Training in progress, step 9000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d940b624e42af265966f792f158b5e6dff6cf498a4c59d70a1629ae2fdc2efc
+oid sha256:336e73efd327d7a1521b5a4d27a9fc5038eee564a716b9140d3d16b364a23a50
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a2bec32040a69e58023b5509b0fb90efe9794b8b9079e790fb6687d3ff55f17
+oid sha256:d97c69acfb193391ec999ba15e870e63ab169b8ed9bf00f41fd88c47a66c65b8
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08998c919fed10f9ef4173715a99abc07523cdf2197bb7756b598ec6ecad7017
+oid sha256:899366455e0955e5cf5c394ff7d4037b7abb9e5bade054905761b5a1a2bd5b8c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a2d7ef4474f599b4e657eaa32ef5df2560c025d5712ce31e544f317cb28ad99
+oid sha256:a63facda9ec9ba059fa6f2a71adafa722008934178d5e063ac43b7ad2180ad7f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5666666666666667,
+  "epoch": 0.6,
   "eval_steps": 500,
-  "global_step": 8500,
+  "global_step": 9000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -602,6 +602,41 @@
       "learning_rate": 1.6223555555555556e-05,
       "loss": 0.0677,
       "step": 8500
+    },
+    {
+      "epoch": 0.5733333333333334,
+      "grad_norm": 0.11715523153543472,
+      "learning_rate": 1.617911111111111e-05,
+      "loss": 0.0657,
+      "step": 8600
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.2229638546705246,
+      "learning_rate": 1.6134666666666666e-05,
+      "loss": 0.0672,
+      "step": 8700
+    },
+    {
+      "epoch": 0.5866666666666667,
+      "grad_norm": 0.18995241820812225,
+      "learning_rate": 1.609022222222222e-05,
+      "loss": 0.0742,
+      "step": 8800
+    },
+    {
+      "epoch": 0.5933333333333334,
+      "grad_norm": 0.23822380602359772,
+      "learning_rate": 1.604577777777778e-05,
+      "loss": 0.0771,
+      "step": 8900
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.21793758869171143,
+      "learning_rate": 1.6001333333333336e-05,
+      "loss": 0.0635,
+      "step": 9000
     }
   ],
   "logging_steps": 100,
@@ -621,7 +656,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.070456827904e+16,
+  "total_flos": 2.192248406016e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null