Training in progress, step 700, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a945eaf84ac4c6e0b5b83544c0b4d47c7a5891bb7e8b3093fc6e33ced8e5f40
+oid sha256:d057d0a1d8f925e7558f46d4a4c34b21d9b5f820bc861a769f177eb125707363
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fd0026f0553d84240e27a4e9c9f6c9a5072e9c6302f3784b14244b339354079
+oid sha256:c1ef76c368113f6301c4bb8332ea48c5ed12b1800fd070b0b1008c580f238d06
 size 268176506

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff06fe01c4139c090d0df9360b3c3845e31fa093fb76cd36c4680f43b5c19bbc
+oid sha256:6b5599301c205fc42e0e8135f51193ee2bebafcd1a4d6a3b4feecf007c1f1ce7
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b93c3eadcb967bd6ad19f6a06de005f690fe78024193daf072549f782c0a08f
+oid sha256:ee56eaf54c09c4358352c491f7793aa582a4a81ef64ce914f528144f64ff1abf
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3324dff504aa7dcc0bc86c1de0a07d1a0796d6f03bbebcd354e63f2d8588a287
+oid sha256:6628c34d087e1fcc9fbc85a8f96f98fb8c1c91ba0c3c07cef9a263e5a226c39d
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c5317e5ba2bb59b2cfde19c847e9fc2d4683e69a4612af553937619f5473c3b
+oid sha256:484fc5ea1e1dac1456d9fcb86d4e4d3656366da363d8d79e384d8e30f57d0646
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97d1e96db72d8f4e476e889f3f48fe64370e5820cc7406f66eef791e030d45bd
+oid sha256:135bfd72324279412e0dde44bc412f71aa3910cd7f65679073b1ce83dead7e55
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.035285234451294,
-  "best_model_checkpoint": "mgh6/TCS_MLM_All/checkpoint-600",
-  "epoch": 5.714285714285714,
+  "best_metric": 1.0223731994628906,
+  "best_model_checkpoint": "mgh6/TCS_MLM_All/checkpoint-700",
+  "epoch": 6.666666666666667,
   "eval_steps": 100,
-  "global_step": 600,
+  "global_step": 700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -97,6 +97,21 @@
       "eval_samples_per_second": 86.713,
       "eval_steps_per_second": 4.564,
       "step": 600
+    },
+    {
+      "epoch": 6.666666666666667,
+      "grad_norm": 0.16807609796524048,
+      "learning_rate": 0.0003333333333333333,
+      "loss": 1.1944,
+      "step": 700
+    },
+    {
+      "epoch": 6.666666666666667,
+      "eval_loss": 1.0223731994628906,
+      "eval_runtime": 0.2174,
+      "eval_samples_per_second": 87.385,
+      "eval_steps_per_second": 4.599,
+      "step": 700
     }
   ],
   "logging_steps": 100,
@@ -125,7 +140,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.759036336766976e+16,
+  "total_flos": 2.052209059561472e+16,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null