Training in progress, step 6500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba67af77e590add1234ed9e6707c3290aff04c26a766ec648f4300588e0afe16
+oid sha256:607db0aaa8aec5e0c77d2ae44dc9557d7f988e24abbaafafb4f1cac3b2f705c1
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbe63bd17935f5a39a7f184f7d8114197718b8cbb65f4193ecb4011c7d3b4022
+oid sha256:ec9a254aabc26c9ecaf2cca002ad97ad758900e1f80c8fe6c553cb0486cd0cbe
 size 268176506

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3da06ea7fd1000116d22b485aedad0cad93b28290b3d5dbb3f366fd88b44390
+oid sha256:25f76838f8e3a157a00d912b4db2e3d23619e7a0258f470c79764f0201444368
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49ea0a73b6835eaf0ddaf0b8b30c4d80570d58f4c008d678e3873e2b2b06348e
+oid sha256:531bda37c4200f52a8cc18f945f8530ba4b8f333e7e166099701e69c6e3dab0f
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:895fc1f187ec064c8fbc6029dd7b1972f6a6c4742fc4d164dd5488f493b85c4d
+oid sha256:9e10dda7822ada68460df36e65fcda5e475c2ef0ad7968e70f7057f87ffe1360
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d5acff08e0047885af8ddd8c4e0c85f4e5ecff94472442c3435d42f29f06dc6
+oid sha256:870b1b4c249a2b7e5c44fcd3356decbda105298b8a1839f4d0cfae2d944ee375
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0738fae84b946e365269b38dfada90de3b34d88297d57fd448fba6217d237f7f
+oid sha256:d317150b0d3412b691ca8098a37f80eb1b7190219c8c4e550a8598f46571a60c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.7565015554428101,
-  "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-6300",
-  "epoch": 8.56760374832664,
+  "best_metric": 0.7487396597862244,
+  "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-6500",
+  "epoch": 8.701472556894243,
   "eval_steps": 100,
-  "global_step": 6400,
+  "global_step": 6500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -967,6 +967,21 @@
       "eval_samples_per_second": 888.342,
       "eval_steps_per_second": 3.59,
       "step": 6400
+    },
+    {
+      "epoch": 8.701472556894243,
+      "grad_norm": 0.20278280973434448,
+      "learning_rate": 0.00012985274431057565,
+      "loss": 0.6707,
+      "step": 6500
+    },
+    {
+      "epoch": 8.701472556894243,
+      "eval_loss": 0.7487396597862244,
+      "eval_runtime": 6.3846,
+      "eval_samples_per_second": 891.523,
+      "eval_steps_per_second": 3.602,
+      "step": 6500
     }
   ],
   "logging_steps": 100,
@@ -981,7 +996,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 0
       }
     },
     "TrainerControl": {
@@ -995,7 +1010,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.32398532902912e+17,
+  "total_flos": 2.3602975997952e+17,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null