Training in progress, step 33, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd9419f7cbcfd2e8a6d4de4387d7d34821b9333707694a393b247587d7f9d8be
+oid sha256:33a81957b3066118353e17930a692f4a5ae735b1a10180dc7f262ed340a72cbf
 size 180385008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e75600d1e58cd20ca48265c1978cb139e3ba3bea8e1c446ec4876591809b30d
+oid sha256:f566cd4237489568edc6eaa8911d4a9d9d25f33e74308b883e671481ddca8f23
 size 91850362

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce01ccd0d976d15c54472e5693d9b466e62f7bed3397b898091810ab0a9a60c2
+oid sha256:27711bd45caa46be0b86bab81ee13a8a63dcc0e717df52325b0112fd9feff843
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b925a88ee07aa88f61077f9b202717bfde744a8b9630c92d5857c028e7513d40
+oid sha256:27575060924a140e753cf4290b803eceafe8f2b71ca53127ae4a896e790b23a6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.5531914893617023,
+  "epoch": 2.8085106382978724,
   "eval_steps": 3,
-  "global_step": 30,
+  "global_step": 33,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -165,6 +165,21 @@
       "eval_samples_per_second": 47.983,
       "eval_steps_per_second": 7.197,
       "step": 30
+    },
+    {
+      "epoch": 2.8085106382978724,
+      "grad_norm": 2.3609039783477783,
+      "learning_rate": 3.249187865729264e-06,
+      "loss": 2.3787,
+      "step": 33
+    },
+    {
+      "epoch": 2.8085106382978724,
+      "eval_loss": 2.7300968170166016,
+      "eval_runtime": 0.4182,
+      "eval_samples_per_second": 47.827,
+      "eval_steps_per_second": 7.174,
+      "step": 33
     }
   ],
   "logging_steps": 3,
@@ -184,7 +199,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6005793698611200.0,
+  "total_flos": 6606373068472320.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null