Uploaded checkpoint-15000

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a15eb9315483b3e56b05091f1531b26cadbe36a6e736e6f70bda3f75221e6b8c
+oid sha256:948fb1e98580e330d4d842e33a37f9084da9e25cc7f48a4d02a36faaddab5b4e
 size 119975656

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1066f24e58a5547030a7f83888490c431db8d182fcf127c93d1f95d5c5063ec
+oid sha256:099dcb4361bb2049aa6db3b6e81a9f34b1202083b425b25c3af7c20f9259fe22
 size 60477396

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21341ea1e3d0ca174eca172ae8f5dd909607c3fbf76f8554ed9f6a5b644ebf0d
-size 14308
+oid sha256:099feb85b2265fa46cec748072b982183c4dbb871e47eb59c01b10707a2a6958
+size 14244

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e92d596f376f9a515800068cef0d91e543a25c37a7a7bdea3611bf7c16f7dcb0
+oid sha256:2c59c86cac1045db21cd2eb48ce1a34a6e8c676f8d6333a24ac6d07a63dbb2c3
 size 1064

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3125,
+  "epoch": 0.375,
   "eval_steps": 2500,
-  "global_step": 12500,
+  "global_step": 15000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -131,6 +131,35 @@
       "eval_samples_per_second": 4.94,
       "eval_steps_per_second": 4.94,
       "step": 12500
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 3.805086612701416,
+      "learning_rate": 1.2756521739130436e-05,
+      "loss": 1.4003,
+      "step": 13000
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 6.0652241706848145,
+      "learning_rate": 1.21768115942029e-05,
+      "loss": 1.3952,
+      "step": 14000
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 8.923527717590332,
+      "learning_rate": 1.1597681159420292e-05,
+      "loss": 1.3933,
+      "step": 15000
+    },
+    {
+      "epoch": 0.38,
+      "eval_loss": 1.3821483850479126,
+      "eval_runtime": 201.8609,
+      "eval_samples_per_second": 4.954,
+      "eval_steps_per_second": 4.954,
+      "step": 15000
     }
   ],
   "logging_steps": 1000,
@@ -138,7 +167,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 2500,
-  "total_flos": 2.012765749248e+17,
+  "total_flos": 2.4153188990976e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null