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:a612ba147b180eafae3fb0c222b42306eb2e0e70418fc23d8036cdd11ccf5451
+oid sha256:3a374f3110a413584b10458e51dc4a09437a30c3ac88fc255903585a27c43651
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:377ccfd27dded3caa1e332796359ffc75c68eac4c39973e3db1a3812241a2f44
+oid sha256:f859e27e55bafc9eb51e3f452f8259313a6d46ecda8228a1e377f224d97ae00b
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63416c461104e18e6f2dc58027f2f497f343071f984012e0153e5a8ba969515d
+oid sha256:42d82cefe3dbce05d21cd31fd65135b0f507fa0308fd19dcaa91f644308efc23
 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": 2.3456737995147705,
-  "best_model_checkpoint": "./outputs/checkpoint-1600",
-  "epoch": 1.1657559198542806,
+  "best_metric": 2.329716920852661,
+  "best_model_checkpoint": "./outputs/checkpoint-1700",
+  "epoch": 1.238615664845173,
   "eval_steps": 100,
-  "global_step": 1600,
+  "global_step": 1700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -231,13 +231,27 @@
       "eval_samples_per_second": 30.682,
       "eval_steps_per_second": 3.839,
       "step": 1600
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.0002,
+      "loss": 2.3308,
+      "step": 1700
+    },
+    {
+      "epoch": 1.24,
+      "eval_loss": 2.329716920852661,
+      "eval_runtime": 204.6937,
+      "eval_samples_per_second": 30.651,
+      "eval_steps_per_second": 3.835,
+      "step": 1700
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 4.564478592866304e+16,
+  "total_flos": 4.850935894038528e+16,
   "trial_name": null,
   "trial_params": null
 }