Training in progress, step 16000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e4c46a908162b00f3ba9486bea20fb84fb3214d554c60ceeedafb0b57bf2240
+oid sha256:75a86cd786a5d3a1e1f2adcb3f9a3150ccda047965e61deb6383da469625f4c5
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99c44c9279a3a25aea078d1e884539b925aea0259a9d1b9cea8a21f053a5066d
+oid sha256:3d52a7d049b044518630bdac24825b9c5aace7c2129b9296a1f4f71f920000ff
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13d5ccf4326b5409b6c9f169af8a58a6579e0381579d71b37aaa359b3cba5d5e
+oid sha256:c907d42c9636b923c5bcc4fd78594e76582ee7e7c3af9d3ccfeae6b74654c31c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bd47cad1117d63c0c537ebb025d165a0cc6ebd76cda442e82a66a6ac283ef01
+oid sha256:3cf6ca81cadd867bd2c8ff23d5105fee09afef52498d5c300dfd5de226b319d5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.0333333333333334,
+  "epoch": 1.0666666666666667,
   "eval_steps": 500,
-  "global_step": 15500,
+  "global_step": 16000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1100,6 +1100,41 @@
       "learning_rate": 1.311288888888889e-05,
       "loss": 0.0703,
       "step": 15500
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 0.2654290497303009,
+      "learning_rate": 1.3068444444444446e-05,
+      "loss": 0.0593,
+      "step": 15600
+    },
+    {
+      "epoch": 1.0466666666666666,
+      "grad_norm": 0.2421567589044571,
+      "learning_rate": 1.3024000000000001e-05,
+      "loss": 0.0556,
+      "step": 15700
+    },
+    {
+      "epoch": 1.0533333333333332,
+      "grad_norm": 0.1856231540441513,
+      "learning_rate": 1.2979555555555556e-05,
+      "loss": 0.0619,
+      "step": 15800
+    },
+    {
+      "epoch": 1.06,
+      "grad_norm": 0.11161370575428009,
+      "learning_rate": 1.2935111111111111e-05,
+      "loss": 0.0597,
+      "step": 15900
+    },
+    {
+      "epoch": 1.0666666666666667,
+      "grad_norm": 0.31690728664398193,
+      "learning_rate": 1.2890666666666667e-05,
+      "loss": 0.061,
+      "step": 16000
     }
   ],
   "logging_steps": 100,
@@ -1119,7 +1154,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.775538921472e+16,
+  "total_flos": 3.897330499584e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null