Training in progress, step 700, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07133a57cd409f13f7fb70e2ecc4e17f8c76d2b2f2722a98932b07d0fb327a04
+oid sha256:fa7d297a715ed53593606619851c3ddaec99c328c13049dac1aec25894a5f7c0
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b51da921fbe2a27efa2f149c1d3c401f04ab9871d703bcf2cd039ab8cebfbf46
+oid sha256:a107b3a6c5ac6b665adcf872ffe7223db9fb47d00471ba1b3568c44f75057a26
 size 268176506

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0eafb4d32d5f97572a7dd49675823c5a05c926db2721c484333b160f1dea2f9a
+oid sha256:22335d1afc43b18db3f4821c47fac48f2223469013cac823ac98843650719f77
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc1ccb881bfc2f4da797b2ac388091a96990dd46b24d51d31e0d546218039497
+oid sha256:6464bc3172885ec0bd3f8c80c1c0d0a1dbea4886505e1a499c1ed9982785bee4
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:361572bb7af40a1a855f17fdc90b50fb1ec57fb0caaf012037cbeee8377a6afd
+oid sha256:b9e90e485aaf6343ad1bf5734ae6c75fa9e64d0e3b6234f973ab3e1fb708699a
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:976387079a97999d0b2e6e2737b6c8474786d0d94fee3c0406f13da51540af6d
+oid sha256:de96033abad00ff376fb78cd29d2bd5f1c16303f077ffd68d25475d1c28ac948
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e66fd270fdccfe0d7203fa3bb3a0ab09d81ec8c245c1f68d396e2015484ea6d
+oid sha256:22b97a6a74fd29df01e364d2801cbd13f4a5f11282c2e557f0a10ebcac32304d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.9555763602256775,
-  "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-600",
-  "epoch": 0.8032128514056225,
+  "best_metric": 0.9372277855873108,
+  "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-700",
+  "epoch": 0.9370816599732262,
   "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": 893.733,
       "eval_steps_per_second": 3.611,
       "step": 600
+    },
+    {
+      "epoch": 0.9370816599732262,
+      "grad_norm": 0.21632438898086548,
+      "learning_rate": 0.0009062918340026773,
+      "loss": 0.9922,
+      "step": 700
+    },
+    {
+      "epoch": 0.9370816599732262,
+      "eval_loss": 0.9372277855873108,
+      "eval_runtime": 6.3894,
+      "eval_samples_per_second": 890.852,
+      "eval_steps_per_second": 3.6,
+      "step": 700
     }
   ],
   "logging_steps": 100,
@@ -125,7 +140,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.1787362459648e+16,
+  "total_flos": 2.5418589536256e+16,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null