Training in progress, step 15, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:873c73a0b6b43cbf57f1921c183907b829957d5d4e542bd1a235c645ea383b7a
+oid sha256:315f8cab177079d6e380b6f1cdda7eed7aa465799ae8f2108a8d27f87e9ef5b7
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:156e05563d9eeb97d1ec493276a36284b191704208bf78a838adf0443dfb208f
+oid sha256:8a18a323766377d7f9340a7a9699843051bd8d3f1def1038e05e9fd3ea72072a
 size 51244020

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6011dbc1beaf916a24aa0692a7ad3787fe62f4d3127d9859b27643438838594d
+oid sha256:ff5440c0314dadc3defe4b4803f353543d71edfcba882e67961bec9458fb6240
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
+oid sha256:ff2736979009751c0c6b0ddcc5f6544d6f723aa752b4798eab0b70fb76cf0083
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0016326197424542355,
+  "epoch": 0.0024489296136813534,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 15,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 22.205,
       "eval_steps_per_second": 11.103,
       "step": 10
+    },
+    {
+      "epoch": 0.0017958817166996593,
+      "grad_norm": 0.7647472023963928,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 1.7135,
+      "step": 11
+    },
+    {
+      "epoch": 0.001959143690945083,
+      "grad_norm": 0.7802902460098267,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 1.5259,
+      "step": 12
+    },
+    {
+      "epoch": 0.0021224056651905064,
+      "grad_norm": 0.7555536031723022,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 1.7871,
+      "step": 13
+    },
+    {
+      "epoch": 0.00228566763943593,
+      "grad_norm": 0.8001874685287476,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 1.5847,
+      "step": 14
+    },
+    {
+      "epoch": 0.0024489296136813534,
+      "grad_norm": 0.6708170771598816,
+      "learning_rate": 5e-05,
+      "loss": 1.5489,
+      "step": 15
+    },
+    {
+      "epoch": 0.0024489296136813534,
+      "eval_loss": 1.675947666168213,
+      "eval_runtime": 504.0522,
+      "eval_samples_per_second": 20.466,
+      "eval_steps_per_second": 10.233,
+      "step": 15
     }
   ],
   "logging_steps": 1,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8313247660769280.0,
+  "total_flos": 1.227876234952704e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null