Training in progress, step 700, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc191803cd0e53be77c2dba2b0d597f90a12f2e582c0a194c3dc3a33d16375c1
+oid sha256:c1bfe3de0e87ac55e372474748650d29469ea43618f69f4b3b1cda7a1c9e5275
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7aa0f2e56e087014b3024e59242f999df31bb9ec854960102dee184fb81de8eb
+oid sha256:57e118cafcc459602f3924757e157e3852e7caa20692d2fb027a0bb1e66ba14c
 size 268176506

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11465cf536e83fdad93931dcb6689da9268f72da3bfe23713c9605230238e759
+oid sha256:b2af69833d69f080b3cc67beaefccdeb3962ea34b1a77f84a64e357eb155a372
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a1e738055e8bc0ebf68a93d55511ca26bd12dd7297a12608356f1b695a95f64
+oid sha256:6f3f413b5f7ea3d1f3927898a7f680914683b4dac70ee76ea36b52d5795badb6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.1928865909576416,
-  "best_model_checkpoint": "mgh6/TCS_MLM_50/checkpoint-600",
-  "epoch": 0.1741654571843251,
+  "best_metric": 1.181251049041748,
+  "best_model_checkpoint": "mgh6/TCS_MLM_50/checkpoint-700",
+  "epoch": 0.20319303338171263,
   "eval_steps": 100,
-  "global_step": 600,
+  "global_step": 700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -97,6 +97,21 @@
       "eval_samples_per_second": 213.077,
       "eval_steps_per_second": 3.33,
       "step": 600
+    },
+    {
+      "epoch": 0.20319303338171263,
+      "grad_norm": 0.5164414048194885,
+      "learning_rate": 0.0009796806966618288,
+      "loss": 2.5121,
+      "step": 700
+    },
+    {
+      "epoch": 0.20319303338171263,
+      "eval_loss": 1.181251049041748,
+      "eval_runtime": 213.4132,
+      "eval_samples_per_second": 213.197,
+      "eval_steps_per_second": 3.332,
+      "step": 700
     }
   ],
   "logging_steps": 100,
@@ -125,7 +140,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6002325646737408.0,
+  "total_flos": 7002713254526976.0,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null