Training in progress, step 2000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ce8c93031b5005ff29d0de4c4bea3ef63d7117a09f6194d706cb0d62d750608
+oid sha256:456747f9f9062a632d390b887bd07bf9bdbb14149eb73c1f8e4653a9965e56be
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82508f1ccc6ca824641932b1ce98c70060e5eca701f7217e5c8c988687f33aca
+oid sha256:4f671c6c5c8494b3e46c55e252556e8340775a3483a44f7743c6b1f9d39f546d
 size 268176506

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45c14eca485041f991017b7ed43cabab08436eb348dfcbdf38fa2fdaa2ee7b51
+oid sha256:145ba2f9dd4ec81afed9af18b40011a6f60a67d579bb7dbd4684df15787bd991
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d9a40433f0c7323dd191f89449ea6b410e3489e40240e57dfef2b5081bd1993
+oid sha256:6b383e59a1ebdc9bcae3e7149a6bf24375cdea86f20952bcbd60b95e565536d7
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcdc92d14f158bc03bfd2fd79b4acd07987b1777384730ae0e9a3dfc215701db
+oid sha256:86e8e833d541e6dd46d7f1e61b855496a085cf2d11854131ccb1e25d44309925
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af02c613a8685a26dc5a14b364cebf568fa71cd2543f760459bf3c3d0199a792
+oid sha256:cb26b1e8203066db35c249e162eec7503528d6c26174477aeef1a623dbe86327
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4437ef0bea09f93eb22ddf1af8da54ed8c2143ddb333951491c8e9d79d0e4801
+oid sha256:a8b566dcf926fa2676b4cb6372c85569269920704cd9ac2594aad37fba636c71
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.8446890115737915,
   "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-1900",
-  "epoch": 2.5435073627844713,
+  "epoch": 2.677376171352075,
   "eval_steps": 100,
-  "global_step": 1900,
+  "global_step": 2000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -292,6 +292,21 @@
       "eval_samples_per_second": 892.622,
       "eval_steps_per_second": 3.607,
       "step": 1900
+    },
+    {
+      "epoch": 2.677376171352075,
+      "grad_norm": 0.1894202083349228,
+      "learning_rate": 0.0007322623828647925,
+      "loss": 0.8463,
+      "step": 2000
+    },
+    {
+      "epoch": 2.677376171352075,
+      "eval_loss": 0.8482021689414978,
+      "eval_runtime": 6.3911,
+      "eval_samples_per_second": 890.609,
+      "eval_steps_per_second": 3.599,
+      "step": 2000
     }
   ],
   "logging_steps": 100,
@@ -306,7 +321,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -320,7 +335,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.8993314455552e+16,
+  "total_flos": 7.262454153216e+16,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null