Training in progress, step 15, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e8d7ec1f21bcfdc2b7ba978600de345aac8ce7d4832d13445c36957aa7f9333
+oid sha256:6cc45f662a81cd8da2f3cecda712b0bde184f48920a0b6880ccc83b96ff827a2
 size 28351000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bf2aaae0631c26d4508e347a271bb65449c5909e473971dbfd7b2d73d7ced15
+oid sha256:328edce91614d1e949084d0f0839b97e3cde45034569a6a8b041f56cc7059627
 size 14714004

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6b5eeaa3329a2f692c9a29f4e72a4b2332babf5877cdad50435bef108f64f17
+oid sha256:14f4f21ebf227d19ef9d4226df0a754a81b16268b7730a8fca801390c48ac89d
 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": 0.30592734225621415,
+  "epoch": 0.4588910133843212,
   "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": 125.394,
       "eval_steps_per_second": 63.837,
       "step": 10
+    },
+    {
+      "epoch": 0.3365200764818356,
+      "grad_norm": 64.02308654785156,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 34.875,
+      "step": 11
+    },
+    {
+      "epoch": 0.367112810707457,
+      "grad_norm": 63.0142707824707,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 31.0859,
+      "step": 12
+    },
+    {
+      "epoch": 0.3977055449330784,
+      "grad_norm": 74.16285705566406,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 29.8125,
+      "step": 13
+    },
+    {
+      "epoch": 0.42829827915869984,
+      "grad_norm": 61.39728927612305,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 26.4844,
+      "step": 14
+    },
+    {
+      "epoch": 0.4588910133843212,
+      "grad_norm": 63.88688659667969,
+      "learning_rate": 5e-05,
+      "loss": 22.7109,
+      "step": 15
+    },
+    {
+      "epoch": 0.4588910133843212,
+      "eval_loss": 1.4044034481048584,
+      "eval_runtime": 0.465,
+      "eval_samples_per_second": 118.289,
+      "eval_steps_per_second": 60.22,
+      "step": 15
     }
   ],
   "logging_steps": 1,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1195062570516480.0,
+  "total_flos": 1792593855774720.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null