Training in progress, step 5300, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2761ff572db59c5aecc26cadebe2b3c310edf9f5658935e4f8e5f076ce90c256
+oid sha256:48512a617ecc29150b3fcffc3bac9271f2eda18eca4cee93e9e28f3c59f3c029
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2bed59d383288af89d4784b966e5e779104557d9a85beccf999f6b8b5bd60037
+oid sha256:743feb1efb1570c9ec8c4ef71f43c7975a5fe72147038b7cf83ee6fe0eedf3aa
 size 268176506

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48853219c3721bfb1d8a8a72ba5ffe30f2c1ba73bc07d138a1b4a193d3afab4d
+oid sha256:8226358c0f700bb53afaf3faa43d9a6777fe792182c7a0d8c41428742fabc93e
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f942cf6a67d933c0b44194525e6ee82fee88e9788fcbcaca8ed48932e8f5814
+oid sha256:e1ea7dbc1c07cc0ee1e9a988b533591fbe9d67d89330e265a709f3e1f3bdef37
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b80ecc72333b784c6cdf3d6b9144e0aa0d0bc25d43325b1e539b072dfd36677b
+oid sha256:46fd91a40094f0ed12960b9a22012adeee1744512dd947ed5b7be5481bdd5925
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d412c9dbf728be352d15375e7d7c7252109f52d96ae6908746618d551026f8a
+oid sha256:585c063c64e11f9c35800000b730bf431ff5b1b49d2de618e99ffd81b58444ba
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23242f275cee508f1223f3a0ccfb8b0edebc96a11df25195045635ecb00d2687
+oid sha256:4e58b1bb199274c073865174a1d6bddf72f0586f5c109844e3442547260217dd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.7706419825553894,
   "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-5100",
-  "epoch": 6.961178045515394,
+  "epoch": 7.095046854082999,
   "eval_steps": 100,
-  "global_step": 5200,
+  "global_step": 5300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -787,6 +787,21 @@
       "eval_samples_per_second": 895.429,
       "eval_steps_per_second": 3.618,
       "step": 5200
+    },
+    {
+      "epoch": 7.095046854082999,
+      "grad_norm": 0.19971829652786255,
+      "learning_rate": 0.0002904953145917001,
+      "loss": 0.6997,
+      "step": 5300
+    },
+    {
+      "epoch": 7.095046854082999,
+      "eval_loss": 0.7725899815559387,
+      "eval_runtime": 6.3729,
+      "eval_samples_per_second": 893.153,
+      "eval_steps_per_second": 3.609,
+      "step": 5300
     }
   ],
   "logging_steps": 100,
@@ -801,7 +816,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 2
       }
     },
     "TrainerControl": {
@@ -815,7 +830,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.88823807983616e+17,
+  "total_flos": 1.92455035060224e+17,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null