Training in progress, step 4000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:738e305862686c3d72ee22dd724608c287b6f78591a8f50668a3b1a1d4f8f1f0
+oid sha256:60abf88d896a194144af4d46953b60449e1221e1a95206d3184cc6888468f1b3
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:358086d4b8ebb80d8325fa8021a1f540bbfef86e93ce348b4fd0b6da5409f31b
+oid sha256:4c31c122da48d6c9c0f2cdde3c7ef9521f0fd07780cbea9911eef7d5f74b3986
 size 268176506

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:693e8accb7d153672b52d1ce8a93c52cf5633622e82005e1da0f7a8036b06b6a
+oid sha256:433c43bb530b3efe8cd31ff9a32e89904e5dd3b0867a45122f34dbefd5725c76
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be05fc0cfe3f94e07bb2eb3ee4f8e95f1c4a90b483b506d8d0d3cc90bdbde9a5
+oid sha256:964c69f61d0bbf0c796f0c2c9c9e1115ff56f13e1e7564a1b7a147cbb95abc2a
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd1a28ad120c475db877f2e4d79fbd99b3f32f6412b13f66863121037081436f
+oid sha256:1086384f9480def9ef326fcb17e1858cd985a99bbe88fa0719775b0cfbe77694
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f64a2a65f7a860f03517f72544babee772014efc4e48a4ebf473421db557027a
+oid sha256:35ff45b850b10b88d179a4b292143f4790bf179db89196535716df70aaf3df49
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b7d2fadfd8b525611a599f16f2334bdd79a5d311cc5dcb4d8a12cdd4837a522
+oid sha256:c21aa8c015b0555648fb033821c3da85b80cf68da16ae0f0aa43c78eed3bb59a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.7911626696586609,
   "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-3900",
-  "epoch": 5.220883534136546,
+  "epoch": 5.35475234270415,
   "eval_steps": 100,
-  "global_step": 3900,
+  "global_step": 4000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -592,6 +592,21 @@
       "eval_samples_per_second": 889.442,
       "eval_steps_per_second": 3.594,
       "step": 3900
+    },
+    {
+      "epoch": 5.35475234270415,
+      "grad_norm": 0.199341282248497,
+      "learning_rate": 0.000464524765729585,
+      "loss": 0.7462,
+      "step": 4000
+    },
+    {
+      "epoch": 5.35475234270415,
+      "eval_loss": 0.7948747873306274,
+      "eval_runtime": 6.3721,
+      "eval_samples_per_second": 893.27,
+      "eval_steps_per_second": 3.609,
+      "step": 4000
     }
   ],
   "logging_steps": 100,
@@ -606,7 +621,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -620,7 +635,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.41617855987712e+17,
+  "total_flos": 1.4524908306432e+17,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null