Training in progress, step 3000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b6c7aa02ad037fa96a4381728e53f0fafa1da2ed91cc0141709e2e5d71816de
+oid sha256:aa4fca34cbed28dfbb1cd0b64ab6ad7ea8411ecd57025c2603e8e34d69f96efa
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e1a54220aec49cd2b58809e49606c8065c3219081891c3eb8bf4bd10ea3cc75
+oid sha256:21fd822768be183f3f21935f34b833106ba986b0c6deb53a62db58fb4544ab88
 size 268176506

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:003d712eacc96db4b1e9f9ea6462638360632df8717cfc9c27e390427c420f80
+oid sha256:9c427cc96f82888b4f5f999f54fbddd6ffd6601cc97fca9c2d0bb619f41c0d43
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a2ccaf2634d99170fe09ec7dfb2e072f998f454217effcb3bbb113c4def1ab9
+oid sha256:d629f47b012bd4716fbd06c1a801bd8338866570d3f145993b800ebbcd5f242a
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcf670565b7763d3a5d6cb67bcff09d4876ecb37d40e9b94a9e3a74516fda78d
+oid sha256:fda321a22829d039fcd566a3c7d2c1122d8fd1d3c4a3340add915e3e858c1b45
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c93ff9f17b794800226b76e29a2a6058e4ee03ef0750730776d2f447917682cc
+oid sha256:2170e2709f230c49ff410906179c868ec7a5748fcf6a0bab2da9ce8832e524f2
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d2ad79caa591550a772254cffcdaae56a8f2d87675bda6761552ca68d8a0bf8
+oid sha256:266007e2046e89dca879b11f93a11db868f0c26dc5a6e44ba8e9f335c12b6523
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.8169597387313843,
   "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-2900",
-  "epoch": 3.8821954484605086,
+  "epoch": 4.016064257028113,
   "eval_steps": 100,
-  "global_step": 2900,
+  "global_step": 3000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -442,6 +442,21 @@
       "eval_samples_per_second": 888.036,
       "eval_steps_per_second": 3.588,
       "step": 2900
+    },
+    {
+      "epoch": 4.016064257028113,
+      "grad_norm": 0.20041291415691376,
+      "learning_rate": 0.0005983935742971888,
+      "loss": 0.7909,
+      "step": 3000
+    },
+    {
+      "epoch": 4.016064257028113,
+      "eval_loss": 0.819555401802063,
+      "eval_runtime": 6.3716,
+      "eval_samples_per_second": 893.337,
+      "eval_steps_per_second": 3.61,
+      "step": 3000
     }
   ],
   "logging_steps": 100,
@@ -456,7 +471,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -470,7 +485,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.05305585221632e+17,
+  "total_flos": 1.0893681229824e+17,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null