Training in progress, step 35, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a22dc5933573d5ad0e2f0b88c8c0e4722f68fbee2dc78913b62afe5cdb963ee
+oid sha256:f92496aae4e50218f17c408d9883e0b6631b5eec345e15dc4d75b8e3b39a5f39
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5590974220156f343bf17cd1dfea83c1eb69ca441840f889bdfb9ac844cbedc1
+oid sha256:897bf189cdb8886d28116188448a1b8194928f43fed0c2ceb003736fb174b1eb
 size 325339796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67ed692faf639600dadb63e47f782862b02e2b4f1c7bed5e0ed7d786d641b235
+oid sha256:2f6cda69bfbe0de119defc83e5da3ac5af16a274455608c670b1651222f7fc96
 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": 0.17569546120058566,
+  "epoch": 0.20497803806734993,
   "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": 15.585,
       "eval_steps_per_second": 1.948,
       "step": 30
+    },
+    {
+      "epoch": 0.19326500732064422,
+      "grad_norm": 9.957014083862305,
+      "learning_rate": 3.832773180720475e-05,
+      "loss": 2.2084,
+      "step": 33
+    },
+    {
+      "epoch": 0.20497803806734993,
+      "eval_loss": 0.4224419891834259,
+      "eval_runtime": 18.4611,
+      "eval_samples_per_second": 15.6,
+      "eval_steps_per_second": 1.95,
+      "step": 35
     }
   ],
   "logging_steps": 3,
@@ -152,7 +167,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.991525977489408e+16,
+  "total_flos": 4.656780307070976e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null