Training in progress, step 12, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f232bd228e4f664dbba85e67cfcc3c6164d36ace7266b89d7a699205dd4c12a9
+oid sha256:343dfb75fb5c0ea331bb2fea28faa4a62f086a7a5d2e36f8ee0ac386ded7fb33
 size 200068512

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0730d46ab97c102b2ceae9a7bfa3bb9dc1bab4b85c9a5e3a25267670d64e8f06
+oid sha256:2ff2227ceb1f5a2ee89106e1c6e1021a48cff57efe25c1149e99d0bec513e79a
 size 102030196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ccf4171573c4aa942fd9e6830083f77573db8b338bc5d43c1892694648afeb6a
+oid sha256:742ac93365f9f5139042c83640a290eb5bf78fa0571f5209fdc989f29567f644
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a3d18e607a27cfab9cec7cfaa7384cdb877a2330c4bcd4e1efcae25be9908cb
+oid sha256:f9249a82eef8eec6a1c71d7af2159d50f378e28b90f1d4a939b2f9ac7c40432e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5289256198347108,
+  "epoch": 0.7933884297520661,
   "eval_steps": 4,
-  "global_step": 8,
+  "global_step": 12,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -87,6 +87,42 @@
       "eval_samples_per_second": 6.041,
       "eval_steps_per_second": 3.021,
       "step": 8
+    },
+    {
+      "epoch": 0.5950413223140496,
+      "grad_norm": 4.271751403808594,
+      "learning_rate": 9e-05,
+      "loss": 2.8224,
+      "step": 9
+    },
+    {
+      "epoch": 0.6611570247933884,
+      "grad_norm": 4.623085975646973,
+      "learning_rate": 0.0001,
+      "loss": 3.1332,
+      "step": 10
+    },
+    {
+      "epoch": 0.7272727272727273,
+      "grad_norm": 7.002574920654297,
+      "learning_rate": 9.330127018922194e-05,
+      "loss": 2.8715,
+      "step": 11
+    },
+    {
+      "epoch": 0.7933884297520661,
+      "grad_norm": 10.354272842407227,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 3.1827,
+      "step": 12
+    },
+    {
+      "epoch": 0.7933884297520661,
+      "eval_loss": 2.666003942489624,
+      "eval_runtime": 4.2925,
+      "eval_samples_per_second": 6.057,
+      "eval_steps_per_second": 3.029,
+      "step": 12
     }
   ],
   "logging_steps": 1,
@@ -106,7 +142,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.908123913872998e+16,
+  "total_flos": 7.362185870809498e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null