Training in progress, step 15, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c34a98cfa104e1761e26722d9e257bab07cd0696f48fe81dd1ee83747c4fcde
+oid sha256:ce16af6efe20a4f464d6bc2e38cd7334edda7f3287d78d421355b2a5ba0b4947
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:299ad2c1abc4d06b1320a67722c4330181ef9169683b13f1ff338a1d5f4bcedc
+oid sha256:91642a9bd286adb05fb1317402f8f8a959aa0ab54f3ea17938061dee6d7b95d2
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ac108aa9eba00358310a4439f789a188dfe5197c585ee0c9b69af254e4ad32c
+oid sha256:4a39a41f912d3765e4194e7bf2d118cba79dcbe423e3417f95fa83853160b690
 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": 0.07017543859649122,
+  "epoch": 0.10526315789473684,
   "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": 26.506,
       "eval_steps_per_second": 13.253,
       "step": 10
+    },
+    {
+      "epoch": 0.07719298245614035,
+      "grad_norm": 6.979969501495361,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 16.7988,
+      "step": 11
+    },
+    {
+      "epoch": 0.08421052631578947,
+      "grad_norm": 6.168642997741699,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 15.2197,
+      "step": 12
+    },
+    {
+      "epoch": 0.0912280701754386,
+      "grad_norm": 7.531093120574951,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 14.5283,
+      "step": 13
+    },
+    {
+      "epoch": 0.09824561403508772,
+      "grad_norm": 6.556507110595703,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 15.0155,
+      "step": 14
+    },
+    {
+      "epoch": 0.10526315789473684,
+      "grad_norm": 6.081122398376465,
+      "learning_rate": 5e-05,
+      "loss": 13.9098,
+      "step": 15
+    },
+    {
+      "epoch": 0.10526315789473684,
+      "eval_loss": 0.8202072381973267,
+      "eval_runtime": 8.9737,
+      "eval_samples_per_second": 26.745,
+      "eval_steps_per_second": 13.372,
+      "step": 15
     }
   ],
   "logging_steps": 1,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0871901190619136e+16,
+  "total_flos": 1.608389876514816e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null