Training in progress, step 2900, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3275db1b5a86c5b6612168662974ab24ff4e50bc9e950612349082dc1a8a3b6c
+oid sha256:3b6c7aa02ad037fa96a4381728e53f0fafa1da2ed91cc0141709e2e5d71816de
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bc6f4a89efc879497b4ddc34c86aa2f054ff5129aecdbf08b02672266d3e2b5
+oid sha256:5e1a54220aec49cd2b58809e49606c8065c3219081891c3eb8bf4bd10ea3cc75
 size 268176506

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1145540475c0a4c79a3a5842268be5e5da26abd6b06f053e6694bfc0aca78085
+oid sha256:003d712eacc96db4b1e9f9ea6462638360632df8717cfc9c27e390427c420f80
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa6b8130fc275f74497f0f2c0e8985fcfbb5fad7a54468b0aad3be0404e7bd8d
+oid sha256:9a2ccaf2634d99170fe09ec7dfb2e072f998f454217effcb3bbb113c4def1ab9
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de3c1c136abbbea82ff4de4468be7f915bc5f8a9c6ad49af141dfcc308a12f8a
+oid sha256:fcf670565b7763d3a5d6cb67bcff09d4876ecb37d40e9b94a9e3a74516fda78d
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87e9cc4330de4223b102d8ccc87860ad366dd4f3aa8d42a0ea73f3e90f3d5c75
+oid sha256:c93ff9f17b794800226b76e29a2a6058e4ee03ef0750730776d2f447917682cc
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c6da0ccf2d6b10c100f0be489d4673c497f11d835893c8abee99f077fabf46c
+oid sha256:8d2ad79caa591550a772254cffcdaae56a8f2d87675bda6761552ca68d8a0bf8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.8202800750732422,
-  "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-2600",
-  "epoch": 3.748326639892905,
+  "best_metric": 0.8169597387313843,
+  "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-2900",
+  "epoch": 3.8821954484605086,
   "eval_steps": 100,
-  "global_step": 2800,
+  "global_step": 2900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -427,6 +427,21 @@
       "eval_samples_per_second": 889.945,
       "eval_steps_per_second": 3.596,
       "step": 2800
+    },
+    {
+      "epoch": 3.8821954484605086,
+      "grad_norm": 0.22407300770282745,
+      "learning_rate": 0.0006117804551539491,
+      "loss": 0.7964,
+      "step": 2900
+    },
+    {
+      "epoch": 3.8821954484605086,
+      "eval_loss": 0.8169597387313843,
+      "eval_runtime": 6.4097,
+      "eval_samples_per_second": 888.036,
+      "eval_steps_per_second": 3.588,
+      "step": 2900
     }
   ],
   "logging_steps": 100,
@@ -441,7 +456,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 2
+        "early_stopping_patience_counter": 0
       }
     },
     "TrainerControl": {
@@ -455,7 +470,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.01674358145024e+17,
+  "total_flos": 1.05305585221632e+17,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null