Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47dc1fbbd5669ac94b72b9f6ff93d9d44ee13d9d3f4c0df0a23df0675fb70034
+oid sha256:63c0f3c102d3c14203b3d119cb745a909dd362f38b5ae9a3881089cc800f8966
 size 48679352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0fed541ec9fa7a453fb4383a792ebe4e380cb5cf0416f635b24d6d6d0ae9d78
+oid sha256:5d563a0e60da5be76efc491f9ec7ea926f3a932489e0cae235f155cab0ab7dab
 size 25152500

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d5b557f9ac731f277d55c777bf769719d64b454cd4a996ecd46ec39906e6568
+oid sha256:03ffe07feb625055b808b0da3d9803c9bf6c86313f030e3967ef5cb0025ceb2b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5adea6def46a60dd5782726d51a89bdf0f30226cd791e511d8af09a5644f99e2
+oid sha256:6e65bdb10468d12c8b6afa89fe8730e38a94a4f704431de04b0c1bf27440afce
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.08356769787063077,
+  "epoch": 0.16713539574126154,
   "eval_steps": 10,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -30,6 +30,21 @@
       "eval_samples_per_second": 27.307,
       "eval_steps_per_second": 3.413,
       "step": 10
+    },
+    {
+      "epoch": 0.12856568903173965,
+      "grad_norm": 0.17785143852233887,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 2.0029,
+      "step": 20
+    },
+    {
+      "epoch": 0.12856568903173965,
+      "eval_loss": 1.9852516651153564,
+      "eval_runtime": 38.2636,
+      "eval_samples_per_second": 27.389,
+      "eval_steps_per_second": 3.424,
+      "step": 20
     }
   ],
   "logging_steps": 10,
@@ -49,7 +64,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.662778079182848e+16,
+  "total_flos": 3.37425677156352e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null