Training in progress, step 60, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2a731ad90cb1208f24500760746be021e19f1c8a28830d6576caaa8378d6390
+oid sha256:c5b541bb702a004bd26e22a9b25613caa40ba226e1c32db33b163b11a283ee28
 size 3380768360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57e6fef3b80c3a466d80f26292b1b4075bb303f0144109f1c0bf035a689e9eff
-size 1756772889
+oid sha256:de5abaa4082b22bd4a967f9c79a0482a15f529323f25a7e5d2a3e5d715794ca1
+size 1757617777

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:544245d4a0da8d847252bdfe403e41a1a64fc9c974c22cff9871dfc244f5affc
+oid sha256:8568e47b8b6c26e0a7b5540da26be8f44a34e9279c25ee15a34f94896178a6b5
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50733553a6cea7b86768bb775429ef570a01c42581c9a321c702771217ac2eb9
+oid sha256:09d25955d4e2674e5dd5eed0c89d1bc41de0292bbbb39829ac908ea95d7cec10
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.313588850174216,
+  "epoch": 0.627177700348432,
   "eval_steps": 30,
-  "global_step": 30,
+  "global_step": 60,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -65,6 +65,56 @@
       "eval_samples_per_second": 0.292,
       "eval_steps_per_second": 0.073,
       "step": 30
+    },
+    {
+      "epoch": 0.36585365853658536,
+      "grad_norm": 0.08448098599910736,
+      "learning_rate": 9.451192254041758e-05,
+      "loss": 0.285,
+      "step": 35
+    },
+    {
+      "epoch": 0.4181184668989547,
+      "grad_norm": 0.0991150364279747,
+      "learning_rate": 9.243221287473756e-05,
+      "loss": 0.3197,
+      "step": 40
+    },
+    {
+      "epoch": 0.47038327526132406,
+      "grad_norm": 0.17393162846565247,
+      "learning_rate": 9.005005472346924e-05,
+      "loss": 0.3749,
+      "step": 45
+    },
+    {
+      "epoch": 0.5226480836236934,
+      "grad_norm": 0.0953838899731636,
+      "learning_rate": 8.738242764239046e-05,
+      "loss": 0.2699,
+      "step": 50
+    },
+    {
+      "epoch": 0.5749128919860628,
+      "grad_norm": 0.07958400994539261,
+      "learning_rate": 8.444834595378434e-05,
+      "loss": 0.2421,
+      "step": 55
+    },
+    {
+      "epoch": 0.627177700348432,
+      "grad_norm": 0.08708363026380539,
+      "learning_rate": 8.126872321608184e-05,
+      "loss": 0.2645,
+      "step": 60
+    },
+    {
+      "epoch": 0.627177700348432,
+      "eval_loss": 0.26565828919410706,
+      "eval_runtime": 1749.0443,
+      "eval_samples_per_second": 0.292,
+      "eval_steps_per_second": 0.073,
+      "step": 60
     }
   ],
   "logging_steps": 5,
@@ -84,7 +134,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.0997070578499584e+17,
+  "total_flos": 4.066496537929974e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null