Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f4a60a51d12fc2d0a3c7411866b7694a4598c5db07ae14ba51215bfe35a6cae
+oid sha256:60650739a65a81ce6f77eefbf0a51414477d7793dd24fdf5f202f9e88b691531
 size 180385008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67453e5e0b000bc1d906d1fb35e08a83b3bb047851bdd7ff45271c7a21a70ad3
+oid sha256:fe51c10ae8b51806e9a4d4e0f69e4e762671d3d8616b9991e263f46dc2c79738
 size 91850362

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78efeda8a2aa0f62fe902cb47d79c4fa73d8aee293a52051995480fbb0999766
+oid sha256:c67e3f354d332558d71a6e74fff042f2e6dc9a3fd62453938cf2b8dac23d58a6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc78163c347c258a17d5fa38a4e22e79b63c35d2cfce0e026e30c38b9ae55f80
+oid sha256:92b4cf85d7ba7a497f88ff799bf4dec5af7dd95be6e00f78bf46ba5deb56bbf8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2553191489361702,
+  "epoch": 0.5106382978723404,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -30,6 +30,21 @@
       "eval_samples_per_second": 48.228,
       "eval_steps_per_second": 7.234,
       "step": 3
+    },
+    {
+      "epoch": 0.5106382978723404,
+      "grad_norm": 3.631814479827881,
+      "learning_rate": 6e-05,
+      "loss": 3.5773,
+      "step": 6
+    },
+    {
+      "epoch": 0.5106382978723404,
+      "eval_loss": 3.226794481277466,
+      "eval_runtime": 0.4126,
+      "eval_samples_per_second": 48.473,
+      "eval_steps_per_second": 7.271,
+      "step": 6
     }
   ],
   "logging_steps": 3,
@@ -49,7 +64,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 600579369861120.0,
+  "total_flos": 1201158739722240.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null