Training in progress, step 600, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bba9b4836d639104335717cb80ac797972d0b1666c9c1c4b4edf83167131dfd0
+oid sha256:3a945eaf84ac4c6e0b5b83544c0b4d47c7a5891bb7e8b3093fc6e33ced8e5f40
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc218ed8be015b5c9fff7834a8abbeffe48206aa027ef290843ed1eac4da8059
+oid sha256:3fd0026f0553d84240e27a4e9c9f6c9a5072e9c6302f3784b14244b339354079
 size 268176506

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abc12d6786e7dd3b7420a4b8c290b5f3a3eaf26cc0c72c3d0caec69af6f1043d
+oid sha256:ff06fe01c4139c090d0df9360b3c3845e31fa093fb76cd36c4680f43b5c19bbc
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8894673e03958a789d9433911c342c40ae473daeeb0fc900f4dba59f13c1c66
+oid sha256:1b93c3eadcb967bd6ad19f6a06de005f690fe78024193daf072549f782c0a08f
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48462d02d478582fb3a3340e2b554665bb7af4d1c98b93a0aa11f02c7c60beb4
+oid sha256:3324dff504aa7dcc0bc86c1de0a07d1a0796d6f03bbebcd354e63f2d8588a287
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6ae521876195862a7594672f9a93b6c7ff1ea7a377350fb4e8e8821ddabab2d
+oid sha256:9c5317e5ba2bb59b2cfde19c847e9fc2d4683e69a4612af553937619f5473c3b
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08f3e6fc63b0471c324d6c03bb092a04fc5e2ec5bab6eb88b30f3f90fa396adc
+oid sha256:97d1e96db72d8f4e476e889f3f48fe64370e5820cc7406f66eef791e030d45bd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.0535513162612915,
-  "best_model_checkpoint": "mgh6/TCS_MLM_All/checkpoint-500",
-  "epoch": 4.761904761904762,
+  "best_metric": 1.035285234451294,
+  "best_model_checkpoint": "mgh6/TCS_MLM_All/checkpoint-600",
+  "epoch": 5.714285714285714,
   "eval_steps": 100,
-  "global_step": 500,
+  "global_step": 600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -82,6 +82,21 @@
       "eval_samples_per_second": 87.904,
       "eval_steps_per_second": 4.627,
       "step": 500
+    },
+    {
+      "epoch": 5.714285714285714,
+      "grad_norm": 0.1662505716085434,
+      "learning_rate": 0.00042857142857142855,
+      "loss": 1.2114,
+      "step": 600
+    },
+    {
+      "epoch": 5.714285714285714,
+      "eval_loss": 1.035285234451294,
+      "eval_runtime": 0.2191,
+      "eval_samples_per_second": 86.713,
+      "eval_steps_per_second": 4.564,
+      "step": 600
     }
   ],
   "logging_steps": 100,
@@ -110,7 +125,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.46586361397248e+16,
+  "total_flos": 1.759036336766976e+16,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null