Training in progress, step 600, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6524a8dc8ffd44a4aad5706555682cc986cd5e794d0647846be8b48d722898bb
+oid sha256:77bb905d9236e55a1c8048367641832d0432d5423ec7cf04357b1b736054ee1a
 size 438032472

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb932a14fec643e7accb161576afe5656443633ddf7ba41ac67603c0dd8a9c1e
+oid sha256:14512c44f1f37bd3c3d83693760eaaaba30f33ea26360258c85a62aec0a0ca30
 size 876185914

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ffb954a902be01861dce53df5b8e0e58bbd7c4238660d81e4e5352d7dbfa14c
+oid sha256:a703767195d880aff1d5c2dbc4d23286715c3798d1940a8fd2720bd4a5a675ff
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f79448e82854dffe6b7c3a8f3de3b1b77cdf39eced0ca3f2633d3d28a7e4375e
+oid sha256:51bb83752794024a27eef10009054d3313b178287743eebf62418a466a4bf8b4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2947503328323364,
-  "best_model_checkpoint": "/kaggle/working/results/checkpoint-400",
-  "epoch": 0.028958227756461303,
+  "best_metric": 1.2087372541427612,
+  "best_model_checkpoint": "/kaggle/working/results/checkpoint-600",
+  "epoch": 0.043437341634691956,
   "eval_steps": 200,
-  "global_step": 400,
+  "global_step": 600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -23,6 +23,21 @@
       "eval_samples_per_second": 63.764,
       "eval_steps_per_second": 0.499,
       "step": 400
+    },
+    {
+      "epoch": 0.03619778469557663,
+      "grad_norm": 10.083489418029785,
+      "learning_rate": 0.00019276044306088468,
+      "loss": 1.6511,
+      "step": 500
+    },
+    {
+      "epoch": 0.043437341634691956,
+      "eval_loss": 1.2087372541427612,
+      "eval_runtime": 122.3404,
+      "eval_samples_per_second": 63.757,
+      "eval_steps_per_second": 0.499,
+      "step": 600
     }
   ],
   "logging_steps": 500,
@@ -42,7 +57,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3368547228057600.0,
+  "total_flos": 5052820842086400.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null