Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9615ab8102d7acf0c40c0342c6dffa028cdf5ba1b81cdec9276f116f2668f37
+oid sha256:7a1be63503f7a53a0f6c786dc2e69889f1f1f1077fef1c5a354c235385d5d7fd
 size 75507072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13fcaf331f38370d0848f3cbb5f9e35357835d50e4370abde901b2608a9e160f
+oid sha256:eccf00635b2d8d6cf67b85d7c0b6860e8e925974296be5a2120e0075099fb8ea
 size 151034437

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11be9bd2e974e04df9cfd0b6436e3d066bcab6217d1724e34d746d53a050a63d
+oid sha256:f4844b248bb8bc6625514d53ad7de0c9c14b2aad47aacb389b6b1780e4e27aac
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:216f76b8039f833c337db298c81f13b12082d5fd4f9d866cecd34b2ca7550b37
+oid sha256:7aa2c8b84e17817e6a4dcba5955fca913e266fdcd47f5594a29933ebd4972a01
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.631608486175537,
-  "best_model_checkpoint": "./outputs/checkpoint-100",
-  "epoch": 0.07285974499089254,
+  "best_metric": 1.5870035886764526,
+  "best_model_checkpoint": "./outputs/checkpoint-200",
+  "epoch": 0.14571948998178508,
   "eval_steps": 100,
-  "global_step": 100,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -21,13 +21,27 @@
       "eval_samples_per_second": 14.586,
       "eval_steps_per_second": 1.825,
       "step": 100
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0002,
+      "loss": 1.6077,
+      "step": 200
+    },
+    {
+      "epoch": 0.15,
+      "eval_loss": 1.5870035886764526,
+      "eval_runtime": 417.8578,
+      "eval_samples_per_second": 15.015,
+      "eval_steps_per_second": 1.879,
+      "step": 200
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 3.240742900390195e+16,
+  "total_flos": 6.481310369453568e+16,
   "trial_name": null,
   "trial_params": null
 }