Training in progress, step 35, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e204fc319f37ca92a83df076ee7b55ede9ac3e0d7f7fe6d5e38c2ac6ecb2ee0
+oid sha256:b7da63f343f3c3a4f6152d5a6217f9c0a7b7200b7f4d431e4cc17cd1e7a970f0
 size 93608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ed1f714420aa41b6aeae7718ea7244c8f8beae5b12cbacfe870b59b27623bf3
+oid sha256:165212386841129c6e4bd627989c298583cabbe15ae4f6c702eed493cacce220
 size 197158

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4542ee77b862586921f712605c9da4a157f7c6fb74687d0b6cef8d69e7a87363
+oid sha256:005d9a86e0834fe0802ab2e1c3fa9eca806e3cae26d1cbb14ab848a758219c13
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d37b0dad6b9c48822da5c83a071d50252502799ad22c4c4907147ad4e4f8e2f4
+oid sha256:88f387d8c434535a84694e469cebc18f2e722ba31b0dc0372632798b59011377
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.43795620437956206,
+  "epoch": 0.5109489051094891,
   "eval_steps": 5,
-  "global_step": 30,
+  "global_step": 35,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -133,6 +133,21 @@
       "eval_samples_per_second": 192.507,
       "eval_steps_per_second": 25.11,
       "step": 30
+    },
+    {
+      "epoch": 0.48175182481751827,
+      "grad_norm": 0.5701283812522888,
+      "learning_rate": 3.832773180720475e-05,
+      "loss": 11.8888,
+      "step": 33
+    },
+    {
+      "epoch": 0.5109489051094891,
+      "eval_loss": 11.877020835876465,
+      "eval_runtime": 0.5948,
+      "eval_samples_per_second": 193.331,
+      "eval_steps_per_second": 25.217,
+      "step": 35
     }
   ],
   "logging_steps": 3,
@@ -152,7 +167,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 144624844800.0,
+  "total_flos": 168728985600.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null