Training in progress, step 39, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33a9fb099d28cd45498012bf304953ce45f6983500b457d9d1c6549cc0f0862c
+oid sha256:d3195e67cfe3bdac4d38ebf880ca1cd86f20087c755eb36486c94c4fbc707f4b
 size 17640136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24b7d8c6c695813fbc1fc64a0d06cb7c63fee5bb09529bbcca40c8fca8a394f8
+oid sha256:fae249a849793fe537aca98eb17291e19fad9e8605c68ebe17a96b015e0a7f24
 size 9568884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c73b88f5a325402ade8b631cbde07f764e38136b3a98cd5bf088404635b73f25
+oid sha256:0c3b386391a624b1bd584d01969e845897c710c297088eab7a1800fd97b3f3de
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8712da1b2787df41952a507984ec77e0f72c59fac7ee6cf21606445686249de
+oid sha256:ccc7e73cc5879da996ace4c3a10d9efe08a100111973e801d61997747e95e982
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.010853683990816114,
+  "epoch": 0.01628052598622417,
   "eval_steps": 13,
-  "global_step": 26,
+  "global_step": 39,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -45,6 +45,21 @@
       "eval_samples_per_second": 54.134,
       "eval_steps_per_second": 27.094,
       "step": 26
+    },
+    {
+      "epoch": 0.012523481527864746,
+      "grad_norm": 1.0255998373031616,
+      "learning_rate": 0.0001,
+      "loss": 2.8861,
+      "step": 30
+    },
+    {
+      "epoch": 0.01628052598622417,
+      "eval_loss": 2.917876720428467,
+      "eval_runtime": 18.5288,
+      "eval_samples_per_second": 54.456,
+      "eval_steps_per_second": 27.255,
+      "step": 39
     }
   ],
   "logging_steps": 10,
@@ -64,7 +79,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 244854950461440.0,
+  "total_flos": 365056471597056.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null