Training in progress, step 3700, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae9af042b30122d511c4de856fcb639515f6f4a3c96adccdd7a6895b84625eb5
+oid sha256:e769bfc1724ed308c205a8c14b676fae0abcbd6c25becc3bfe12e722223c07cf
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8693137b3625d8191eaf09f56cc6a20deac33951f92616a9a9ff1d0bccef851f
+oid sha256:74753ec518e8d2666789da18f5c923b6bc477180e32f344e5a49afb25a6e0e8d
 size 268176506

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7a142eda4bee97f02836c75c2cea66f8d4f33d7e9be433b7ff56a4b55b578bf
+oid sha256:0ef6f32abae8765ac279f01b65645da0753bd6efe11cfd496c1755d230e06403
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a92fcdc754e0876e9404de3df54c27cb79a7c0afc847521af42ae3acfe1f7cd6
+oid sha256:f0821ee9d28fc01fbc262ed483413dc26739baf1e14fa4d0c91c7a556f900b29
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87f2fe9f360100c5123a9602f4555fd65a0fa138dde4bb977811cb5c0435ea3d
+oid sha256:5d3848ebfcaff899018cb00e793689532c0c6ee3110dd60ff1772d5938a5bbb8
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f47a3a95313e72338e0f81c77e920d1114ed4ffb8d2fd63e23d9c6025a96711
+oid sha256:50e13b7d008018a901e0404dc7c5d0954ab2a8a902f5925b2a1cf755436238ef
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2c97b5830b5d625b7756ed3a27f46a63a2eed00e33c75466ccb85b04cd34654
+oid sha256:441414a8b2ee43835af49fbc545c51f73e6eb50f2e424bb61db75a70f48a2169
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.7966070771217346,
-  "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-3500",
-  "epoch": 4.8192771084337345,
+  "best_metric": 0.7916857600212097,
+  "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-3700",
+  "epoch": 4.953145917001339,
   "eval_steps": 100,
-  "global_step": 3600,
+  "global_step": 3700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -547,6 +547,21 @@
       "eval_samples_per_second": 890.099,
       "eval_steps_per_second": 3.597,
       "step": 3600
+    },
+    {
+      "epoch": 4.953145917001339,
+      "grad_norm": 0.18897077441215515,
+      "learning_rate": 0.0005046854082998661,
+      "loss": 0.765,
+      "step": 3700
+    },
+    {
+      "epoch": 4.953145917001339,
+      "eval_loss": 0.7916857600212097,
+      "eval_runtime": 6.3763,
+      "eval_samples_per_second": 892.674,
+      "eval_steps_per_second": 3.607,
+      "step": 3700
     }
   ],
   "logging_steps": 100,
@@ -561,7 +576,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 0
       }
     },
     "TrainerControl": {
@@ -575,7 +590,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.30724174757888e+17,
+  "total_flos": 1.34355401834496e+17,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null