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:cd328a6c4b91973d593d1bcb81d0b2b8c9653c2b778ecfa0c2bfdf5d2568bbfe
+oid sha256:7d549372ecda0aabd1980c9049d511b784d28fbea1ab6cba08ab7f7c2958ba61
 size 125040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12bfd27ea4802427ac6a31b0c4996c8ccbb9be2af3c8b85fd1d44460fe346a92
+oid sha256:93f034a6cac0630266d66989c2e0e876e0339c9a916b63e5a87073c4acb56a21
 size 162868

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": 0.01520045601368041,
+  "epoch": 0.022800684020520615,
   "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": 780.319,
       "eval_steps_per_second": 390.159,
       "step": 10
+    },
+    {
+      "epoch": 0.016720501615048452,
+      "grad_norm": 5.062138557434082,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 177.625,
+      "step": 11
+    },
+    {
+      "epoch": 0.01824054721641649,
+      "grad_norm": 4.429068565368652,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 177.75,
+      "step": 12
+    },
+    {
+      "epoch": 0.019760592817784535,
+      "grad_norm": 4.724205017089844,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 177.5,
+      "step": 13
+    },
+    {
+      "epoch": 0.021280638419152575,
+      "grad_norm": 5.304701328277588,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 177.4375,
+      "step": 14
+    },
+    {
+      "epoch": 0.022800684020520615,
+      "grad_norm": 5.0064005851745605,
+      "learning_rate": 5e-05,
+      "loss": 177.25,
+      "step": 15
+    },
+    {
+      "epoch": 0.022800684020520615,
+      "eval_loss": 11.090591430664062,
+      "eval_runtime": 1.464,
+      "eval_samples_per_second": 756.813,
+      "eval_steps_per_second": 378.406,
+      "step": 15
     }
   ],
   "logging_steps": 1,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 390614482944.0,
+  "total_flos": 583510523904.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null