Training in progress, step 1500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0fef1db67ac977720c047d252588fd18bef0cb290d28e1d9d058df5c23bc9b4
+oid sha256:e4a390625c5a0b45524ce5c107505323b7b11577af61c6b912fd1d133677eef2
 size 12595704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a081813ee762e60a4e3208448a1b83529283fad9ecea44e13ab242ba0ee3455
+oid sha256:67692472b15ddd6e34ccfa3e44e8b562831e32dc7bc560580bd8c5cd26bc2dd9
 size 25222341

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e30e6ed91bf92efee6b0b2958ad13a151734e9702f0b270a999e923840ecdad3
+oid sha256:f3fba0bf8a4807b4cc9ec083d75ccc64f6405a9dce2113d7d3112534da857918
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1351871b6e069a7a4437616d40b913152ecc2cd046e996fcfeb300a3cf60638
+oid sha256:d397c26ac1ddd7670b9ddd8b909580a771b707ad5b586b657ad627e8bc4e787f
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.0864734649658203,
-  "best_model_checkpoint": "./outputs/checkpoint-1400",
-  "epoch": 1.8666666666666667,
+  "best_metric": 1.0845235586166382,
+  "best_model_checkpoint": "./outputs/checkpoint-1500",
+  "epoch": 2.0,
   "eval_steps": 100,
-  "global_step": 1400,
+  "global_step": 1500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -203,6 +203,20 @@
       "eval_samples_per_second": 10.351,
       "eval_steps_per_second": 1.298,
       "step": 1400
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.0002,
+      "loss": 0.9357,
+      "step": 1500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.0845235586166382,
+      "eval_runtime": 186.2213,
+      "eval_samples_per_second": 10.364,
+      "eval_steps_per_second": 1.3,
+      "step": 1500
     }
   ],
   "logging_steps": 100,
@@ -210,7 +224,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.9793785004539085e+17,
+  "total_flos": 2.1203973628956672e+17,
   "trial_name": null,
   "trial_params": null
 }