Training in progress, step 2100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3d150927f0fbbecdc9f0fdaf18eb1f70b5f0df32c477b999d7a0863a3df2b85
+oid sha256:b57764bb5b3811570abc732e72629d9f86dbe79fc44543b3738057e9e88bd1f6
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a51baf271a0ffff2b328c6ab56bbd6d3a4956d41a88bd2507057a156c394c896
+oid sha256:ac2ef5c9cd75faba73e1013f6fc3af086d99275b8847c3f937ed81ff2b876f40
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:613209fe19785aab62e1f8fb807af95ea3ab972ed7fc7b2d61958367dc06f82c
+oid sha256:5475b1ce7a4d7950d1b1c1234e4bd9b06df23ed931dac1d75f24c3fa63c2c513
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:720bafe9a34b3041027dccef7d9c03bb23064e1fcdd80ae5f27e717d41b7cf31
+oid sha256:b1238b3bfa75e49a19396161e9e7b72ab89cdd1a3f63b51c0ab4d6e8d216c5a5
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.28745436668396,
-  "best_model_checkpoint": "./outputs/checkpoint-2000",
-  "epoch": 1.4571948998178508,
+  "best_metric": 2.273569107055664,
+  "best_model_checkpoint": "./outputs/checkpoint-2100",
+  "epoch": 1.530054644808743,
   "eval_steps": 100,
-  "global_step": 2000,
+  "global_step": 2100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -287,13 +287,27 @@
       "eval_samples_per_second": 30.602,
       "eval_steps_per_second": 3.829,
       "step": 2000
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 0.0002,
+      "loss": 2.2577,
+      "step": 2100
+    },
+    {
+      "epoch": 1.53,
+      "eval_loss": 2.273569107055664,
+      "eval_runtime": 205.4686,
+      "eval_samples_per_second": 30.535,
+      "eval_steps_per_second": 3.821,
+      "step": 2100
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 5.70422421531648e+16,
+  "total_flos": 5.987678208325632e+16,
   "trial_name": null,
   "trial_params": null
 }