Training in progress, step 15, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c6a831b79179bd8a1ecf4b0281eeb3aa36f7d70d2b23ae7d0f3f734dfbf244e
+oid sha256:3db1f765b2c03a0fa1533ee49bba6ccd2805a8fe8fd0db097871584a885a3dc5
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5735482d0392f5e16ca515c65dba1a261b761044dd18f524a60b0b679e59de00
+oid sha256:07fe565650efccf784843f888e5b62e941ebbc132edec9966c82a0b2f15b71fb
 size 43122580

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": 0.0011235560549138022,
+  "epoch": 0.0016853340823707033,
   "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": 20.669,
       "eval_steps_per_second": 10.335,
       "step": 10
+    },
+    {
+      "epoch": 0.0012359116604051825,
+      "grad_norm": 9.459853172302246,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 8.5236,
+      "step": 11
+    },
+    {
+      "epoch": 0.0013482672658965626,
+      "grad_norm": 9.357318878173828,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 8.5885,
+      "step": 12
+    },
+    {
+      "epoch": 0.0014606228713879429,
+      "grad_norm": 8.91463565826416,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 7.9383,
+      "step": 13
+    },
+    {
+      "epoch": 0.001572978476879323,
+      "grad_norm": 8.66787052154541,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 7.472,
+      "step": 14
+    },
+    {
+      "epoch": 0.0016853340823707033,
+      "grad_norm": 8.063846588134766,
+      "learning_rate": 5e-05,
+      "loss": 7.9145,
+      "step": 15
+    },
+    {
+      "epoch": 0.0016853340823707033,
+      "eval_loss": 0.4864272177219391,
+      "eval_runtime": 593.7636,
+      "eval_samples_per_second": 25.246,
+      "eval_steps_per_second": 12.623,
+      "step": 15
     }
   ],
   "logging_steps": 1,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.292595451920384e+16,
+  "total_flos": 1.923557299637453e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null