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:e4a390625c5a0b45524ce5c107505323b7b11577af61c6b912fd1d133677eef2
+oid sha256:682eee2933dcbb1011fec9ab30eb99c2f76905b374aad78d82ef51793b2ddfab
 size 12595704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67692472b15ddd6e34ccfa3e44e8b562831e32dc7bc560580bd8c5cd26bc2dd9
+oid sha256:48b8fc50410b4e4848c3fefdd6aafe8e8ad69ec9ee4b27bddfcd3e8a57ed3bdf
 size 25222341

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3fba0bf8a4807b4cc9ec083d75ccc64f6405a9dce2113d7d3112534da857918
+oid sha256:f3f369c633e7cdbde61c687a519838babc30351943278707f66364f3dc85d9c5
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d397c26ac1ddd7670b9ddd8b909580a771b707ad5b586b657ad627e8bc4e787f
+oid sha256:fcd2587f362188ac4728d4fa6edf8d2b0b6d72db365d49f7b847d4d79e3da09f
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.0845235586166382,
-  "best_model_checkpoint": "./outputs/checkpoint-1500",
-  "epoch": 2.0,
+  "best_metric": 1.0820677280426025,
+  "best_model_checkpoint": "./outputs/checkpoint-1600",
+  "epoch": 2.1333333333333333,
   "eval_steps": 100,
-  "global_step": 1500,
+  "global_step": 1600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -217,6 +217,20 @@
       "eval_samples_per_second": 10.364,
       "eval_steps_per_second": 1.3,
       "step": 1500
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 0.0002,
+      "loss": 0.9329,
+      "step": 1600
+    },
+    {
+      "epoch": 2.13,
+      "eval_loss": 1.0820677280426025,
+      "eval_runtime": 187.4263,
+      "eval_samples_per_second": 10.297,
+      "eval_steps_per_second": 1.291,
+      "step": 1600
     }
   ],
   "logging_steps": 100,
@@ -224,7 +238,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.1203973628956672e+17,
+  "total_flos": 2.2614230595981312e+17,
   "trial_name": null,
   "trial_params": null
 }