Training in progress, step 1600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f404772dbfc6484d56cf268fff416e4d99e924bf618a5f6fd70db14e446a6cb7
+oid sha256:d67b6d1e5ac08c55ca272dae5cef94538203ca81a7fd6189cc24a85e8020af1d
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36e4af8591c9cb3e6471099476e46f360f01ef2b76ecc78b87b06ab70991b090
+oid sha256:05dae8539f5c93edb2c67fdaaadbb3ffc382a05d59552d72ef43583b1403bbd1
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33e9f79b5682cc7de6c19637ae4bc96dff9f33f94a98cd0c93f9b811cc4e7411
+oid sha256:59436ee7d20f5ba0ec694086a8e3e4769ad9219178f69a9c92d3d97e58bb26b2
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d397c26ac1ddd7670b9ddd8b909580a771b707ad5b586b657ad627e8bc4e787f
+oid sha256:fcd2587f362188ac4728d4fa6edf8d2b0b6d72db365d49f7b847d4d79e3da09f
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.3967318534851074,
-  "best_model_checkpoint": "./outputs/checkpoint-1500",
-  "epoch": 2.0,
+  "best_metric": 1.3913403749465942,
+  "best_model_checkpoint": "./outputs/checkpoint-1600",
+  "epoch": 2.1333333333333333,
   "eval_steps": 100,
-  "global_step": 1500,
+  "global_step": 1600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -217,6 +217,20 @@
       "eval_samples_per_second": 15.554,
       "eval_steps_per_second": 1.951,
       "step": 1500
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 0.0002,
+      "loss": 1.1462,
+      "step": 1600
+    },
+    {
+      "epoch": 2.13,
+      "eval_loss": 1.3913403749465942,
+      "eval_runtime": 93.297,
+      "eval_samples_per_second": 15.552,
+      "eval_steps_per_second": 1.951,
+      "step": 1600
     }
   ],
   "logging_steps": 100,
@@ -224,7 +238,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 8.770169121251328e+16,
+  "total_flos": 9.356583872176128e+16,
   "trial_name": null,
   "trial_params": null
 }