Training in progress, step 15, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58394d19f651935273a21893d0991707b76bafd74d6f6d709568f91cef904280
+oid sha256:2fd19d3f121bbb7f69c2666f3b81c70fbaf9cd7b4d666155c311a350a31fede5
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eaff94df0511bb372aea639d8928070ccc70f3c5868384e4f1f6673dbd4cb1cf
+oid sha256:e5cf2dfe76fa8042b6bf6df2e8f95b194097a81be7202b7ab310198bdbf631e5
 size 41119636

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": 0.013748066678123389,
+  "epoch": 0.020622100017185084,
   "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": 20.964,
       "eval_steps_per_second": 10.482,
       "step": 10
+    },
+    {
+      "epoch": 0.015122873345935728,
+      "grad_norm": 0.5674175024032593,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 1.4697,
+      "step": 11
+    },
+    {
+      "epoch": 0.016497680013748066,
+      "grad_norm": 0.5313400030136108,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 1.3832,
+      "step": 12
+    },
+    {
+      "epoch": 0.017872486681560405,
+      "grad_norm": 0.5378307700157166,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 1.3486,
+      "step": 13
+    },
+    {
+      "epoch": 0.019247293349372745,
+      "grad_norm": 0.48813918232917786,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 1.2926,
+      "step": 14
+    },
+    {
+      "epoch": 0.020622100017185084,
+      "grad_norm": 0.4850353002548218,
+      "learning_rate": 5e-05,
+      "loss": 1.2852,
+      "step": 15
+    },
+    {
+      "epoch": 0.020622100017185084,
+      "eval_loss": 1.2362544536590576,
+      "eval_runtime": 59.0914,
+      "eval_samples_per_second": 20.748,
+      "eval_steps_per_second": 10.374,
+      "step": 15
     }
   ],
   "logging_steps": 1,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6514932543651840.0,
+  "total_flos": 9772398815477760.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null