Training in progress, step 800, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d057d0a1d8f925e7558f46d4a4c34b21d9b5f820bc861a769f177eb125707363
+oid sha256:57ed8507cba571672723e651b2ad2a2f4162369ef3e5f3bcef011bb02fd42532
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1ef76c368113f6301c4bb8332ea48c5ed12b1800fd070b0b1008c580f238d06
+oid sha256:df255327f8390b65bc51b95b87e6d714178d2b89f1498dc5fe13d91fe4e70f70
 size 268176506

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b5599301c205fc42e0e8135f51193ee2bebafcd1a4d6a3b4feecf007c1f1ce7
+oid sha256:11b2d09f29c19f9b835e50802bef90522f0cd424941352bab4add1b2071c9ef1
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee56eaf54c09c4358352c491f7793aa582a4a81ef64ce914f528144f64ff1abf
+oid sha256:2b858a1083e6305555ad6248393e7824f5c1494c3ae09db8d65339a34a8fa324
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6628c34d087e1fcc9fbc85a8f96f98fb8c1c91ba0c3c07cef9a263e5a226c39d
+oid sha256:0b61495d21ac3bc3f03e123369a24257a831ff25abc9dd149ee250d02589497c
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:484fc5ea1e1dac1456d9fcb86d4e4d3656366da363d8d79e384d8e30f57d0646
+oid sha256:57c12301b0341347f4468f16645e8afe020ff48eae5729a0687af53b018e61da
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:135bfd72324279412e0dde44bc412f71aa3910cd7f65679073b1ce83dead7e55
+oid sha256:d334b29ea982f165897a8bd2704fecb4ee283e4d9702b8be82a196505cc46cc9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.0223731994628906,
   "best_model_checkpoint": "mgh6/TCS_MLM_All/checkpoint-700",
-  "epoch": 6.666666666666667,
+  "epoch": 7.619047619047619,
   "eval_steps": 100,
-  "global_step": 700,
+  "global_step": 800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -112,6 +112,21 @@
       "eval_samples_per_second": 87.385,
       "eval_steps_per_second": 4.599,
       "step": 700
+    },
+    {
+      "epoch": 7.619047619047619,
+      "grad_norm": 0.20244956016540527,
+      "learning_rate": 0.0002380952380952381,
+      "loss": 1.1797,
+      "step": 800
+    },
+    {
+      "epoch": 7.619047619047619,
+      "eval_loss": 1.049731731414795,
+      "eval_runtime": 0.2231,
+      "eval_samples_per_second": 85.156,
+      "eval_steps_per_second": 4.482,
+      "step": 800
     }
   ],
   "logging_steps": 100,
@@ -126,7 +141,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -140,7 +155,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.052209059561472e+16,
+  "total_flos": 2.345381782355968e+16,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null