Training in progress, step 600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36d47cba5d8dfc1a4316dcf1892101b71c238a74b798d4e103d0d45fbedc68e3
+oid sha256:c71b88b8d6e19a9eea83b71bc0570c31f070e7bb59806ad27ece6a1eba57eb6e
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a372a7ae2e840ea66a794672e1d9701c591c56244fc7a51fa1ea1a109dfab69
+oid sha256:8b1b1313a7678283925ccbff97dea2fa074a7043265000ed1208f05ae7bf7b11
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1585afb4bb5c414a38503027658037a96267ad2845903b5a78a03fb0cbe9f594
+oid sha256:4ff5af48530f4550cd16476eb97c9d3b0a2fbd3235f2203be2913691b5a5e0e2
 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": 1.7833176851272583,
-  "best_model_checkpoint": "./outputs/checkpoint-500",
-  "epoch": 0.36429872495446264,
+  "best_metric": 1.755702018737793,
+  "best_model_checkpoint": "./outputs/checkpoint-600",
+  "epoch": 0.4371584699453552,
   "eval_steps": 100,
-  "global_step": 500,
+  "global_step": 600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -77,13 +77,27 @@
       "eval_samples_per_second": 43.658,
       "eval_steps_per_second": 5.462,
       "step": 500
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0002,
+      "loss": 1.769,
+      "step": 600
+    },
+    {
+      "epoch": 0.44,
+      "eval_loss": 1.755702018737793,
+      "eval_runtime": 143.6171,
+      "eval_samples_per_second": 43.686,
+      "eval_steps_per_second": 5.466,
+      "step": 600
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.983213629977395e+16,
+  "total_flos": 3.579456002506752e+16,
   "trial_name": null,
   "trial_params": null
 }