Training in progress, step 200, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cd9a570af82105305cf26766d7851aa7b4e32c4acb1dcdebd64cd9be4301098
+oid sha256:db757bc3775ce2b22261275c3c067a5f29c74aa7c3fe5bbd75b4ae2cd72d5701
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1eda6ad8e7e768db6abb9e04b52a008b2ecbe0f771c73b2c2ef7955c8d156e46
+oid sha256:4ae2a3833b0f0747b6d7320f475c3dc27198cfa0bb3cb5b818b178baded93b48
 size 268176506

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ad6436ce5e8229a5c4ab20ebe8cb7f55bf37abeb42cc6031740224925ccece0
+oid sha256:6242d91b23d26aaf36eff89477251a99db12b884840e91018a4334bd9fde5610
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30ce71d1ff265e905b2803194965013784a4a1c2ebcd76de912d912dd5430327
+oid sha256:a5e22b2a2843ce706fbf823b6124dbe8ac9013ba578730467f535c1093539a53
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac4ea73b7e3e12f80c898b525181786b56f8cafbf02cf3e2661eb5c2237f1786
+oid sha256:f1b82fcc60f09c292335cf857fb27c07cde649312ad30b4eb7d0dce1131d1d5e
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df5ac7dd4844d948bc63bc160ee8e329c029b596511f3d1234b31a48caf5cc47
+oid sha256:73784ba49228f3808b2d8c3413a07d9f0d06397abba4a302454586636be59647
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf0d25366e7e2e728cd627802a5543527b6178cf70866baa22ea5a7d28baa2af
+oid sha256:c409ef2722f271c561931fe81937589049d3a4d4409ff868699b6a54fced761c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.1609667539596558,
-  "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-100",
-  "epoch": 0.13386880856760375,
+  "best_metric": 1.0809524059295654,
+  "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-200",
+  "epoch": 0.2677376171352075,
   "eval_steps": 100,
-  "global_step": 100,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -22,6 +22,21 @@
       "eval_samples_per_second": 894.697,
       "eval_steps_per_second": 3.615,
       "step": 100
+    },
+    {
+      "epoch": 0.2677376171352075,
+      "grad_norm": 0.24928592145442963,
+      "learning_rate": 0.0009732262382864793,
+      "loss": 1.195,
+      "step": 200
+    },
+    {
+      "epoch": 0.2677376171352075,
+      "eval_loss": 1.0809524059295654,
+      "eval_runtime": 6.3583,
+      "eval_samples_per_second": 895.204,
+      "eval_steps_per_second": 3.617,
+      "step": 200
     }
   ],
   "logging_steps": 100,
@@ -50,7 +65,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3631227076608000.0,
+  "total_flos": 7262454153216000.0,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null