Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc001b96856608ce2d9f6e817c93bc0927aaaf61e9e3d37a1fbb7feaa7a6f771
+oid sha256:5ccd62b779e31a9e0f81b74a773eaa0c658e750fa8d9604edabc7f9807b687a0
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a555458b509cebd0a7664e6d050b6098cdb0892b55621d349d92e1a06fc9ac75
+oid sha256:5d2b1fb8faf93203bfa23b694242ee971b02d2b858005f0adf558fb264e03357
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4f1181e0e3e2c9c9c4867f3c8fa0bba665e663473833a2ab7b385cf778c0261
+oid sha256:16429469a49bff10e4c592f3a9a29ce1bd33c24708692eafba2bae5fee5e8095
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13276f15dd2b6acc19b970176aa2db4ac9b58241843e72c89b50e3094e903b19
+oid sha256:5efc416a6883409dd7ab6f5c779e107c7c2baa7af6e12ed9fbd9dd73b8b20784
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.1916158199310303,
-  "best_model_checkpoint": "./outputs/checkpoint-400",
-  "epoch": 0.5333333333333333,
+  "best_metric": 1.1772679090499878,
+  "best_model_checkpoint": "./outputs/checkpoint-500",
+  "epoch": 0.6666666666666666,
   "eval_steps": 100,
-  "global_step": 400,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -63,6 +63,20 @@
       "eval_samples_per_second": 10.874,
       "eval_steps_per_second": 1.363,
       "step": 400
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0002,
+      "loss": 0.9773,
+      "step": 500
+    },
+    {
+      "epoch": 0.67,
+      "eval_loss": 1.1772679090499878,
+      "eval_runtime": 193.3709,
+      "eval_samples_per_second": 9.981,
+      "eval_steps_per_second": 1.251,
+      "step": 500
     }
   ],
   "logging_steps": 100,
@@ -70,7 +84,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.9915995189248e+16,
+  "total_flos": 3.735371896897536e+16,
   "trial_name": null,
   "trial_params": null
 }