Training in progress, step 15, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c36b832af60590c9c6a5e230db3b1d09118a58179dbb4ab280c7ac5dc2ea683
+oid sha256:99bef05b73063a9a4199cb6218e91d84cbb482c95e54c11ac4baac7dcb9c04ca
 size 14696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7a5608a6b20c0caad90c84d17a01f6b0d8761d623e8509c9d10c0db96c8a7df
+oid sha256:a6fe2310411c7fc7e36f13652132603e10d34509b044505a528f3e51a2caf8a2
 size 39398

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": 0.0004958211573085588,
+  "epoch": 0.0007437317359628382,
   "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": 734.384,
       "eval_steps_per_second": 367.203,
       "step": 10
+    },
+    {
+      "epoch": 0.0005454032730394147,
+      "grad_norm": 0.05759993568062782,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 11.9496,
+      "step": 11
+    },
+    {
+      "epoch": 0.0005949853887702706,
+      "grad_norm": 0.06732578575611115,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 11.9443,
+      "step": 12
+    },
+    {
+      "epoch": 0.0006445675045011264,
+      "grad_norm": 0.06317765265703201,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 11.9255,
+      "step": 13
+    },
+    {
+      "epoch": 0.0006941496202319823,
+      "grad_norm": 0.0681978166103363,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 11.9497,
+      "step": 14
+    },
+    {
+      "epoch": 0.0007437317359628382,
+      "grad_norm": 0.05356225371360779,
+      "learning_rate": 5e-05,
+      "loss": 11.9456,
+      "step": 15
+    },
+    {
+      "epoch": 0.0007437317359628382,
+      "eval_loss": 11.933807373046875,
+      "eval_runtime": 45.986,
+      "eval_samples_per_second": 738.681,
+      "eval_steps_per_second": 369.351,
+      "step": 15
     }
   ],
   "logging_steps": 1,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4726456320.0,
+  "total_flos": 7089684480.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null