Training in progress, step 15, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:142c51a19fd0de3a3eea1bd8bff2a8662a166067c6118778e29cd81cbfa14651
+oid sha256:61a1a01dfb0640c4f39a48d06f5800b8cdb86fa1ca1fcecb74ef6c290f428512
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7982a7be520b360f4200b182e5bf4cf8c7cc1ab5d8159ce905e530306731e157
+oid sha256:1ca14eefa7d7bf36d2545030dd33adb9e09d1a7dade937830a89aeaed1c9c2da
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:786c2a878181864eaae3009c839540dd50237b1930f80d9955fbabc0ccf3cc14
+oid sha256:288a16e6d9d8c06d39eaaf028ab7ce6ab9c130eeb62c3121161c9ecb57cfd771
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
+oid sha256:a991012fbb3e0053bc41a0b782b67db27509c27d2801c8bf4a64c3687e55e582
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00566331587144273,
+  "epoch": 0.008494973807164095,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 15,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,28 @@
       "eval_samples_per_second": 12.499,
       "eval_steps_per_second": 3.127,
       "step": 10
+    },
+    {
+      "epoch": 0.006795979045731275,
+      "grad_norm": 5.078495979309082,
+      "learning_rate": 9.938441702975689e-05,
+      "loss": 5.1733,
+      "step": 12
+    },
+    {
+      "epoch": 0.008494973807164095,
+      "grad_norm": 3.602994441986084,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 4.8478,
+      "step": 15
+    },
+    {
+      "epoch": 0.008494973807164095,
+      "eval_loss": 4.539829730987549,
+      "eval_runtime": 237.9504,
+      "eval_samples_per_second": 12.498,
+      "eval_steps_per_second": 3.127,
+      "step": 15
     }
   ],
   "logging_steps": 3,
@@ -71,7 +93,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.508513578745856e+16,
+  "total_flos": 2.262770368118784e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null