Uploaded checkpoint-7500

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db00791fe6be02cbf9d58bde5545dde203c803d64036669187cec6cf3eb19284
+oid sha256:0e59ddad1a1d98177772aa8b2d13012639122cef2ae95e899b2f443df4013be9
 size 119975656

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2d7f277b633524451fcf79452d7657c0be7ab33e9b11323f79bf0ffbd3e95da
+oid sha256:16d0966176c322c30b36b89c66ec18f8ae74ea263592b068be163fcdb1afc4db
 size 60477396

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:056c47f7cb4d7abe8a557a81ae1942cf3eb44d8487b4271bb8bc5c01f0d844ba
+oid sha256:22beba43193d1d8ce34d77ec3d0e7488bf78a103ac3870877f9df324c89bc84b
 size 14244

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a8b9195a0ab65d895e29be71344b338c125cf19b59f7afb36df3047db308f52
+oid sha256:09df5969990294970fc033fefa68b2ddf4a576ed9124e0a712451ec50a2e090f
 size 1064

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.125,
+  "epoch": 0.1875,
   "eval_steps": 2500,
-  "global_step": 5000,
+  "global_step": 7500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,28 @@
       "eval_samples_per_second": 4.952,
       "eval_steps_per_second": 4.952,
       "step": 5000
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 2.666102170944214,
+      "learning_rate": 1.6812753623188408e-05,
+      "loss": 1.4754,
+      "step": 6000
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 2.95894455909729,
+      "learning_rate": 1.623304347826087e-05,
+      "loss": 1.4816,
+      "step": 7000
+    },
+    {
+      "epoch": 0.19,
+      "eval_loss": 1.4514989852905273,
+      "eval_runtime": 201.9852,
+      "eval_samples_per_second": 4.951,
+      "eval_steps_per_second": 4.951,
+      "step": 7500
     }
   ],
   "logging_steps": 1000,
@@ -65,7 +87,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 2500,
-  "total_flos": 8.051062996992e+16,
+  "total_flos": 1.2076594495488e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null