Training in progress, step 3900, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1d5f735fc1982152b996e49d1c5f6328da127293e51ef73bceca4e1c2b1e27f
+oid sha256:738e305862686c3d72ee22dd724608c287b6f78591a8f50668a3b1a1d4f8f1f0
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2dfef2bf7d54f763d0efd5e0b9d3a27087c659b5cd7c1cfc6aa847f8c06a3018
+oid sha256:358086d4b8ebb80d8325fa8021a1f540bbfef86e93ce348b4fd0b6da5409f31b
 size 268176506

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc82e060dbeb087813f8570d4ef0d683a7cb5bc0dc56d6dc00e0c84cd7b34d06
+oid sha256:693e8accb7d153672b52d1ce8a93c52cf5633622e82005e1da0f7a8036b06b6a
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20d31eebb7ed74aa29b670f4a1178907b09cdcd684c7c072daf50f49cc9dad3b
+oid sha256:be05fc0cfe3f94e07bb2eb3ee4f8e95f1c4a90b483b506d8d0d3cc90bdbde9a5
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fa2d9146d3c80203b405802e7f42444a6a216553aa167001257311731741b78
+oid sha256:fd1a28ad120c475db877f2e4d79fbd99b3f32f6412b13f66863121037081436f
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da0c66931a0baac79fda86a1d4643855609847d8b5184185ec34959c81348839
+oid sha256:f64a2a65f7a860f03517f72544babee772014efc4e48a4ebf473421db557027a
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efaa118bc9e720a18496866cfec00973dee8a5557f3fd9597f9df5a86a299377
+oid sha256:3b7d2fadfd8b525611a599f16f2334bdd79a5d311cc5dcb4d8a12cdd4837a522
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.7916857600212097,
-  "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-3700",
-  "epoch": 5.087014725568943,
+  "best_metric": 0.7911626696586609,
+  "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-3900",
+  "epoch": 5.220883534136546,
   "eval_steps": 100,
-  "global_step": 3800,
+  "global_step": 3900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -577,6 +577,21 @@
       "eval_samples_per_second": 888.745,
       "eval_steps_per_second": 3.591,
       "step": 3800
+    },
+    {
+      "epoch": 5.220883534136546,
+      "grad_norm": 0.19813202321529388,
+      "learning_rate": 0.0004779116465863454,
+      "loss": 0.75,
+      "step": 3900
+    },
+    {
+      "epoch": 5.220883534136546,
+      "eval_loss": 0.7911626696586609,
+      "eval_runtime": 6.3995,
+      "eval_samples_per_second": 889.442,
+      "eval_steps_per_second": 3.594,
+      "step": 3900
     }
   ],
   "logging_steps": 100,
@@ -591,7 +606,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 0
       }
     },
     "TrainerControl": {
@@ -605,7 +620,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.37986628911104e+17,
+  "total_flos": 1.41617855987712e+17,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null