Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:740f80dcbedacdc51eba3c57b799d349b9d1ccbe0c19e678683a2fa3e14440d3
+oid sha256:707e9141ec886da0e6ed83ed0d7cdbfc8d57602e01753191e21913d219d1b7c6
 size 6298560

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c8ad5470ae68a25db6178f579118cfdc2c3c478c4eb58f1b5df7adc467b5319
+oid sha256:3ff1f1b47273d5c12f779fd8ae696d18f12f8d5cb1feb92f1d45a42261897af5
 size 12611145

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9569a82096629a4752f43390cc4d687d8747d343bb173c2c0aa596b7a3fc989e
+oid sha256:ab796cb22d1f99e1a64175a4124c719d63af93d54a8325b07b8b479b7426620f
 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": 1.2875007390975952,
-  "best_model_checkpoint": "./outputs/checkpoint-400",
-  "epoch": 0.5333333333333333,
+  "best_metric": 1.2735565900802612,
+  "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": 4.231,
       "eval_steps_per_second": 0.53,
       "step": 400
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0002,
+      "loss": 1.0562,
+      "step": 500
+    },
+    {
+      "epoch": 0.67,
+      "eval_loss": 1.2735565900802612,
+      "eval_runtime": 461.3936,
+      "eval_samples_per_second": 4.183,
+      "eval_steps_per_second": 0.524,
+      "step": 500
     }
   ],
   "logging_steps": 100,
@@ -70,7 +84,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.33237140701184e+16,
+  "total_flos": 1.6636259895410688e+16,
   "trial_name": null,
   "trial_params": null
 }