Training in progress, step 2900, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd0e2bd8d8e10f97f3353032dab792c5ef7dfb51f92e71a27b03914feafdb2fc
+oid sha256:ba8c6b49c9b8776d8fa9734fcfa1d344263eb37301aaa74df8f4ac32f816215c
 size 31466288

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8097b657d12b779bfe84dc4576f72eaf299b8f4f8d6e51df0a753cbc30227a9
+oid sha256:33bf614459aa886d7f42cd2e6107e5625b3d91b219a1c249ff2b58525e8daa70
 size 62950917

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:944725f5846a061a9cf95ad40915b85f42f52686b7894054faae01c1082a5042
+oid sha256:0340d4911a993658f9871059b3f1911f3f1227a4050f7280c82fa19df52394e3
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee2eceee28d7a299780008f817c050eb9e87b0d18fb8d8f19062cda68b3e10f9
+oid sha256:097f95efaf3ced711759e9e49c3b8b3ef906ff28483e958d227db85b3ea360b9
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.3847733736038208,
-  "best_model_checkpoint": "./outputs/checkpoint-2600",
-  "epoch": 1.8943533697632058,
+  "best_metric": 1.3265427350997925,
+  "best_model_checkpoint": "./outputs/checkpoint-2900",
+  "epoch": 2.1129326047358834,
   "eval_steps": 100,
-  "global_step": 2600,
+  "global_step": 2900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -371,13 +371,55 @@
       "eval_samples_per_second": 11.268,
       "eval_steps_per_second": 1.41,
       "step": 2600
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 0.0002,
+      "loss": 1.3487,
+      "step": 2700
+    },
+    {
+      "epoch": 1.97,
+      "eval_loss": 1.3603800535202026,
+      "eval_runtime": 556.2959,
+      "eval_samples_per_second": 11.278,
+      "eval_steps_per_second": 1.411,
+      "step": 2700
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 0.0002,
+      "loss": 1.2769,
+      "step": 2800
+    },
+    {
+      "epoch": 2.04,
+      "eval_loss": 1.3475805521011353,
+      "eval_runtime": 556.1265,
+      "eval_samples_per_second": 11.282,
+      "eval_steps_per_second": 1.412,
+      "step": 2800
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 0.0002,
+      "loss": 1.226,
+      "step": 2900
+    },
+    {
+      "epoch": 2.11,
+      "eval_loss": 1.3265427350997925,
+      "eval_runtime": 555.0977,
+      "eval_samples_per_second": 11.303,
+      "eval_steps_per_second": 1.414,
+      "step": 2900
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 6.77331627764564e+17,
+  "total_flos": 7.548286956953272e+17,
   "trial_name": null,
   "trial_params": null
 }