Uploaded checkpoint-17500

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:948fb1e98580e330d4d842e33a37f9084da9e25cc7f48a4d02a36faaddab5b4e
+oid sha256:9a6cdbde4f4ccad23f4f917c627b157da08e6dc847e2ed92ac14c89589880841
 size 119975656

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:099dcb4361bb2049aa6db3b6e81a9f34b1202083b425b25c3af7c20f9259fe22
+oid sha256:4075ec4b36d7b30f8711cdc8411eb66cf7511268abac12ba6b2db316a1ee7dd7
 size 60477396

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:099feb85b2265fa46cec748072b982183c4dbb871e47eb59c01b10707a2a6958
+oid sha256:81db4d08b4f0905e940e600b34d55e9d49b371b457fe52a1dd9b0fc61bd94779
 size 14244

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c59c86cac1045db21cd2eb48ce1a34a6e8c676f8d6333a24ac6d07a63dbb2c3
+oid sha256:a95ec91bf6b79176b87aeb9e7899423b6eea55e3aa8c4701936014715782af7e
 size 1064

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.375,
+  "epoch": 0.4375,
   "eval_steps": 2500,
-  "global_step": 15000,
+  "global_step": 17500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -160,6 +160,28 @@
       "eval_samples_per_second": 4.954,
       "eval_steps_per_second": 4.954,
       "step": 15000
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 5.487946033477783,
+      "learning_rate": 1.1017971014492755e-05,
+      "loss": 1.3825,
+      "step": 16000
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 2.9339723587036133,
+      "learning_rate": 1.0438260869565218e-05,
+      "loss": 1.373,
+      "step": 17000
+    },
+    {
+      "epoch": 0.44,
+      "eval_loss": 1.371016263961792,
+      "eval_runtime": 201.6518,
+      "eval_samples_per_second": 4.959,
+      "eval_steps_per_second": 4.959,
+      "step": 17500
     }
   ],
   "logging_steps": 1000,
@@ -167,7 +189,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 2500,
-  "total_flos": 2.4153188990976e+17,
+  "total_flos": 2.8178720489472e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null