Training in progress, step 2700, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16838d94768edad04519e160a50d26b25a308f1bef6f73c75c73a4e953a33dad
+oid sha256:c11959d1a54ed24e6504b3a7484ae49b10337ba2a362e5bf3855096eaa2b78b6
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf04c22e7bd4aeb40474b8c876e857ed0703db651f039235905d29ac261cff39
+oid sha256:ec4dab928a5671648f91f6edb9f9b46cddb080bf748d16e59637c5e2b1b20f6c
 size 268176506

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9fd353e5dfefc6101a83a5d98caf9c9a5705a14c0ab8ade5223b2ce5b3f0460
+oid sha256:7a4ad3f49abac91372ab22166688ad3b24262bbea19f98731b164e717c6cc735
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:223fcd89486c49e6df65821113f3a4b9aa86800e9ee923c785f21124af5e08fc
+oid sha256:d686c689b3c6a4d2b77ed6b1ef483124aa34c81c7681baf6fd79cefe4b25eb50
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa85081c50e299ccc1c9c3813903596abe8f8c8fba7b16270e601163512ed80a
+oid sha256:fbc028578ac33bb688119670e675c9fc3875194620aade50b80dfa75e5f59e02
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebbb62282efa748ff5d8a9552b46ba05c50b2d92255f80816616d6608479a3d2
+oid sha256:916622e8111782ccd0b9437c72abd974013c58a4fc1744fb22eb33803158a1f3
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3649421385e1a24ace04961edc12c9bf862a555cae6bc8873a6c17202a59515f
+oid sha256:bbe0a9ed9e12f4fdfd9ffe0c1e4f6a485f29e209889bc15dc3cbaaec66e1d5d9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.8202800750732422,
   "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-2600",
-  "epoch": 3.480589022757697,
+  "epoch": 3.6144578313253013,
   "eval_steps": 100,
-  "global_step": 2600,
+  "global_step": 2700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -397,6 +397,21 @@
       "eval_samples_per_second": 896.32,
       "eval_steps_per_second": 3.622,
       "step": 2600
+    },
+    {
+      "epoch": 3.6144578313253013,
+      "grad_norm": 0.18545600771903992,
+      "learning_rate": 0.0006385542168674699,
+      "loss": 0.8071,
+      "step": 2700
+    },
+    {
+      "epoch": 3.6144578313253013,
+      "eval_loss": 0.8289027214050293,
+      "eval_runtime": 6.4542,
+      "eval_samples_per_second": 881.901,
+      "eval_steps_per_second": 3.564,
+      "step": 2700
     }
   ],
   "logging_steps": 100,
@@ -411,7 +426,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -425,7 +440,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.4411903991808e+16,
+  "total_flos": 9.8043131068416e+16,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null