Training in progress, step 4400, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d23141409bbb36a38c3ce6252dcd54c440951d823323c077f592e6f354d33732
+oid sha256:17354674ebfd7ee39e27d2d7c18efe07ba47500bf6960899f0eafdf72eead626
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d8a3a5334ea620d0b1aa7d05f74d5b2e45113047721b4d09e02ce2e2caca40f
+oid sha256:8ffd1ca3853498761f71027ee26ab56f29b18b7339583b6e4060a60d4b7e6d35
 size 268176506

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38679a2b5c2a15bfaedda45a175bd9dc69ff598a51cb53b08d2ee68a513aad2a
+oid sha256:b88a294175177dc754ff5113f4db5f5889ecf637e68dfb3e98c14246dd8d3714
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1470c935f1f6cd56241e6cdca8ba23824c7931ab218970a075485e3692d413b
+oid sha256:70db09ddd19e86007f322d281cc5c5f94909d942e37598ec3ceaa08be20aecba
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a3afd79a56cf15dde135418a9cc05bad23ce2f4495ba4281f7957156612fd22
+oid sha256:598c58dd54a328d92dfc9ab91d559118e55f09ef3e6d1a542d0d2ba34a4f7769
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6248feb49b80cbe7da84d4d5a5df02cdfd3c071ecca50d38f674563e33ad624
+oid sha256:1529a258db9857087589ba7d21800b6cb787f5ab31dae6d6c97ea8d5a4171643
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9db256387c89b824cc8694ccbc88b87e90fb06a8490ffefcb4a7211239aa0c26
+oid sha256:49ae85bf7a65e337693025f4ceb61bc3ab49ed353192027ce2cc225b05fa7ea5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.78049236536026,
   "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-4200",
-  "epoch": 5.756358768406961,
+  "epoch": 5.890227576974565,
   "eval_steps": 100,
-  "global_step": 4300,
+  "global_step": 4400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -652,6 +652,21 @@
       "eval_samples_per_second": 897.535,
       "eval_steps_per_second": 3.627,
       "step": 4300
+    },
+    {
+      "epoch": 5.890227576974565,
+      "grad_norm": 0.19738435745239258,
+      "learning_rate": 0.0004109772423025435,
+      "loss": 0.7339,
+      "step": 4400
+    },
+    {
+      "epoch": 5.890227576974565,
+      "eval_loss": 0.7912316918373108,
+      "eval_runtime": 6.4227,
+      "eval_samples_per_second": 886.234,
+      "eval_steps_per_second": 3.581,
+      "step": 4400
     }
   ],
   "logging_steps": 100,
@@ -666,7 +681,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 2
       }
     },
     "TrainerControl": {
@@ -680,7 +695,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.56142764294144e+17,
+  "total_flos": 1.59773991370752e+17,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null