Training in progress, step 500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7633ad3e063cb428a0b8188912a6c200fed276f3ac3958cb073af61a7af3b6e
+oid sha256:bba9b4836d639104335717cb80ac797972d0b1666c9c1c4b4edf83167131dfd0
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27143edcddc7e4bb7d8afa4ad94874a2e2b960a13504529dd2d4838332938619
+oid sha256:dc218ed8be015b5c9fff7834a8abbeffe48206aa027ef290843ed1eac4da8059
 size 268176506

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:778326eea75bceb231d76d4240266406ce58200b0ab03f90cf031acbe9d10c9b
+oid sha256:abc12d6786e7dd3b7420a4b8c290b5f3a3eaf26cc0c72c3d0caec69af6f1043d
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89c94a0c557709e37ca8b5be98f902c3c5b689c111517a992bd8c6198bc0a13b
+oid sha256:c8894673e03958a789d9433911c342c40ae473daeeb0fc900f4dba59f13c1c66
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8441d9b4dfab33943d5c16fa962c16bea0a6d9e292d0fc439720612487ca5895
+oid sha256:48462d02d478582fb3a3340e2b554665bb7af4d1c98b93a0aa11f02c7c60beb4
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa59e55205aedcec55695be0e324d9123d7e7aaffc98fdd62cc6a7fe21771b1f
+oid sha256:f6ae521876195862a7594672f9a93b6c7ff1ea7a377350fb4e8e8821ddabab2d
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8497e2283a464062b42ac5a931608c0c03aeed3224f849e0bfe9c9ea0a315a8f
+oid sha256:08f3e6fc63b0471c324d6c03bb092a04fc5e2ec5bab6eb88b30f3f90fa396adc
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.1724227666854858,
-  "best_model_checkpoint": "mgh6/TCS_MLM_All/checkpoint-300",
-  "epoch": 3.8095238095238093,
+  "best_metric": 1.0535513162612915,
+  "best_model_checkpoint": "mgh6/TCS_MLM_All/checkpoint-500",
+  "epoch": 4.761904761904762,
   "eval_steps": 100,
-  "global_step": 400,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -67,6 +67,21 @@
       "eval_samples_per_second": 86.925,
       "eval_steps_per_second": 4.575,
       "step": 400
+    },
+    {
+      "epoch": 4.761904761904762,
+      "grad_norm": 0.18052713572978973,
+      "learning_rate": 0.0005238095238095238,
+      "loss": 1.235,
+      "step": 500
+    },
+    {
+      "epoch": 4.761904761904762,
+      "eval_loss": 1.0535513162612915,
+      "eval_runtime": 0.2161,
+      "eval_samples_per_second": 87.904,
+      "eval_steps_per_second": 4.627,
+      "step": 500
     }
   ],
   "logging_steps": 100,
@@ -81,7 +96,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 0
       }
     },
     "TrainerControl": {
@@ -95,7 +110,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.172690891177984e+16,
+  "total_flos": 1.46586361397248e+16,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null