Training in progress, step 1700, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56d45a39849f9201859f4a53714dab79fc07ddbc7cb91d473f04d2cf07fbdcde
+oid sha256:e51f1f96b44ce86fbf1d64f1718ca95e39eb444009bcb0151220ee41471b79b1
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22c59d3ffe23d2bf61f637f3b9661fda7c87961d3b1f7c782aba5f444d9704ec
+oid sha256:636aeaa5e2d625a775a992ef2e7871fbe6cd8b31f1b7614dae873c0de1175fa7
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21058290b200caf979635695ca85070470640799fa7d0341ca6289f38b1cb4cb
+oid sha256:e70e901d59aad5639708bb0f13d15cb4f87186324b7acf9bdc81bd00942e078e
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcd2587f362188ac4728d4fa6edf8d2b0b6d72db365d49f7b847d4d79e3da09f
+oid sha256:0410ad60e6d0138b921a03b0a3e367fd27c6ab07cb9a5006fcb66ea8e5bbacc4
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.885960340499878,
-  "best_model_checkpoint": "./outputs/checkpoint-1600",
-  "epoch": 2.2727272727272725,
+  "best_metric": 1.8800793886184692,
+  "best_model_checkpoint": "./outputs/checkpoint-1700",
+  "epoch": 2.4147727272727275,
   "eval_steps": 100,
-  "global_step": 1600,
+  "global_step": 1700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -231,6 +231,20 @@
       "eval_samples_per_second": 19.884,
       "eval_steps_per_second": 2.492,
       "step": 1600
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 0.0002,
+      "loss": 1.9859,
+      "step": 1700
+    },
+    {
+      "epoch": 2.41,
+      "eval_loss": 1.8800793886184692,
+      "eval_runtime": 78.108,
+      "eval_samples_per_second": 19.102,
+      "eval_steps_per_second": 2.394,
+      "step": 1700
     }
   ],
   "logging_steps": 100,
@@ -238,7 +252,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 4.877824836261888e+16,
+  "total_flos": 5.178676400658432e+16,
   "trial_name": null,
   "trial_params": null
 }