Training in progress, step 2800, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c11959d1a54ed24e6504b3a7484ae49b10337ba2a362e5bf3855096eaa2b78b6
+oid sha256:3275db1b5a86c5b6612168662974ab24ff4e50bc9e950612349082dc1a8a3b6c
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec4dab928a5671648f91f6edb9f9b46cddb080bf748d16e59637c5e2b1b20f6c
+oid sha256:4bc6f4a89efc879497b4ddc34c86aa2f054ff5129aecdbf08b02672266d3e2b5
 size 268176506

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a4ad3f49abac91372ab22166688ad3b24262bbea19f98731b164e717c6cc735
+oid sha256:1145540475c0a4c79a3a5842268be5e5da26abd6b06f053e6694bfc0aca78085
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d686c689b3c6a4d2b77ed6b1ef483124aa34c81c7681baf6fd79cefe4b25eb50
+oid sha256:aa6b8130fc275f74497f0f2c0e8985fcfbb5fad7a54468b0aad3be0404e7bd8d
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbc028578ac33bb688119670e675c9fc3875194620aade50b80dfa75e5f59e02
+oid sha256:de3c1c136abbbea82ff4de4468be7f915bc5f8a9c6ad49af141dfcc308a12f8a
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:916622e8111782ccd0b9437c72abd974013c58a4fc1744fb22eb33803158a1f3
+oid sha256:87e9cc4330de4223b102d8ccc87860ad366dd4f3aa8d42a0ea73f3e90f3d5c75
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbe0a9ed9e12f4fdfd9ffe0c1e4f6a485f29e209889bc15dc3cbaaec66e1d5d9
+oid sha256:8c6da0ccf2d6b10c100f0be489d4673c497f11d835893c8abee99f077fabf46c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.8202800750732422,
   "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-2600",
-  "epoch": 3.6144578313253013,
+  "epoch": 3.748326639892905,
   "eval_steps": 100,
-  "global_step": 2700,
+  "global_step": 2800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -412,6 +412,21 @@
       "eval_samples_per_second": 881.901,
       "eval_steps_per_second": 3.564,
       "step": 2700
+    },
+    {
+      "epoch": 3.748326639892905,
+      "grad_norm": 0.19937384128570557,
+      "learning_rate": 0.0006251673360107095,
+      "loss": 0.8,
+      "step": 2800
+    },
+    {
+      "epoch": 3.748326639892905,
+      "eval_loss": 0.8232221007347107,
+      "eval_runtime": 6.3959,
+      "eval_samples_per_second": 889.945,
+      "eval_steps_per_second": 3.596,
+      "step": 2800
     }
   ],
   "logging_steps": 100,
@@ -426,7 +441,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 2
       }
     },
     "TrainerControl": {
@@ -440,7 +455,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.8043131068416e+16,
+  "total_flos": 1.01674358145024e+17,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null