Training in progress, step 400, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:684abd4d5b21391156d21c54364e2e1416d5b0e198cf472ef443d6d8678bcbe3
+oid sha256:6524a8dc8ffd44a4aad5706555682cc986cd5e794d0647846be8b48d722898bb
 size 438032472

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c69eacbc3274d5425b2c592e326a0bc50845a50d3b7e919d42e852ba0b5fbb0
+oid sha256:bb932a14fec643e7accb161576afe5656443633ddf7ba41ac67603c0dd8a9c1e
 size 876185914

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d07fe5e368968f1270424443d1b736035f0f483e173fce89646e31c44df92fb
+oid sha256:1ffb954a902be01861dce53df5b8e0e58bbd7c4238660d81e4e5352d7dbfa14c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79b960af4789495a27505e4a78b0d73b74bbb7c00968bb82429593736842d383
+oid sha256:f79448e82854dffe6b7c3a8f3de3b1b77cdf39eced0ca3f2633d3d28a7e4375e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.4317502975463867,
-  "best_model_checkpoint": "/kaggle/working/results/checkpoint-200",
-  "epoch": 0.014479113878230651,
+  "best_metric": 1.2947503328323364,
+  "best_model_checkpoint": "/kaggle/working/results/checkpoint-400",
+  "epoch": 0.028958227756461303,
   "eval_steps": 200,
-  "global_step": 200,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -15,6 +15,14 @@
       "eval_samples_per_second": 63.737,
       "eval_steps_per_second": 0.498,
       "step": 200
+    },
+    {
+      "epoch": 0.028958227756461303,
+      "eval_loss": 1.2947503328323364,
+      "eval_runtime": 122.3265,
+      "eval_samples_per_second": 63.764,
+      "eval_steps_per_second": 0.499,
+      "step": 400
     }
   ],
   "logging_steps": 500,
@@ -34,7 +42,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1684273614028800.0,
+  "total_flos": 3368547228057600.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null