Training in progress, step 1600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f07c10f4dca771f6ef4aed098b257078b29bcda188ad2ccb555a4f0a736ce63
+oid sha256:a612ba147b180eafae3fb0c222b42306eb2e0e70418fc23d8036cdd11ccf5451
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11483cbb5186f10c49bbfd7e8a9fddd6522bda58b0a3908000aef6661f0c7d98
+oid sha256:377ccfd27dded3caa1e332796359ffc75c68eac4c39973e3db1a3812241a2f44
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e878fc0fbc86334888140425f50a172daf0ca6c9b8e00f870566985c8b9eac8
+oid sha256:63416c461104e18e6f2dc58027f2f497f343071f984012e0153e5a8ba969515d
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1351871b6e069a7a4437616d40b913152ecc2cd046e996fcfeb300a3cf60638
+oid sha256:fcd2587f362188ac4728d4fa6edf8d2b0b6d72db365d49f7b847d4d79e3da09f
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.381305694580078,
-  "best_model_checkpoint": "./outputs/checkpoint-1400",
-  "epoch": 1.0200364298724955,
+  "best_metric": 2.3456737995147705,
+  "best_model_checkpoint": "./outputs/checkpoint-1600",
+  "epoch": 1.1657559198542806,
   "eval_steps": 100,
-  "global_step": 1400,
+  "global_step": 1600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -203,13 +203,41 @@
       "eval_samples_per_second": 30.684,
       "eval_steps_per_second": 3.839,
       "step": 1400
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.0002,
+      "loss": 2.3396,
+      "step": 1500
+    },
+    {
+      "epoch": 1.09,
+      "eval_loss": 2.3646771907806396,
+      "eval_runtime": 204.6348,
+      "eval_samples_per_second": 30.659,
+      "eval_steps_per_second": 3.836,
+      "step": 1500
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.0002,
+      "loss": 2.3327,
+      "step": 1600
+    },
+    {
+      "epoch": 1.17,
+      "eval_loss": 2.3456737995147705,
+      "eval_runtime": 204.4826,
+      "eval_samples_per_second": 30.682,
+      "eval_steps_per_second": 3.839,
+      "step": 1600
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 3.994021987006464e+16,
+  "total_flos": 4.564478592866304e+16,
   "trial_name": null,
   "trial_params": null
 }