Training in progress, step 13500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92965ce174a5a7f2cd7cc2a9458e927278fbe87e49f06e7f80e19898f1ec8065
+oid sha256:edd68aebab71b92a6ed1b6722fe165759ebf83a538eb2271c50c9f7d34b9310a
 size 438032472

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0cedd25416214cd9a75c7b887bbb7f5f8da59d9275014384fada95a849e2376
+oid sha256:cadcda0e477d2446a66b7f972b749a231e78f5c08da90e2a860fe7f51cc5c671
 size 876185914

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d3d464249f4a39ec225bcb2a558b6eb72607957e90d74d6a2882277e87903cf
+oid sha256:f3ae56aa2daceb1c35b80f86e740f89fafa1aeedd31c9afb3852c0bad57bceb6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d9049a24c9e94cbf3030b6058909a52a72de351c864ad3381bc5ac9def102ff
+oid sha256:d894bb4a51f57aaa20006b8fe3b25869340284fd903307bc0e17589d747cb184
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.5564497113227844,
   "best_model_checkpoint": "/kaggle/working/results/checkpoint-11500",
-  "epoch": 0.8252601363473269,
+  "epoch": 0.9687836383207751,
   "eval_steps": 500,
-  "global_step": 11500,
+  "global_step": 13500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -352,6 +352,66 @@
       "eval_samples_per_second": 68.365,
       "eval_steps_per_second": 0.539,
       "step": 11500
+    },
+    {
+      "epoch": 0.8611410118406889,
+      "grad_norm": 5.504430294036865,
+      "learning_rate": 5.554359526372443e-06,
+      "loss": 0.4743,
+      "step": 12000
+    },
+    {
+      "epoch": 0.8611410118406889,
+      "eval_loss": 0.5606986284255981,
+      "eval_runtime": 152.3774,
+      "eval_samples_per_second": 68.252,
+      "eval_steps_per_second": 0.538,
+      "step": 12000
+    },
+    {
+      "epoch": 0.897021887334051,
+      "grad_norm": 4.161441326141357,
+      "learning_rate": 4.119124506637962e-06,
+      "loss": 0.4842,
+      "step": 12500
+    },
+    {
+      "epoch": 0.897021887334051,
+      "eval_loss": 0.5657362937927246,
+      "eval_runtime": 152.0558,
+      "eval_samples_per_second": 68.396,
+      "eval_steps_per_second": 0.539,
+      "step": 12500
+    },
+    {
+      "epoch": 0.932902762827413,
+      "grad_norm": 15.681989669799805,
+      "learning_rate": 2.6838894869034805e-06,
+      "loss": 0.4583,
+      "step": 13000
+    },
+    {
+      "epoch": 0.932902762827413,
+      "eval_loss": 0.5640388131141663,
+      "eval_runtime": 152.0718,
+      "eval_samples_per_second": 68.389,
+      "eval_steps_per_second": 0.539,
+      "step": 13000
+    },
+    {
+      "epoch": 0.9687836383207751,
+      "grad_norm": 6.109396934509277,
+      "learning_rate": 1.248654467168999e-06,
+      "loss": 0.4662,
+      "step": 13500
+    },
+    {
+      "epoch": 0.9687836383207751,
+      "eval_loss": 0.5629301071166992,
+      "eval_runtime": 152.1551,
+      "eval_samples_per_second": 68.351,
+      "eval_steps_per_second": 0.539,
+      "step": 13500
     }
   ],
   "logging_steps": 500,
@@ -371,7 +431,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.6845732806656e+16,
+  "total_flos": 1.13688468946944e+17,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null