      "step": 3000
-    },
-    {
-      "epoch": 0.21528525296017223,
-      "eval_loss": 0.5547525882720947,
-      "eval_runtime": 162.9245,
-      "eval_samples_per_second": 63.833,
-      "eval_steps_per_second": 0.503,
-      "step": 3000
     }
   ],
   "logging_steps": 500,
@@ -116,7 +41,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.5264104210432e+16,
+  "total_flos": 4210684035072000.0,
   "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 sha256:024404cab287149bf244ccc23f601abbe7bc7e89069fc8b56dff5b18ec2e7ebe
+oid sha256:97df412f733e7b3de5ed3af702cb7e80553e26b0f47356c4f1b0fb309bee1536
 size 5240