Training in progress, step 16000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47ec1fd68430fdacb80810ecd09adfa63b256edd752390b582d7134186c11fe5
+oid sha256:39065861c3b099700bb000236a9e498a039343f48398b98c2fb9a14bb096b6c1
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7dedc049b8b109e2a1e1d8ca3aa0a4db96cc41f55ad87c5be1b4f1d3b32922bb
+oid sha256:8e12bc163cfe02cd564c638e298b40f4155a4f87b8f01adeb81746cbd797e5ef
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc7b29b924630649498d282773659d36f4c79fef1453c3983d39d7e7e53066c4
+oid sha256:4eebbe4891f802a9c170f9968f3ddf4d71a0eff2d959ee8775998aa9a7034155
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0adcdf1185fa7d1b89a354568f52beda1398968ea15296ac3bc948fc9b42fcfd
+oid sha256:6949e36257fd6db2d60885342ebdb2dc7d96352bf8e47bc5271716a48f4cbc6e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.08158940076828003,
   "best_model_checkpoint": "./fine-tuned/checkpoint-12500",
-  "epoch": 2.48,
+  "epoch": 2.56,
   "eval_steps": 500,
-  "global_step": 15500,
+  "global_step": 16000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2425,6 +2425,84 @@
       "eval_samples_per_second": 17.134,
       "eval_steps_per_second": 2.142,
       "step": 15500
+    },
+    {
+      "epoch": 2.488,
+      "grad_norm": 6472.25537109375,
+      "learning_rate": 5.12e-06,
+      "loss": 0.0496,
+      "step": 15550
+    },
+    {
+      "epoch": 2.496,
+      "grad_norm": 6369.4833984375,
+      "learning_rate": 5.04e-06,
+      "loss": 0.0518,
+      "step": 15600
+    },
+    {
+      "epoch": 2.504,
+      "grad_norm": 8784.1083984375,
+      "learning_rate": 4.96e-06,
+      "loss": 0.0547,
+      "step": 15650
+    },
+    {
+      "epoch": 2.512,
+      "grad_norm": 8509.6650390625,
+      "learning_rate": 4.88e-06,
+      "loss": 0.0555,
+      "step": 15700
+    },
+    {
+      "epoch": 2.52,
+      "grad_norm": 7856.84716796875,
+      "learning_rate": 4.800000000000001e-06,
+      "loss": 0.0513,
+      "step": 15750
+    },
+    {
+      "epoch": 2.528,
+      "grad_norm": 6816.51123046875,
+      "learning_rate": 4.72e-06,
+      "loss": 0.0493,
+      "step": 15800
+    },
+    {
+      "epoch": 2.536,
+      "grad_norm": 6773.06884765625,
+      "learning_rate": 4.6400000000000005e-06,
+      "loss": 0.05,
+      "step": 15850
+    },
+    {
+      "epoch": 2.544,
+      "grad_norm": 9726.3818359375,
+      "learning_rate": 4.56e-06,
+      "loss": 0.0518,
+      "step": 15900
+    },
+    {
+      "epoch": 2.552,
+      "grad_norm": 8707.6591796875,
+      "learning_rate": 4.48e-06,
+      "loss": 0.0499,
+      "step": 15950
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 4772.958984375,
+      "learning_rate": 4.4e-06,
+      "loss": 0.0522,
+      "step": 16000
+    },
+    {
+      "epoch": 2.56,
+      "eval_loss": 0.08175843954086304,
+      "eval_runtime": 116.8011,
+      "eval_samples_per_second": 17.123,
+      "eval_steps_per_second": 2.14,
+      "step": 16000
     }
   ],
   "logging_steps": 50,
@@ -2444,7 +2522,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.551077842944e+16,
+  "total_flos": 7.794660999168e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null