Training in progress, step 5200, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42f43a47f0498ebcc1fca1385aecf88d6754f5a79846a31ae5ffcc7a965bb762
+oid sha256:2761ff572db59c5aecc26cadebe2b3c310edf9f5658935e4f8e5f076ce90c256
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e7cc7f29707dd2ad6e0f596052b19567d73a72985f9f96e6051c98e7b68484e
+oid sha256:2bed59d383288af89d4784b966e5e779104557d9a85beccf999f6b8b5bd60037
 size 268176506

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da206a62ecb726d4d9d08b729122b498506d40bd61f1cf3b358d85abe26faff6
+oid sha256:48853219c3721bfb1d8a8a72ba5ffe30f2c1ba73bc07d138a1b4a193d3afab4d
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:740677f917cc0b44daacf55a4d0b688d702cbb84e375538956a299e232c2c525
+oid sha256:4f942cf6a67d933c0b44194525e6ee82fee88e9788fcbcaca8ed48932e8f5814
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9239cd703fb2c09c1ae81a6126f897df0103303809825bcafdce13173d8bb27
+oid sha256:b80ecc72333b784c6cdf3d6b9144e0aa0d0bc25d43325b1e539b072dfd36677b
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcc83b43cba9115448342cd27740376c2eac2f3414497eb5ad5fa4bcc1e36d28
+oid sha256:2d412c9dbf728be352d15375e7d7c7252109f52d96ae6908746618d551026f8a
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a39c004fabb87004f6fa700ec70e32d89d41dc550ed41a4cdd9348c43c13c97
+oid sha256:23242f275cee508f1223f3a0ccfb8b0edebc96a11df25195045635ecb00d2687
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.7706419825553894,
   "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-5100",
-  "epoch": 6.827309236947791,
+  "epoch": 6.961178045515394,
   "eval_steps": 100,
-  "global_step": 5100,
+  "global_step": 5200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -772,6 +772,21 @@
       "eval_samples_per_second": 890.547,
       "eval_steps_per_second": 3.598,
       "step": 5100
+    },
+    {
+      "epoch": 6.961178045515394,
+      "grad_norm": 0.1983019858598709,
+      "learning_rate": 0.00030388219544846053,
+      "loss": 0.7077,
+      "step": 5200
+    },
+    {
+      "epoch": 6.961178045515394,
+      "eval_loss": 0.7824519276618958,
+      "eval_runtime": 6.3567,
+      "eval_samples_per_second": 895.429,
+      "eval_steps_per_second": 3.618,
+      "step": 5200
     }
   ],
   "logging_steps": 100,
@@ -786,7 +801,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -800,7 +815,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.85192580907008e+17,
+  "total_flos": 1.88823807983616e+17,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null