Training in progress, step 700, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be43f34602bb0b1e78f12f20303870ddf509450d43057fe05fb7d102f30ef4dc
+oid sha256:5d2996db00ecc3c5c253ea1a0ab8d1c3b6bb640a5140dc05cc843d9bb6e5f283
 size 6304192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abb5df1246bfeccb8956222c5dd783e076afe72c2c2b2b9df2d1bc87b14cde93
+oid sha256:31e5e71fc67ade3e7de5cf84c7350522ff4dd271b5d8127728966a8f8819fa50
 size 12639429

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:354336e3d2096475e2dbe89576e77c5e214cdcb69bb19ba1dc01b08c50a83b5a
+oid sha256:fd8dd7793a5701b64cff4ece571f2d331ce025868e37b09362177387e1ab6cc1
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c1a2ac1c11599601eeac95feb1dbfd49ec5c625e61dcce18b3f094491f9cf2d
+oid sha256:30423cc69a1c7d18caef4643847588d5884db012263cbe7b7224fa4719ca4156
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2814782857894897,
-  "best_model_checkpoint": "./outputs/checkpoint-600",
-  "epoch": 0.8,
+  "best_metric": 1.2781809568405151,
+  "best_model_checkpoint": "./outputs/checkpoint-700",
+  "epoch": 0.9333333333333333,
   "eval_steps": 100,
-  "global_step": 600,
+  "global_step": 700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -91,6 +91,20 @@
       "eval_samples_per_second": 15.316,
       "eval_steps_per_second": 1.92,
       "step": 600
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0002,
+      "loss": 1.1083,
+      "step": 700
+    },
+    {
+      "epoch": 0.93,
+      "eval_loss": 1.2781809568405151,
+      "eval_runtime": 126.2703,
+      "eval_samples_per_second": 15.285,
+      "eval_steps_per_second": 1.917,
+      "step": 700
     }
   ],
   "logging_steps": 100,
@@ -98,7 +112,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.126816116772045e+16,
+  "total_flos": 2.482400846458061e+16,
   "trial_name": null,
   "trial_params": null
 }