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:b3c640cec8e45c2c2a3a67c2ad8fbe397b4323a2d9d24327def8e3830cb6c35e
+oid sha256:40836a859b2cdb7b8277d38e75ae6a3e3b1af4560318b7a45e6b5828b1a17d4d
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6921e0460bab0880b2cd1e37cc02fdf15ce6a7d0101180ac51463d6f169ed46
+oid sha256:5e231fe7841d08f0fcbec5c9e0801379a00de3ae16a076fcaec79eab59a36faa
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a37b20fb123df82ce7439a8a4fe878c98f20fd90e4b8f892214d734f93311746
+oid sha256:3cfaf422c3607cab8ab925751360ef6b2209d09d20c7d5a51cd9f13ec5aa92b2
 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": 0.9676819443702698,
-  "best_model_checkpoint": "./outputs/checkpoint-1400",
-  "epoch": 1.9886363636363638,
+  "best_metric": 0.9654238224029541,
+  "best_model_checkpoint": "./outputs/checkpoint-1500",
+  "epoch": 2.1306818181818183,
   "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": 12.439,
       "eval_steps_per_second": 1.559,
       "step": 1400
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 0.0002,
+      "loss": 1.08,
+      "step": 1500
+    },
+    {
+      "epoch": 2.13,
+      "eval_loss": 0.9654238224029541,
+      "eval_runtime": 120.0799,
+      "eval_samples_per_second": 12.425,
+      "eval_steps_per_second": 1.557,
+      "step": 1500
     }
   ],
   "logging_steps": 100,
@@ -210,7 +224,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 7.869951653566464e+16,
+  "total_flos": 8.435041115203584e+16,
   "trial_name": null,
   "trial_params": null
 }