Training in progress, step 800, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa7d297a715ed53593606619851c3ddaec99c328c13049dac1aec25894a5f7c0
+oid sha256:f449ecaea05023856701cc6a7482fc4575a7d78905c0579ac3cd784669119041
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a107b3a6c5ac6b665adcf872ffe7223db9fb47d00471ba1b3568c44f75057a26
+oid sha256:64c3cdc6de437bb4cd73d82d3785754a70052aee12cbfbea25694372cfbd99cf
 size 268176506

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22335d1afc43b18db3f4821c47fac48f2223469013cac823ac98843650719f77
+oid sha256:1a2f28005ae080d5f74ee78733fad5c069f8b08635360a4876733f9e12e33dea
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6464bc3172885ec0bd3f8c80c1c0d0a1dbea4886505e1a499c1ed9982785bee4
+oid sha256:cb645dc2e4148818e3b8abafb0475d084098a031401b3762383d7bb8284eea3a
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9e90e485aaf6343ad1bf5734ae6c75fa9e64d0e3b6234f973ab3e1fb708699a
+oid sha256:adb042206d9d129a5489fd88e856b87f650944ac6e30a8e680a63423187eafd8
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de96033abad00ff376fb78cd29d2bd5f1c16303f077ffd68d25475d1c28ac948
+oid sha256:38e70ba9ff6e871b9d42454856b4698e04796c285cbeeab7718443e202a72c0d
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22b97a6a74fd29df01e364d2801cbd13f4a5f11282c2e557f0a10ebcac32304d
+oid sha256:60f77b738f0f28a29c728f4c7ce2972e380af6a14dc67f95a2dd3348d64628be
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.9372277855873108,
-  "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-700",
-  "epoch": 0.9370816599732262,
+  "best_metric": 0.9347544312477112,
+  "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-800",
+  "epoch": 1.07095046854083,
   "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": 890.852,
       "eval_steps_per_second": 3.6,
       "step": 700
+    },
+    {
+      "epoch": 1.07095046854083,
+      "grad_norm": 0.19669267535209656,
+      "learning_rate": 0.000892904953145917,
+      "loss": 0.9746,
+      "step": 800
+    },
+    {
+      "epoch": 1.07095046854083,
+      "eval_loss": 0.9347544312477112,
+      "eval_runtime": 6.3997,
+      "eval_samples_per_second": 889.412,
+      "eval_steps_per_second": 3.594,
+      "step": 800
     }
   ],
   "logging_steps": 100,
@@ -140,7 +155,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.5418589536256e+16,
+  "total_flos": 2.9049816612864e+16,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null