Training in progress, step 700, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:658704b0960cd8fb8a36f35a83a39b3fa3040ded1e6dc2e913e967aeb684a70f
+oid sha256:314671661e1779f4be9ba1e37d3f33640c3b7a3109ccde61bcaafc3a09c634f2
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c31dd5016db31342a454363b8de91f8d9cf183e4a8c778154c57c45fbb48611f
+oid sha256:557c7d0ebb0408821bdca91acba1bcd71dff8aea26d641f256bf7fee93a2b4da
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5e1dc5f769c4cbaa0ba676908c39cfb7cd49352afc3941d90d0685280366309
+oid sha256:db6358da13f324834878bd2b4485e5667664a0d92ed16a7f6a761dd9dea8cc65
 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": 2.4732720851898193,
-  "best_model_checkpoint": "./outputs/checkpoint-600",
-  "epoch": 0.4371584699453552,
+  "best_metric": 2.4523911476135254,
+  "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": 30.345,
       "eval_steps_per_second": 3.797,
       "step": 600
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0002,
+      "loss": 2.4509,
+      "step": 700
+    },
+    {
+      "epoch": 0.51,
+      "eval_loss": 2.4523911476135254,
+      "eval_runtime": 206.8041,
+      "eval_samples_per_second": 30.338,
+      "eval_steps_per_second": 3.796,
+      "step": 700
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.752346796949504e+16,
+  "total_flos": 2.042513200078848e+16,
   "trial_name": null,
   "trial_params": null
 }