Training in progress, step 4800, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b2ebc191aabc6518793124df3ec298a1068dca6ea1077091f4ec338c4512e2e
+oid sha256:dcdef8815876651e789e32f5ba829418b53bdbe3939243812f3f736f8d8cdb6c
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da785101c78f6dba8b1d769af93c9e7addd1451bd3280b193c78ec34b8a92a2e
+oid sha256:b613bb035d70d3ea5dd71539a712ebf1251f75ba46a6b0c71d40229483d5493f
 size 268176506

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21f98b38a5644907d645ad97db8abc78adfefa25b7bb27d6365c84f993e3afd0
+oid sha256:c2c2c42416feac893f835e6829ce76ea3a625b1b8b854969739b7a81e0808468
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d438bcc44b8d54150c5792a66e3e5020186af506dfd2594179ec54fbf9e4cae
+oid sha256:cc3ea084381e50acdc6e01e417e6afeda08205af73943c00cc06c438f6132d83
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdcdbf45854e83758fb28548c63ecd326f239ee595c8bfeb7203ec3a5ea5ad7a
+oid sha256:c77695fbb03c4e55a83075b2d20bc6414bf683d62aff481dc8f99e253cab1ba8
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bf80ca3ed0ae8728cae90df90e2694d6facafbe5f1f509a5b1356858eb2c480
+oid sha256:fff0592719262f858821de597e03301f84523b5c8ca2137da9d52b7bd85f4eec
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85ab8ba4274200fbed9bf770f5d7a8007101aadb14e325d86f417f8df6b6001a
+oid sha256:a62653dc6da916bc0c8d89e707516144c0487544be3b708626da1a9bfdb05f8f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.7793735861778259,
-  "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-4600",
-  "epoch": 6.291834002677376,
+  "best_metric": 0.7769716382026672,
+  "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-4800",
+  "epoch": 6.42570281124498,
   "eval_steps": 100,
-  "global_step": 4700,
+  "global_step": 4800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -712,6 +712,21 @@
       "eval_samples_per_second": 892.303,
       "eval_steps_per_second": 3.606,
       "step": 4700
+    },
+    {
+      "epoch": 6.42570281124498,
+      "grad_norm": 0.19508065283298492,
+      "learning_rate": 0.000357429718875502,
+      "loss": 0.7196,
+      "step": 4800
+    },
+    {
+      "epoch": 6.42570281124498,
+      "eval_loss": 0.7769716382026672,
+      "eval_runtime": 6.3587,
+      "eval_samples_per_second": 895.148,
+      "eval_steps_per_second": 3.617,
+      "step": 4800
     }
   ],
   "logging_steps": 100,
@@ -726,7 +741,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 0
       }
     },
     "TrainerControl": {
@@ -740,7 +755,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.70667672600576e+17,
+  "total_flos": 1.74298899677184e+17,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null