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:b2c592406a7b85db16b18cb40bfb9d066a3ee6f077787df23af933f40f2a8e28
+oid sha256:eb56d32bb37774bec306b90fa3be47e97cc6458e77ff78bf8b13210320d9629a
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb00ef0006490c0d213383b838cbbaba8f50fb67776ad094b67b3f07cb114005
+oid sha256:4da3bece2c27b9cc63a7140ef00a6427e6b154e7cf1f8257777d47f5deb9124b
 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": 0.03658815458495312,
+  "epoch": 0.05488223187742968,
   "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": 39.138,
       "eval_steps_per_second": 19.612,
       "step": 10
+    },
+    {
+      "epoch": 0.04024697004344843,
+      "grad_norm": 1.3785911798477173,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 1.3677,
+      "step": 11
+    },
+    {
+      "epoch": 0.043905785501943746,
+      "grad_norm": 1.3619410991668701,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 1.1551,
+      "step": 12
+    },
+    {
+      "epoch": 0.04756460096043906,
+      "grad_norm": 1.5594295263290405,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 1.1575,
+      "step": 13
+    },
+    {
+      "epoch": 0.05122341641893437,
+      "grad_norm": 1.627646803855896,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 1.1252,
+      "step": 14
+    },
+    {
+      "epoch": 0.05488223187742968,
+      "grad_norm": 1.5937222242355347,
+      "learning_rate": 5e-05,
+      "loss": 1.177,
+      "step": 15
+    },
+    {
+      "epoch": 0.05488223187742968,
+      "eval_loss": 1.0867087841033936,
+      "eval_runtime": 11.7623,
+      "eval_samples_per_second": 39.193,
+      "eval_steps_per_second": 19.639,
+      "step": 15
     }
   ],
   "logging_steps": 1,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7644365665075200.0,
+  "total_flos": 1.14665484976128e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null