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:f04810418f80efb74ff231519d8f17ae18ba7203482ad05a25087826caaa491e
+oid sha256:b6e6aee215e5301fdc5ce3754b1f2ea164d935004d6f9db9464ead89550f7f2c
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3829c41ba62a09dc1349ad60b299ba2cf63852813ebbb4ab0a44da54898ef5a0
+oid sha256:9f318c7631eda1f27274991b77b251da888eea4192344e7aa1b303094523052c
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f3d6d683f19daeffbe361b5e433344e2868a788a494979af8dfd51237d019ef
+oid sha256:bbbabebe5b0848c856d841f6dbe8db82bb44f990eb1381f0226471bd7fa38a4c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59af5f5d66ecb18e9abb84f5d5074a625502d490e59b29de1e9974286a967cbf
+oid sha256:216e1a9a1c53e7de93f56319b4855910155cb98dd7ebb5fa08b3717fd303059f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.06349206349206349,
+  "epoch": 0.09523809523809523,
   "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": 18.302,
       "eval_steps_per_second": 9.204,
       "step": 26
+    },
+    {
+      "epoch": 0.07326007326007326,
+      "grad_norm": 4.645752906799316,
+      "learning_rate": 8.263518223330697e-05,
+      "loss": 4.0549,
+      "step": 30
+    },
+    {
+      "epoch": 0.09523809523809523,
+      "eval_loss": 0.9627972841262817,
+      "eval_runtime": 9.4525,
+      "eval_samples_per_second": 18.302,
+      "eval_steps_per_second": 9.204,
+      "step": 39
     }
   ],
   "logging_steps": 10,
@@ -64,7 +79,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8850992586031104.0,
+  "total_flos": 1.3188855289085952e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null