Training in progress, step 800, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1bfe3de0e87ac55e372474748650d29469ea43618f69f4b3b1cda7a1c9e5275
+oid sha256:47630d4c3006b50921d7e36c744d50be38e8879aea194e330ca9b15f1daaafd3
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57e118cafcc459602f3924757e157e3852e7caa20692d2fb027a0bb1e66ba14c
+oid sha256:697d38dc27773b03d627eaea47fe209ad4c1e9a4073dc7b3d8e4eec46920a338
 size 268176506

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2af69833d69f080b3cc67beaefccdeb3962ea34b1a77f84a64e357eb155a372
+oid sha256:d27635aa3bf8c9513bde838cce12dd861db1a571c559e6e3d3706dff45fc7a8d
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f3f413b5f7ea3d1f3927898a7f680914683b4dac70ee76ea36b52d5795badb6
+oid sha256:c95b96648dba4a14572860ec64f84946a5310ebc9249f9d3352c1018256aeef8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.181251049041748,
-  "best_model_checkpoint": "mgh6/TCS_MLM_50/checkpoint-700",
-  "epoch": 0.20319303338171263,
+  "best_metric": 1.1703433990478516,
+  "best_model_checkpoint": "mgh6/TCS_MLM_50/checkpoint-800",
+  "epoch": 0.23222060957910015,
   "eval_steps": 100,
-  "global_step": 700,
+  "global_step": 800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -112,6 +112,21 @@
       "eval_samples_per_second": 213.197,
       "eval_steps_per_second": 3.332,
       "step": 700
+    },
+    {
+      "epoch": 0.23222060957910015,
+      "grad_norm": 0.535000205039978,
+      "learning_rate": 0.00097677793904209,
+      "loss": 2.456,
+      "step": 800
+    },
+    {
+      "epoch": 0.23222060957910015,
+      "eval_loss": 1.1703433990478516,
+      "eval_runtime": 213.4281,
+      "eval_samples_per_second": 213.182,
+      "eval_steps_per_second": 3.331,
+      "step": 800
     }
   ],
   "logging_steps": 100,
@@ -140,7 +155,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7002713254526976.0,
+  "total_flos": 8003100862316544.0,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null