Uploaded checkpoint-12500

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7347334734f59aeff9afce0e98660df3cae91e6645bc8ec34079b3b2219699f
+oid sha256:a15eb9315483b3e56b05091f1531b26cadbe36a6e736e6f70bda3f75221e6b8c
 size 119975656

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aec12535e081c3ff4957b0d8e608b90c57e8742d6b42f48953e3e75c30a2b79e
+oid sha256:b1066f24e58a5547030a7f83888490c431db8d182fcf127c93d1f95d5c5063ec
 size 60477396

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e418c6ffc12f413437fdbb60a0c8f46583b225f4f359e3e4b81728230a62987
-size 14244
+oid sha256:21341ea1e3d0ca174eca172ae8f5dd909607c3fbf76f8554ed9f6a5b644ebf0d
+size 14308

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edb6921d03e8a850966c91726d888e0bb74b9a81629db489ad598f21f6bb2f09
+oid sha256:e92d596f376f9a515800068cef0d91e543a25c37a7a7bdea3611bf7c16f7dcb0
 size 1064

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.25,
+  "epoch": 0.3125,
   "eval_steps": 2500,
-  "global_step": 10000,
+  "global_step": 12500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -109,6 +109,28 @@
       "eval_samples_per_second": 4.953,
       "eval_steps_per_second": 4.953,
       "step": 10000
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 3.899681806564331,
+      "learning_rate": 1.3915362318840582e-05,
+      "loss": 1.4313,
+      "step": 11000
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 2.839545965194702,
+      "learning_rate": 1.3336231884057973e-05,
+      "loss": 1.415,
+      "step": 12000
+    },
+    {
+      "epoch": 0.31,
+      "eval_loss": 1.4323452711105347,
+      "eval_runtime": 202.4132,
+      "eval_samples_per_second": 4.94,
+      "eval_steps_per_second": 4.94,
+      "step": 12500
     }
   ],
   "logging_steps": 1000,
@@ -116,7 +138,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 2500,
-  "total_flos": 1.6102125993984e+17,
+  "total_flos": 2.012765749248e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null