Training in progress, step 2500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f581c2847de3076c3889d86aef0aeb31a2669f4faeee8bba43d1783b6488762
+oid sha256:548fe575ed72fd429e9fd72d2063ff329da383114295521f2d644f05dd0f118b
 size 438032472

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cf0591b6f960cff8d80c65e126222cc5d33e4ac5480d16bdde877cc65a0675f
+oid sha256:41609801c77675eff7749f85d6fa09c477b156569ed13abaa28fe2b14a39f6ee
 size 876185914

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2a1a360bd35da073058490dcfac520d1611dcc1964a4ae6df1f2feddb4ce673
+oid sha256:de5d76c4e89cee19260e89a6c72add76e5fd233fa0407a0c8086c769fbebc94b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59ca3596845b36ceb40554e9ac681b4f58ff5a427f785c30ed05587a822df839
+oid sha256:1efd8476d96a816ea45c36f3aff908881920abfb89fbb50a379d2343347897d5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.5660845637321472,
-  "best_model_checkpoint": "/kaggle/working/results/checkpoint-500",
-  "epoch": 0.03588087549336204,
+  "best_metric": 0.564910352230072,
+  "best_model_checkpoint": "/kaggle/working/results/checkpoint-2500",
+  "epoch": 0.17940437746681018,
   "eval_steps": 500,
-  "global_step": 500,
+  "global_step": 2500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -22,6 +22,66 @@
       "eval_samples_per_second": 63.677,
       "eval_steps_per_second": 0.502,
       "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
     }
   ],
   "logging_steps": 500,
@@ -41,7 +101,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4210684035072000.0,
+  "total_flos": 2.105342017536e+16,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null