Training in progress, step 1900, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c402418a401fc42141bd36c0dffa61bd88beb6b7427e9148ed9c63474fc2a5ac
+oid sha256:8ce8c93031b5005ff29d0de4c4bea3ef63d7117a09f6194d706cb0d62d750608
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b47d70c5121a40ace5f4132f63b2347b6bc574cc81d2e9672dc05e87573cbff
+oid sha256:82508f1ccc6ca824641932b1ce98c70060e5eca701f7217e5c8c988687f33aca
 size 268176506

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:207cf9631a70e2d9bdd4c8684f0c2a6a015f4e6ca26d375830be22756591e8f6
+oid sha256:45c14eca485041f991017b7ed43cabab08436eb348dfcbdf38fa2fdaa2ee7b51
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2254f70c381341f3fd4305b926429e503a17d1a13bef3de88c304e9bb003e2ce
+oid sha256:1d9a40433f0c7323dd191f89449ea6b410e3489e40240e57dfef2b5081bd1993
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:955ad74908b05bc45defd26fd45cb6db6e3641bf404fef7197fc72ce7f3c47fa
+oid sha256:bcdc92d14f158bc03bfd2fd79b4acd07987b1777384730ae0e9a3dfc215701db
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a97429d67ccafa23b5c0f5e499a8e3287e73941adfdec6f30380f262e08ec04
+oid sha256:af02c613a8685a26dc5a14b364cebf568fa71cd2543f760459bf3c3d0199a792
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cdb28db4cc848685c58f731cb7fade708da32acbb2cf84bb6cb683f59d91ac5
+oid sha256:4437ef0bea09f93eb22ddf1af8da54ed8c2143ddb333951491c8e9d79d0e4801
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.8528442978858948,
-  "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-1800",
-  "epoch": 2.4096385542168672,
+  "best_metric": 0.8446890115737915,
+  "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-1900",
+  "epoch": 2.5435073627844713,
   "eval_steps": 100,
-  "global_step": 1800,
+  "global_step": 1900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -277,6 +277,21 @@
       "eval_samples_per_second": 889.806,
       "eval_steps_per_second": 3.595,
       "step": 1800
+    },
+    {
+      "epoch": 2.5435073627844713,
+      "grad_norm": 0.18157944083213806,
+      "learning_rate": 0.0007456492637215529,
+      "loss": 0.8556,
+      "step": 1900
+    },
+    {
+      "epoch": 2.5435073627844713,
+      "eval_loss": 0.8446890115737915,
+      "eval_runtime": 6.3767,
+      "eval_samples_per_second": 892.622,
+      "eval_steps_per_second": 3.607,
+      "step": 1900
     }
   ],
   "logging_steps": 100,
@@ -305,7 +320,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.5362087378944e+16,
+  "total_flos": 6.8993314455552e+16,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null