Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:252ed57a9c24d44d315f17e266c3262466702d18620587d64737897ce78f6978
+oid sha256:d4397371949a0a11e6c9326f50376c519ee26fcc09698e9c507bb5dcb754345d
 size 25271744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c29f8530ed79bd06b84736c6c2b4be4f81afada2eb8bf190832ba7008011f594
+oid sha256:189c11d49dc4ec1b76a60a13824ce8f8cbdf82945637995ed559a5dd0a12b292
 size 13685516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c43d204983049079e13404efd288d14125bb2ca2e7a98897797a6812d6e7b7a3
+oid sha256:01898d7ee61fd42fd0e6cb22d62ed29c4e5b0a0f5b2fc626a3c984b595e158b0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
+oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.000565493991626339,
+  "epoch": 0.001130987983252678,
   "eval_steps": 10,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -37,6 +37,35 @@
       "eval_samples_per_second": 28.952,
       "eval_steps_per_second": 14.476,
       "step": 10
+    },
+    {
+      "epoch": 0.0006524930672611604,
+      "grad_norm": 0.366901159286499,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 0.6685,
+      "step": 15
+    },
+    {
+      "epoch": 0.0008699907563482138,
+      "grad_norm": 0.4033157229423523,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.6795,
+      "step": 20
+    },
+    {
+      "epoch": 0.0008699907563482138,
+      "eval_loss": 0.6729934215545654,
+      "eval_runtime": 334.9518,
+      "eval_samples_per_second": 28.9,
+      "eval_steps_per_second": 14.45,
+      "step": 20
+    },
+    {
+      "epoch": 0.0010874884454352672,
+      "grad_norm": 0.41979432106018066,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.6557,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 652269544538112.0,
+  "total_flos": 1298144289619968.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null