Training in progress, step 5800, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b963713c26e6a540837d4509d70d66f81e9e24308ec16d71b5d6662c7fd051d2
+oid sha256:464259aa1160c21d7be7d0281cf5d9e24fa2ada0adb8b181a451a8b08e20d13a
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6595bd2248d4977ded600f62f6d7d6763fcba678d81254c117049811d1bca329
+oid sha256:1fcc17b2a1b6bebaaa880feed9123eafc604829151cc6d7c8506bc692c9ba19c
 size 268176506

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b683fe93e06659e14c07a27acf9c77daa9ccce6805dc6d4934912532d8ca893
+oid sha256:8861626d2974eea65d9e9d45679068c8468bbcff28731312236b82396fdd1501
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b650c99e52f3a7d345f923602342fc636939e6770108043213e468229236c75
+oid sha256:0ff113b6e3a7af36c2fa1001fea1da9e7ab58959e64621c09fad4213aef23972
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c506d6c56df8eae6736b3c371165ebaccb53c63ee03a6afd543d841179e8486
+oid sha256:3c0531f0416eb655e0b86503bc22b77c870301e0053657cda1907014a7fdb5de
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad36219e25c788c02e9e91298b0c2723c0887b37c75e14504ad38b22827719b0
+oid sha256:4113b73e69e160af28faa2b395f060414c8473ba52fec1a536387e609ddc76fd
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acda5f631277da28f3059fbed5212e54672b69d0acc256aa668e57f8df64b8d5
+oid sha256:9dc30c4a8e7f8b01c931fefb09d74e5e8b79704150bb29deb3b3753ae05e1017
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.7648805975914001,
   "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-5700",
-  "epoch": 7.6305220883534135,
+  "epoch": 7.764390896921017,
   "eval_steps": 100,
-  "global_step": 5700,
+  "global_step": 5800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -862,6 +862,21 @@
       "eval_samples_per_second": 894.277,
       "eval_steps_per_second": 3.614,
       "step": 5700
+    },
+    {
+      "epoch": 7.764390896921017,
+      "grad_norm": 0.19769689440727234,
+      "learning_rate": 0.00022356091030789827,
+      "loss": 0.6921,
+      "step": 5800
+    },
+    {
+      "epoch": 7.764390896921017,
+      "eval_loss": 0.7649876475334167,
+      "eval_runtime": 6.3876,
+      "eval_samples_per_second": 891.102,
+      "eval_steps_per_second": 3.601,
+      "step": 5800
     }
   ],
   "logging_steps": 100,
@@ -876,7 +891,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -890,7 +905,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.06979943366656e+17,
+  "total_flos": 2.10611170443264e+17,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null