Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65be35c1b2bc26ba83615857e2df5d9921e874ca79072e4666d7c2015ddf64dc
+oid sha256:ef2c8347f1be9aebfc1271f5f427065d90f0e50efb3a58333837af0c92cfabd6
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db17a9c3f1ce8cdb2557846c2c3b026cef52042b764f92855950568f5cf76ad5
+oid sha256:2323219fe41e5b63b7d472b1ca12c211f60c05cc1bc4517c5ee44eb63d4d78ba
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acccb40364c81f60954b209e58ded29513bb5cbed178abd7a3865401a970666f
+oid sha256:bbebb324d09ed3b79588ce704d8e867cae0d7b652313decf15a03bfb1ba6792e
 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": 2.0298001766204834,
-  "best_model_checkpoint": "./outputs/checkpoint-400",
-  "epoch": 0.5681818181818182,
+  "best_metric": 2.005772113800049,
+  "best_model_checkpoint": "./outputs/checkpoint-500",
+  "epoch": 0.7102272727272727,
   "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": 27.594,
       "eval_steps_per_second": 3.459,
       "step": 400
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0002,
+      "loss": 2.1704,
+      "step": 500
+    },
+    {
+      "epoch": 0.71,
+      "eval_loss": 2.005772113800049,
+      "eval_runtime": 54.1197,
+      "eval_samples_per_second": 27.569,
+      "eval_steps_per_second": 3.455,
+      "step": 500
     }
   ],
   "logging_steps": 100,
@@ -70,7 +84,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.21510343872512e+16,
+  "total_flos": 1.52069905096704e+16,
   "trial_name": null,
   "trial_params": null
 }