Training in progress, step 3600, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08313b42957f67090aa115244b6a6aee90773239492ec422bd4cdc2a87eb25df
+oid sha256:ae9af042b30122d511c4de856fcb639515f6f4a3c96adccdd7a6895b84625eb5
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdc2214200b5403f71680f201b18760342827e59a59311c7e771aa14cee56c96
+oid sha256:8693137b3625d8191eaf09f56cc6a20deac33951f92616a9a9ff1d0bccef851f
 size 268176506

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98cfffb13124b787eca8198f34dff7a12f16b165a90f598871cb7e3ecca92324
+oid sha256:f7a142eda4bee97f02836c75c2cea66f8d4f33d7e9be433b7ff56a4b55b578bf
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2986fa958ada5477ebe88ba8fc733f923510de4a8bd10bb9807ab03964f5f1d
+oid sha256:a92fcdc754e0876e9404de3df54c27cb79a7c0afc847521af42ae3acfe1f7cd6
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb952e625e0c2be59a595bcc79e38c96d6dc8c431f14505091b0820a46236bd3
+oid sha256:87f2fe9f360100c5123a9602f4555fd65a0fa138dde4bb977811cb5c0435ea3d
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43c941a63238f94378bcb20909f17c5f59be9cb66d772ba3b2decb25abab3c48
+oid sha256:3f47a3a95313e72338e0f81c77e920d1114ed4ffb8d2fd63e23d9c6025a96711
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:721310d2981547202484da70c2e17048502375ecff14f4280996b3b5ba67e562
+oid sha256:f2c97b5830b5d625b7756ed3a27f46a63a2eed00e33c75466ccb85b04cd34654
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.7966070771217346,
   "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-3500",
-  "epoch": 4.685408299866131,
+  "epoch": 4.8192771084337345,
   "eval_steps": 100,
-  "global_step": 3500,
+  "global_step": 3600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -532,6 +532,21 @@
       "eval_samples_per_second": 894.984,
       "eval_steps_per_second": 3.616,
       "step": 3500
+    },
+    {
+      "epoch": 4.8192771084337345,
+      "grad_norm": 0.19489823281764984,
+      "learning_rate": 0.0005180722891566265,
+      "loss": 0.768,
+      "step": 3600
+    },
+    {
+      "epoch": 4.8192771084337345,
+      "eval_loss": 0.800128698348999,
+      "eval_runtime": 6.3948,
+      "eval_samples_per_second": 890.099,
+      "eval_steps_per_second": 3.597,
+      "step": 3600
     }
   ],
   "logging_steps": 100,
@@ -546,7 +561,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -560,7 +575,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2709294768128e+17,
+  "total_flos": 1.30724174757888e+17,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null