Training in progress, step 600, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4f0d85f152f7a9b20435d5ccab48fb0747459aa51db354acf564d76882e5d3b
+oid sha256:07133a57cd409f13f7fb70e2ecc4e17f8c76d2b2f2722a98932b07d0fb327a04
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43b25973f78ecb3b4ca2aaa7edee6fa01cfd8da42b33aafa6383a3d3e101d4b5
+oid sha256:b51da921fbe2a27efa2f149c1d3c401f04ab9871d703bcf2cd039ab8cebfbf46
 size 268176506

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c08a5cb34c401de64dba778d32fa78dcd9255740d8ef4244d3d83abdd577a6c
+oid sha256:0eafb4d32d5f97572a7dd49675823c5a05c926db2721c484333b160f1dea2f9a
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c7f8b7d21a9165b484558133d97d2a5fb9e69d201d20aa000e828dffbe9a761
+oid sha256:bc1ccb881bfc2f4da797b2ac388091a96990dd46b24d51d31e0d546218039497
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12593cadff9920330bdad68cdfa509eb07af402d9c52c60f9c7c778fe427a31f
+oid sha256:361572bb7af40a1a855f17fdc90b50fb1ec57fb0caaf012037cbeee8377a6afd
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d21ddb5bd6535f74673653b30a2265c9a54e6e793a1597367ced91cc9abfe84d
+oid sha256:976387079a97999d0b2e6e2737b6c8474786d0d94fee3c0406f13da51540af6d
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3a180613ff0d86fead4244263fb556a1d44ce96309b4d204771e05f05441faf
+oid sha256:8e66fd270fdccfe0d7203fa3bb3a0ab09d81ec8c245c1f68d396e2015484ea6d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.9832900762557983,
-  "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-500",
-  "epoch": 0.6693440428380187,
+  "best_metric": 0.9555763602256775,
+  "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-600",
+  "epoch": 0.8032128514056225,
   "eval_steps": 100,
-  "global_step": 500,
+  "global_step": 600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -82,6 +82,21 @@
       "eval_samples_per_second": 892.158,
       "eval_steps_per_second": 3.605,
       "step": 500
+    },
+    {
+      "epoch": 0.8032128514056225,
+      "grad_norm": 0.19500073790550232,
+      "learning_rate": 0.0009196787148594378,
+      "loss": 1.0145,
+      "step": 600
+    },
+    {
+      "epoch": 0.8032128514056225,
+      "eval_loss": 0.9555763602256775,
+      "eval_runtime": 6.3688,
+      "eval_samples_per_second": 893.733,
+      "eval_steps_per_second": 3.611,
+      "step": 600
     }
   ],
   "logging_steps": 100,
@@ -110,7 +125,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.815613538304e+16,
+  "total_flos": 2.1787362459648e+16,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null