Training in progress, step 1700, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f59f0cf83e4db419fe2b090fc5f55ab362a0128e394afeb591fee97c08e5b9af
+oid sha256:8c2f1f9f8e818afd15a7f4f977341e59613b94da75de555537ba5a0b0b59c38a
 size 25191576

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:948d9361e315dab0cb6adbd60b51d5fb9bf89f16118140c803cede14410a1e5c
+oid sha256:cca1d285fd02b926f643a2dc2b51ca848337d4594364248881acd4e05e9dfc47
 size 50444805

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d880e5bb61f695737bb8ab52d42681f045639984678ecc79e639583358afa74
+oid sha256:0eb73b134a129617820e93a4630f6c7e447cc6d5f8021ee7120ae17f44e4c73e
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcd2587f362188ac4728d4fa6edf8d2b0b6d72db365d49f7b847d4d79e3da09f
+oid sha256:0410ad60e6d0138b921a03b0a3e367fd27c6ab07cb9a5006fcb66ea8e5bbacc4
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.9801864624023438,
-  "best_model_checkpoint": "./outputs/checkpoint-1600",
-  "epoch": 2.1333333333333333,
+  "best_metric": 0.9756149649620056,
+  "best_model_checkpoint": "./outputs/checkpoint-1700",
+  "epoch": 2.2666666666666666,
   "eval_steps": 100,
-  "global_step": 1600,
+  "global_step": 1700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -231,6 +231,20 @@
       "eval_samples_per_second": 5.449,
       "eval_steps_per_second": 0.683,
       "step": 1600
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 0.0002,
+      "loss": 0.8414,
+      "step": 1700
+    },
+    {
+      "epoch": 2.27,
+      "eval_loss": 0.9756149649620056,
+      "eval_runtime": 353.6981,
+      "eval_samples_per_second": 5.457,
+      "eval_steps_per_second": 0.684,
+      "step": 1700
     }
   ],
   "logging_steps": 100,
@@ -238,7 +252,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 4.523634737775329e+17,
+  "total_flos": 4.807017024378716e+17,
   "trial_name": null,
   "trial_params": null
 }