Training in progress, step 4100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67fb2641a47847de545739fa9bf331cc86382b9efd2c9bde87633e135625555f
+oid sha256:b71adc56914fcfba3ce48ee620374d3baeb303963254ec685f2e87a69138ec91
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc3cc469c5109a2b089c90098e5ec399489d763128d9b4b4f6ebef13c7d76fa3
+oid sha256:ebc096ce296334fd1391d73a942fdefcb2747828c5bc4568f3206160abef12f8
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8993bfd358e6597f1a1d1729c472a0ff6be3dbbb3d5625584e41e187526fa017
+oid sha256:9856e2e59e51e8b31fe193001ecb6bae6f81f91a485646dec0453febb0bf7275
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ab644d38b64875fe4b9db6a2dd788efbee5d9e5dadfabf0dd125e8dae428442
+oid sha256:1ef51ed05818f33aebca9592cb64baf0df006aad2a34a7cf944f4a48b70afce3
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.3191989660263062,
-  "best_model_checkpoint": "./outputs/checkpoint-4000",
-  "epoch": 2.9143897996357016,
+  "best_metric": 1.305527687072754,
+  "best_model_checkpoint": "./outputs/checkpoint-4100",
+  "epoch": 2.987249544626594,
   "eval_steps": 100,
-  "global_step": 4000,
+  "global_step": 4100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -567,13 +567,27 @@
       "eval_samples_per_second": 43.69,
       "eval_steps_per_second": 5.466,
       "step": 4000
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 0.0002,
+      "loss": 1.2951,
+      "step": 4100
+    },
+    {
+      "epoch": 2.99,
+      "eval_loss": 1.305527687072754,
+      "eval_runtime": 143.5824,
+      "eval_samples_per_second": 43.696,
+      "eval_steps_per_second": 5.467,
+      "step": 4100
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.3815364444912026e+17,
+  "total_flos": 2.4412550549623603e+17,
   "trial_name": null,
   "trial_params": null
 }