Training in progress, step 12500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6989d08304817f7eda2a41817fe6fdf1039613dcc5ce63bc28b05cebb5b0a729
+oid sha256:a82551d15f6384cb873b544e144c1f4a47713f4d120acfb3fbb93f105eb65230
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ef2622b356cc24fc03d43081c989231e41a9f98afae1477feeac80752fcbe27
+oid sha256:2430d0f4d73641065e9bf5dd721f5eb31d0400c5f5950d844482b26db026c2da
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25c75df0b33157e12f11389fab2a782cb08091622aab636059c475b184fac12c
+oid sha256:8295ae519bb42d65fe3f9c31072a390aa31ad86276d0cec6598329f84d5b468f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ba896b8260293f6060945e9d4b6d72d879757324e56407782c7dd941c44937b
+oid sha256:2529f9270ae0263cc98da512a0bbd9cfce3aaadf2f105e2a962446a19cb9d893
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.082674041390419,
-  "best_model_checkpoint": "./fine-tuned/checkpoint-12000",
-  "epoch": 0.96,
+  "best_metric": 0.0824647843837738,
+  "best_model_checkpoint": "./fine-tuned/checkpoint-12500",
+  "epoch": 1.0,
   "eval_steps": 500,
-  "global_step": 12000,
+  "global_step": 12500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1879,6 +1879,84 @@
       "eval_samples_per_second": 22.714,
       "eval_steps_per_second": 5.679,
       "step": 12000
+    },
+    {
+      "epoch": 0.964,
+      "grad_norm": 0.1296168565750122,
+      "learning_rate": 1.55424e-05,
+      "loss": 0.0638,
+      "step": 12050
+    },
+    {
+      "epoch": 0.968,
+      "grad_norm": 0.14450989663600922,
+      "learning_rate": 1.54824e-05,
+      "loss": 0.0623,
+      "step": 12100
+    },
+    {
+      "epoch": 0.972,
+      "grad_norm": 0.09367354214191437,
+      "learning_rate": 1.54224e-05,
+      "loss": 0.0618,
+      "step": 12150
+    },
+    {
+      "epoch": 0.976,
+      "grad_norm": 0.13332900404930115,
+      "learning_rate": 1.53624e-05,
+      "loss": 0.0608,
+      "step": 12200
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.14300012588500977,
+      "learning_rate": 1.53024e-05,
+      "loss": 0.0695,
+      "step": 12250
+    },
+    {
+      "epoch": 0.984,
+      "grad_norm": 0.14829818904399872,
+      "learning_rate": 1.52424e-05,
+      "loss": 0.0589,
+      "step": 12300
+    },
+    {
+      "epoch": 0.988,
+      "grad_norm": 0.08889272063970566,
+      "learning_rate": 1.5182399999999999e-05,
+      "loss": 0.0578,
+      "step": 12350
+    },
+    {
+      "epoch": 0.992,
+      "grad_norm": 0.18994523584842682,
+      "learning_rate": 1.51224e-05,
+      "loss": 0.0667,
+      "step": 12400
+    },
+    {
+      "epoch": 0.996,
+      "grad_norm": 0.16152743995189667,
+      "learning_rate": 1.50624e-05,
+      "loss": 0.0552,
+      "step": 12450
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.2399597018957138,
+      "learning_rate": 1.5002399999999999e-05,
+      "loss": 0.0632,
+      "step": 12500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.0824647843837738,
+      "eval_runtime": 88.0514,
+      "eval_samples_per_second": 22.714,
+      "eval_steps_per_second": 5.678,
+      "step": 12500
     }
   ],
   "logging_steps": 50,
@@ -1898,7 +1976,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.922997874688e+16,
+  "total_flos": 3.0447894528e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null