Uploaded checkpoint-35000

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59ec9fad15410ceb587e40b784f8ea3dc54e938ac10a95294d3699c990784967
+oid sha256:31c9e60b062dc35ba07014b04024f3870086ef8da686c6bd440ce4c3ce2d57a5
 size 119975656

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c12910df6856fa33f58fb4ff472bdd6dc11e30b0182e3ccd2be9e925b347150f
+oid sha256:51808a22cffba497fd0d5aea1aaa9598ef8307f1972222038ec8a8696d4c4c85
 size 60477396

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dec85530e6760daecc8dcc8115ae33468e447116708e85bebcec9d39f1d56b5a
+oid sha256:84a37d0ab19da28f930155bb45ce8d9cc793dd6efc4451420dd7dabae2cc2dbc
 size 14244

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5e0762973dbc38f3dbaecc0938289f2d4040e8f1f2eb1a8e5d560966a6ea45a
+oid sha256:d3b0c99946a1227615c7e0d4d3c3cd5cbc49f8e7b155b57241588038e98ebb81
 size 1064

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8125,
+  "epoch": 0.875,
   "eval_steps": 2500,
-  "global_step": 32500,
+  "global_step": 35000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -335,6 +335,35 @@
       "eval_samples_per_second": 4.952,
       "eval_steps_per_second": 4.952,
       "step": 32500
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 10.57639217376709,
+      "learning_rate": 1.1669565217391306e-06,
+      "loss": 1.2787,
+      "step": 33000
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 5.37148380279541,
+      "learning_rate": 5.872463768115943e-07,
+      "loss": 1.2788,
+      "step": 34000
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 12.262892723083496,
+      "learning_rate": 7.536231884057971e-09,
+      "loss": 1.2844,
+      "step": 35000
+    },
+    {
+      "epoch": 0.88,
+      "eval_loss": 1.2726885080337524,
+      "eval_runtime": 201.8671,
+      "eval_samples_per_second": 4.954,
+      "eval_steps_per_second": 4.954,
+      "step": 35000
     }
   ],
   "logging_steps": 1000,
@@ -342,7 +371,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 2500,
-  "total_flos": 5.2331909480448e+17,
+  "total_flos": 5.6357440978944e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null