Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25032b2e19e3de41e30b2481e1537dc791fc37203f8e8ea85ca0db525881517b
+oid sha256:e0489cd2102d8ad28f7b3c1a78f8fa074eef771313308d2746a78ce8dbc98ee7
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bd4e40b560608d2752118ec8ccc0d19663387a2a69bbcd8e2d092ee1e509517
+oid sha256:36f0b83671ea89b4dd938cc01e06f3bd36b649d0771387c0f14c47d4fb12790f
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2aaa6d8a69d8299a907823adc599422c15491312a4bfb634b6631045d063f404
+oid sha256:d9d2c6bb21a3bf16e24591514b759917b69cadf404c12e76fa21aada81445209
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a991012fbb3e0053bc41a0b782b67db27509c27d2801c8bf4a64c3687e55e582
+oid sha256:02d97e2af7e51ba89efcffc7f2a661ca0885e61db7f78987db5df30514ab62df
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.028585040495474036,
+  "epoch": 0.038113387327298714,
   "eval_steps": 5,
-  "global_step": 15,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -74,6 +74,21 @@
       "eval_samples_per_second": 6.289,
       "eval_steps_per_second": 0.79,
       "step": 15
+    },
+    {
+      "epoch": 0.03430204859456884,
+      "grad_norm": 1.7916969060897827,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 2.6218,
+      "step": 18
+    },
+    {
+      "epoch": 0.038113387327298714,
+      "eval_loss": 2.3375890254974365,
+      "eval_runtime": 140.5851,
+      "eval_samples_per_second": 6.288,
+      "eval_steps_per_second": 0.79,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -93,7 +108,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.525540736237568e+16,
+  "total_flos": 6.034054314983424e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null