Training in progress, step 700, checkpoint

last-checkpoint/adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca2a4b826a5666100d0a23e0d90047d8227d307dbf6a58eeccbfe348f0141a09
+oid sha256:65e3f0294ced8d1de2ebef27b12f72272de3dbfc736c1d286f95a8fc64a76834
 size 50349441

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13b5a14bd53f82f3086f52dfa2ae565823042bc3adbdabb38b03ef1d4e89e43a
+oid sha256:9591719d04e4ffe9c58684b2d8d99ec77ae80af301f541f8292a2cf8cb680fd3
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa942a2735f9e77fcdf287283c57bd6296771ce4bb160fffb501c94085817c55
+oid sha256:451a2106b4c24d69e8c55c73469acc51b69136bb9cd4cc4e5451d1be338a1eaf
 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": 1.7424511909484863,
-  "best_model_checkpoint": "./outputs/checkpoint-600",
-  "epoch": 0.4371584699453552,
+  "best_metric": 1.7112771272659302,
+  "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": 43.562,
       "eval_steps_per_second": 5.45,
       "step": 600
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0002,
+      "loss": 1.7176,
+      "step": 700
+    },
+    {
+      "epoch": 0.51,
+      "eval_loss": 1.7112771272659302,
+      "eval_runtime": 144.2204,
+      "eval_samples_per_second": 43.503,
+      "eval_steps_per_second": 5.443,
+      "step": 700
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 3.5797901188694016e+16,
+  "total_flos": 4.174060032521011e+16,
   "trial_name": null,
   "trial_params": null
 }