Training in progress, step 1400, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38b93229869fbaa7f83dc901e0f80abad3e6409191726851e0d351adbbb23289
+oid sha256:35286f85be522ab120b67ef86a9b2fea852320beeec84ecb8e980c2c25acc3dc
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:246aacfeeb41eb95982a1aa7a0c2ad30cdaac0774e9162d63f49512902035746
+oid sha256:9186371be341491f8cddef66b45c7672dd44b1d906084bbec228e7ac80cb3411
 size 268176506

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fc8ded50a2551e9c75c08b06e38e07c796d38055e9b1c4ca00d25008510b20b
+oid sha256:15433f7b2e9dde73085fab120a65bed01df370c9b02a1594a472d70068457ea5
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67da4e9db4800df6c1e9ce979d121954ce0da621dd31f9082fc18d53729e7dbe
+oid sha256:53a7daa52c58fe1fb49f677ab523d6f9e6c00f2599813aaa026fc90badc494a1
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1b9be461c679a45d0e9dc290a99f941826b96670541a646e875429ebac4b6d4
+oid sha256:70429062c9260565eaadd7c683e4ca4b0df3e30951bd8422b10d4ac7e4ffd7b8
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67d1d3fc519e236cb1a514859da17fb4101fd90584e559ef4092ff69d616f7b4
+oid sha256:ecdce592e98f25cf4a04063424668eaa8d77ff8c0a42490c9215deb661680414
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e95a306d782562de001c16fb3cdca8e82cd47595ef0f485c24a21d851800935b
+oid sha256:a3477b2d9f0cb08adf52a30b7e6192998cc41f2cc3eb4ead00d452c0bcd1756e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.8838639259338379,
-  "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-1300",
-  "epoch": 1.7402945113788486,
+  "best_metric": 0.8721866607666016,
+  "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-1400",
+  "epoch": 1.8741633199464525,
   "eval_steps": 100,
-  "global_step": 1300,
+  "global_step": 1400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -202,6 +202,21 @@
       "eval_samples_per_second": 892.596,
       "eval_steps_per_second": 3.607,
       "step": 1300
+    },
+    {
+      "epoch": 1.8741633199464525,
+      "grad_norm": 0.196046844124794,
+      "learning_rate": 0.0008125836680053548,
+      "loss": 0.8933,
+      "step": 1400
+    },
+    {
+      "epoch": 1.8741633199464525,
+      "eval_loss": 0.8721866607666016,
+      "eval_runtime": 6.3772,
+      "eval_samples_per_second": 892.551,
+      "eval_steps_per_second": 3.607,
+      "step": 1400
     }
   ],
   "logging_steps": 100,
@@ -230,7 +245,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.7205951995904e+16,
+  "total_flos": 5.0837179072512e+16,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null