Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ad106a6741fcc7140bf2703855b87ba0005edcda6f3e322645cd84e39d1a599
+oid sha256:bd9419f7cbcfd2e8a6d4de4387d7d34821b9333707694a393b247587d7f9d8be
 size 180385008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:573bd29d80e268738a043b87faddec9617e4624a19da6c040c2871530c69a301
+oid sha256:9e75600d1e58cd20ca48265c1978cb139e3ba3bea8e1c446ec4876591809b30d
 size 91850362

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:adef96fec1e64951031f99b379c4a942f776e813faab333e4035a6bb2f9ccc95
+oid sha256:ce01ccd0d976d15c54472e5693d9b466e62f7bed3397b898091810ab0a9a60c2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad8befdc63df11e8e98cd226b6de6db77ab7781057363f64d1a63bc437d2cc05
+oid sha256:b925a88ee07aa88f61077f9b202717bfde744a8b9630c92d5857c028e7513d40
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.297872340425532,
+  "epoch": 2.5531914893617023,
   "eval_steps": 3,
-  "global_step": 27,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -150,6 +150,21 @@
       "eval_samples_per_second": 47.356,
       "eval_steps_per_second": 7.103,
       "step": 27
+    },
+    {
+      "epoch": 2.5531914893617023,
+      "grad_norm": 2.887648820877075,
+      "learning_rate": 1.257446259144494e-05,
+      "loss": 2.4327,
+      "step": 30
+    },
+    {
+      "epoch": 2.5531914893617023,
+      "eval_loss": 2.729001998901367,
+      "eval_runtime": 0.4168,
+      "eval_samples_per_second": 47.983,
+      "eval_steps_per_second": 7.197,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -169,7 +184,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5405214328750080.0,
+  "total_flos": 6005793698611200.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null