Training in progress, step 600, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85c5220f3838d461579a307f9cba6f7754614da9f06d2afb5fe0eadc48fce33c
+oid sha256:fc191803cd0e53be77c2dba2b0d597f90a12f2e582c0a194c3dc3a33d16375c1
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e780a9139cdfd95852a5a3519a0e03f2c1b6390678ead1ec676113c4e67654d
+oid sha256:7aa0f2e56e087014b3024e59242f999df31bb9ec854960102dee184fb81de8eb
 size 268176506

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3994f932662b0038291cefc18a6133374272417b603fc4bcda9e4dc677bc51e
+oid sha256:11465cf536e83fdad93931dcb6689da9268f72da3bfe23713c9605230238e759
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f20c3d85c84442524862c494037ef3594faf69a20d2a98864dae3e5231d9b9b
+oid sha256:8a1e738055e8bc0ebf68a93d55511ca26bd12dd7297a12608356f1b695a95f64
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.1977550983428955,
-  "best_model_checkpoint": "mgh6/TCS_MLM_50/checkpoint-500",
-  "epoch": 0.14513788098693758,
+  "best_metric": 1.1928865909576416,
+  "best_model_checkpoint": "mgh6/TCS_MLM_50/checkpoint-600",
+  "epoch": 0.1741654571843251,
   "eval_steps": 100,
-  "global_step": 500,
+  "global_step": 600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -82,6 +82,21 @@
       "eval_samples_per_second": 213.403,
       "eval_steps_per_second": 3.335,
       "step": 500
+    },
+    {
+      "epoch": 0.1741654571843251,
+      "grad_norm": 0.5023015141487122,
+      "learning_rate": 0.0009825834542815674,
+      "loss": 2.526,
+      "step": 600
+    },
+    {
+      "epoch": 0.1741654571843251,
+      "eval_loss": 1.1928865909576416,
+      "eval_runtime": 213.533,
+      "eval_samples_per_second": 213.077,
+      "eval_steps_per_second": 3.33,
+      "step": 600
     }
   ],
   "logging_steps": 100,
@@ -110,7 +125,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5001938038947840.0,
+  "total_flos": 6002325646737408.0,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null