Uploaded checkpoint-10000

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e59ddad1a1d98177772aa8b2d13012639122cef2ae95e899b2f443df4013be9
+oid sha256:f7347334734f59aeff9afce0e98660df3cae91e6645bc8ec34079b3b2219699f
 size 119975656

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16d0966176c322c30b36b89c66ec18f8ae74ea263592b068be163fcdb1afc4db
+oid sha256:aec12535e081c3ff4957b0d8e608b90c57e8742d6b42f48953e3e75c30a2b79e
 size 60477396

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22beba43193d1d8ce34d77ec3d0e7488bf78a103ac3870877f9df324c89bc84b
+oid sha256:1e418c6ffc12f413437fdbb60a0c8f46583b225f4f359e3e4b81728230a62987
 size 14244

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09df5969990294970fc033fefa68b2ddf4a576ed9124e0a712451ec50a2e090f
+oid sha256:edb6921d03e8a850966c91726d888e0bb74b9a81629db489ad598f21f6bb2f09
 size 1064

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.1875,
+  "epoch": 0.25,
   "eval_steps": 2500,
-  "global_step": 7500,
+  "global_step": 10000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -80,6 +80,35 @@
       "eval_samples_per_second": 4.951,
       "eval_steps_per_second": 4.951,
       "step": 7500
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 6.616883277893066,
+      "learning_rate": 1.5653333333333335e-05,
+      "loss": 1.4414,
+      "step": 8000
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 4.114346027374268,
+      "learning_rate": 1.5074202898550725e-05,
+      "loss": 1.4392,
+      "step": 9000
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 9.38364028930664,
+      "learning_rate": 1.4495072463768116e-05,
+      "loss": 1.4307,
+      "step": 10000
+    },
+    {
+      "epoch": 0.25,
+      "eval_loss": 1.4246548414230347,
+      "eval_runtime": 201.9169,
+      "eval_samples_per_second": 4.953,
+      "eval_steps_per_second": 4.953,
+      "step": 10000
     }
   ],
   "logging_steps": 1000,
@@ -87,7 +116,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 2500,
-  "total_flos": 1.2076594495488e+17,
+  "total_flos": 1.6102125993984e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null