Training in progress, step 500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3f27c55a6b7ff26add6ca12b66b08a03938a5264d91f6c3c0858e7cc44a0885
+oid sha256:e4f0d85f152f7a9b20435d5ccab48fb0747459aa51db354acf564d76882e5d3b
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd3528c3f2886f6a6ff39794da95c97e7e9168c462ba99a0aacb9a5f7e0ee006
+oid sha256:43b25973f78ecb3b4ca2aaa7edee6fa01cfd8da42b33aafa6383a3d3e101d4b5
 size 268176506

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36205505ff7c8f39e1e4c85b6853d46fb51500bf0f06c3d0a59c07012b9a9832
+oid sha256:6c08a5cb34c401de64dba778d32fa78dcd9255740d8ef4244d3d83abdd577a6c
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6477b3da99bdcdb3a930c7bf415bba4680e36c852eb3e5e5f110e648f5923ebb
+oid sha256:6c7f8b7d21a9165b484558133d97d2a5fb9e69d201d20aa000e828dffbe9a761
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:196f2299243dc0bc367db6f89dcd8263fed09436b97fc4aea1759596eb3a66c3
+oid sha256:12593cadff9920330bdad68cdfa509eb07af402d9c52c60f9c7c778fe427a31f
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c9840f31cf2ea0e1349fc2944a1471b0767f445ae4b9229fa04546cbf3a99e9
+oid sha256:d21ddb5bd6535f74673653b30a2265c9a54e6e793a1597367ced91cc9abfe84d
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c58c1cd6178c8f979902cb0d2a83ba9e449411fde4b3ef37d83085a443371c56
+oid sha256:e3a180613ff0d86fead4244263fb556a1d44ce96309b4d204771e05f05441faf
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.0003758668899536,
-  "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-400",
-  "epoch": 0.535475234270415,
+  "best_metric": 0.9832900762557983,
+  "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-500",
+  "epoch": 0.6693440428380187,
   "eval_steps": 100,
-  "global_step": 400,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -67,6 +67,21 @@
       "eval_samples_per_second": 891.836,
       "eval_steps_per_second": 3.604,
       "step": 400
+    },
+    {
+      "epoch": 0.6693440428380187,
+      "grad_norm": 0.19088135659694672,
+      "learning_rate": 0.0009330655957161981,
+      "loss": 1.0403,
+      "step": 500
+    },
+    {
+      "epoch": 0.6693440428380187,
+      "eval_loss": 0.9832900762557983,
+      "eval_runtime": 6.38,
+      "eval_samples_per_second": 892.158,
+      "eval_steps_per_second": 3.605,
+      "step": 500
     }
   ],
   "logging_steps": 100,
@@ -95,7 +110,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.4524908306432e+16,
+  "total_flos": 1.815613538304e+16,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null