Upload 5 files

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4f3ee24726555e5e1086c23c28334dc67c9900546d600d694f59a4bd1120eca
+size 14308

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b054a82daf1dc51ea4726a8b05eded8ded0cdd8f7d3601daf669357ade792cd5
+size 1064

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.17145082354545593,
   "best_model_checkpoint": "/kaggle/working/ckpts/checkpoint-3500",
-  "epoch": 14.969696969696969,
+  "epoch": 14.141414141414142,
   "eval_steps": 500,
-  "global_step": 3705,
+  "global_step": 3500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -315,29 +315,6 @@
       "eval_samples_per_second": 21.179,
       "eval_steps_per_second": 5.305,
       "step": 3500
-    },
-    {
-      "epoch": 14.55,
-      "grad_norm": 17.49441146850586,
-      "learning_rate": 2.968960863697706e-07,
-      "loss": 0.0978,
-      "step": 3600
-    },
-    {
-      "epoch": 14.95,
-      "grad_norm": 0.08890076726675034,
-      "learning_rate": 2.6990553306342783e-08,
-      "loss": 0.0463,
-      "step": 3700
-    },
-    {
-      "epoch": 14.97,
-      "step": 3705,
-      "total_flos": 9.492004863262944e+17,
-      "train_loss": 0.2598070231043858,
-      "train_runtime": 2003.5076,
-      "train_samples_per_second": 14.817,
-      "train_steps_per_second": 1.849
     }
   ],
   "logging_steps": 100,
@@ -345,7 +322,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 15,
   "save_steps": 500,
-  "total_flos": 9.492004863262944e+17,
+  "total_flos": 8.971183151896032e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null