Training in progress, step 1600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12d8d44bc5cb2da5a6d0f0bed03a7d35ba3cdd92cafdcfaa45ecaaa43a8f91ea
+oid sha256:3a7be9a0c9b109d1beb0f66c5b8277e133bea76fd1cd9dbf321f2d9882116bc9
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a9b3b3d6d175b27a5188b9184a30feb2c0b407580b749e4b283f6a22ae6e60b
+oid sha256:5292140616dff997e23de6744dbd35051326e4ef1ddc5d7b6c45c53d4dd42bf9
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ade3539adbe7197226065a369a265f6f0f1e7d107ccc3030d3acbbd888426eb0
+oid sha256:ca77415e638cf3b9d32978f227902748bb049cf3a40192fa31a73b897a1b66c8
 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": 2.2644264698028564,
-  "best_model_checkpoint": "./outputs/checkpoint-1500",
-  "epoch": 1.092896174863388,
+  "best_metric": 2.2463176250457764,
+  "best_model_checkpoint": "./outputs/checkpoint-1600",
+  "epoch": 1.1657559198542806,
   "eval_steps": 100,
-  "global_step": 1500,
+  "global_step": 1600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -217,13 +217,27 @@
       "eval_samples_per_second": 30.443,
       "eval_steps_per_second": 3.809,
       "step": 1500
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.0002,
+      "loss": 2.232,
+      "step": 1600
+    },
+    {
+      "epoch": 1.17,
+      "eval_loss": 2.2463176250457764,
+      "eval_runtime": 205.9251,
+      "eval_samples_per_second": 30.467,
+      "eval_steps_per_second": 3.812,
+      "step": 1600
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 4.412678068463616e+16,
+  "total_flos": 4.70673370653696e+16,
   "trial_name": null,
   "trial_params": null
 }