Training in progress, step 700, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01a7f69327d0024b24ca4ed51941c318f1fcbb752ff023875cfd2555eb1d6369
+oid sha256:207b0f93334913f1d85a200490bf415cb7cc3d623c0827fc64386b06007481de
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5390d4be9fcf3c2edc2b58c9fbed59fe6b5b28381ee247eeca9a1370a2ee0abd
+oid sha256:6c3ac062c2696643ce5b31bd8ac6d6654ff117c7f45bee59c8aaeeeb8fc00714
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a419c8171381ef52bb95c0db9d7dc0f3373840624ba9300b663743186a3ad699
+oid sha256:8662557b50cc51438eaa14c2b2a247b688b19166e0ce09334733e3489595dd32
 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": 1.0142004489898682,
-  "best_model_checkpoint": "./outputs/checkpoint-600",
-  "epoch": 0.8522727272727273,
+  "best_metric": 1.0080314874649048,
+  "best_model_checkpoint": "./outputs/checkpoint-700",
+  "epoch": 0.9943181818181818,
   "eval_steps": 100,
-  "global_step": 600,
+  "global_step": 700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -91,6 +91,20 @@
       "eval_samples_per_second": 12.007,
       "eval_steps_per_second": 1.505,
       "step": 600
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.0002,
+      "loss": 1.1492,
+      "step": 700
+    },
+    {
+      "epoch": 0.99,
+      "eval_loss": 1.0080314874649048,
+      "eval_runtime": 124.2662,
+      "eval_samples_per_second": 12.006,
+      "eval_steps_per_second": 1.505,
+      "step": 700
     }
   ],
   "logging_steps": 100,
@@ -98,7 +112,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 3.370874435518464e+16,
+  "total_flos": 3.933519820038144e+16,
   "trial_name": null,
   "trial_params": null
 }