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:c71b88b8d6e19a9eea83b71bc0570c31f070e7bb59806ad27ece6a1eba57eb6e
+oid sha256:dbd39041ce5083ca4c15e2f40183d48b2330b0f6df97a4687e7836a843f29a98
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b1b1313a7678283925ccbff97dea2fa074a7043265000ed1208f05ae7bf7b11
+oid sha256:b5450c59cf8adbf80e9318b1bea92e63ca74fd7d7314b61306a4f389197619d3
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ff5af48530f4550cd16476eb97c9d3b0a2fbd3235f2203be2913691b5a5e0e2
+oid sha256:836b92a3bc8c991adee049fba1895711a4f510235c95414c287849672ddf25b0
 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": 1.755702018737793,
-  "best_model_checkpoint": "./outputs/checkpoint-600",
-  "epoch": 0.4371584699453552,
+  "best_metric": 1.7235804796218872,
+  "best_model_checkpoint": "./outputs/checkpoint-700",
+  "epoch": 0.5100182149362478,
   "eval_steps": 100,
-  "global_step": 600,
+  "global_step": 700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -91,13 +91,27 @@
       "eval_samples_per_second": 43.686,
       "eval_steps_per_second": 5.466,
       "step": 600
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0002,
+      "loss": 1.7302,
+      "step": 700
+    },
+    {
+      "epoch": 0.51,
+      "eval_loss": 1.7235804796218872,
+      "eval_runtime": 143.5461,
+      "eval_samples_per_second": 43.707,
+      "eval_steps_per_second": 5.469,
+      "step": 700
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 3.579456002506752e+16,
+  "total_flos": 4.17362919826391e+16,
   "trial_name": null,
   "trial_params": null
 }