Training in progress, step 1500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4374d344de0ba51b7d2da3fa14ad1ef770c2570cfe6e34a52ffdf5406cb05aec
+oid sha256:df6497b7be986e3959a3bb61600f9c868a5176d599b5978403300eea8a1f1bb0
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8490cb2546fb02532974d34abd0a68c1d70d1cc5d3cd76fdc4149e7ffc1369c1
+oid sha256:f967d6c2e0720085918146fc8b6abd1d0dd6b28f4e9e67250cb1c8f2d57c1b89
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bf486cfe029ef0ab8a98b96c403d9e9430e33b47c3ce9bc8a9e6c2e5289a2e4
+oid sha256:5e54cd928882c59a21f0f9d6da59404bb91fe271db4a26152a1f7f27631b55a7
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1351871b6e069a7a4437616d40b913152ecc2cd046e996fcfeb300a3cf60638
+oid sha256:d397c26ac1ddd7670b9ddd8b909580a771b707ad5b586b657ad627e8bc4e787f
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.3096227645874023,
-  "best_model_checkpoint": "./outputs/checkpoint-1400",
-  "epoch": 1.8666666666666667,
+  "best_metric": 1.3063220977783203,
+  "best_model_checkpoint": "./outputs/checkpoint-1500",
+  "epoch": 2.0,
   "eval_steps": 100,
-  "global_step": 1400,
+  "global_step": 1500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -203,6 +203,20 @@
       "eval_samples_per_second": 12.914,
       "eval_steps_per_second": 1.62,
       "step": 1400
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.0002,
+      "loss": 1.0778,
+      "step": 1500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.3063220977783203,
+      "eval_runtime": 112.5325,
+      "eval_samples_per_second": 12.894,
+      "eval_steps_per_second": 1.617,
+      "step": 1500
     }
   ],
   "logging_steps": 100,
@@ -210,7 +224,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 8.902643832520704e+16,
+  "total_flos": 9.54245491347456e+16,
   "trial_name": null,
   "trial_params": null
 }