Training in progress, step 900, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1437ab9c205f3c6289456bd0eedb93f8c33a13345c2cbd131f8eb95272b80839
+oid sha256:1598db6815cce8da8d1dc394e43fcebca4d9aa417bcd21a82d30023699f62fc8
 size 19669752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96a45b512adaad4c9a9163be5c9a27e03c592347d8d527827267be50339b9108
+oid sha256:fb3d6d8c199ca4b86ef9e94549c0dc43d280e6baecb11a0d5c6864032441a0ba
 size 39357829

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cca3a7099dea147630d4f997ed815413f0ae73f258d866a6a2fb054f2568bdf7
+oid sha256:54a53c8f742c7e589aef35625eb91430169408462122ef08e6057a865fba54c3
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de7840bcb72f2f480fd301578d289cdfa174589e831b0d33e5772f3956b6beae
+oid sha256:a3c39113390004215769b6e7fbe73f1073dd2faa3ab8f9ff815b62e9c2f80c82
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.0014097690582275,
-  "best_model_checkpoint": "./outputs/checkpoint-800",
-  "epoch": 1.0666666666666667,
+  "best_metric": 0.9944414496421814,
+  "best_model_checkpoint": "./outputs/checkpoint-900",
+  "epoch": 1.2,
   "eval_steps": 100,
-  "global_step": 800,
+  "global_step": 900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -119,6 +119,20 @@
       "eval_samples_per_second": 2.655,
       "eval_steps_per_second": 0.333,
       "step": 800
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.0002,
+      "loss": 0.814,
+      "step": 900
+    },
+    {
+      "epoch": 1.2,
+      "eval_loss": 0.9944414496421814,
+      "eval_runtime": 729.3383,
+      "eval_samples_per_second": 2.646,
+      "eval_steps_per_second": 0.332,
+      "step": 900
     }
   ],
   "logging_steps": 100,
@@ -126,7 +140,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.0717810165526528e+17,
+  "total_flos": 2.3315525439270912e+17,
   "trial_name": null,
   "trial_params": null
 }