Training in progress, step 600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3d2315e33bc525bbe5675682c58b3ede77b52403224cbd3771dd7c97823feca
+oid sha256:4edbb76ba7594bd2a1d16ac45feb724118fb5b665706abfd2b0b14292dfc8321
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:350fab16db68303418646f37a3c86cdabe1c0046a7ea290c25893eaf039335b7
+oid sha256:030ef5db8c4e28d8673d9b83f0d158c86f1db49c1f13ead8ee1fc20ff0c2c170
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d956bbe29389d803201f795b58c63ed565fec24e0e84b4e6a37f67b9223d2da
+oid sha256:14b343a857d99bd246e949ce43fa154be57572a92bfe8faaab5d1699d6c3d851
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5efc416a6883409dd7ab6f5c779e107c7c2baa7af6e12ed9fbd9dd73b8b20784
+oid sha256:9c1a2ac1c11599601eeac95feb1dbfd49ec5c625e61dcce18b3f094491f9cf2d
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.0150375366210938,
-  "best_model_checkpoint": "./outputs/checkpoint-500",
-  "epoch": 0.7102272727272727,
+  "best_metric": 1.9949842691421509,
+  "best_model_checkpoint": "./outputs/checkpoint-600",
+  "epoch": 0.8522727272727273,
   "eval_steps": 100,
-  "global_step": 500,
+  "global_step": 600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -77,6 +77,20 @@
       "eval_samples_per_second": 27.78,
       "eval_steps_per_second": 3.482,
       "step": 500
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.0002,
+      "loss": 2.1648,
+      "step": 600
+    },
+    {
+      "epoch": 0.85,
+      "eval_loss": 1.9949842691421509,
+      "eval_runtime": 53.6059,
+      "eval_samples_per_second": 27.833,
+      "eval_steps_per_second": 3.488,
+      "step": 600
     }
   ],
   "logging_steps": 100,
@@ -84,7 +98,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.51321534414848e+16,
+  "total_flos": 1.8159861436416e+16,
   "trial_name": null,
   "trial_params": null
 }