Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60304d92c039236d185ef67ff7429d1c447eefded2b4dffacae3f22ffa6fc929
+oid sha256:38cb5a8a162205ae611395c776c7f0782026668bed5894b651e82ad48684f622
 size 125040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:780240851f6fa2213f2e8f3b92bffccd5d8f0f8ec8f01d389af8a8d2546490ed
+oid sha256:0366a8b64576d74d7105e0eb42a764e14957eb6bb12e67bf0ce0b07ae1690b4d
 size 162868

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af82c1f1d4ec999545a290f8875f59e0434314b9e98a3c2553c0c541daf4cdfa
+oid sha256:eb04243bb25bf686a4dbec102fd9ca7613ad5c31a6a03dfc0541d4df84930100
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
+oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00683371298405467,
+  "epoch": 0.010250569476082005,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 292.042,
       "eval_steps_per_second": 146.021,
       "step": 6
+    },
+    {
+      "epoch": 0.007972665148063782,
+      "grad_norm": 0.8876854181289673,
+      "learning_rate": 0.00014,
+      "loss": 44.492,
+      "step": 7
+    },
+    {
+      "epoch": 0.009111617312072893,
+      "grad_norm": 0.7158226370811462,
+      "learning_rate": 0.00016,
+      "loss": 44.45,
+      "step": 8
+    },
+    {
+      "epoch": 0.010250569476082005,
+      "grad_norm": 0.6475933790206909,
+      "learning_rate": 0.00018,
+      "loss": 44.4055,
+      "step": 9
+    },
+    {
+      "epoch": 0.010250569476082005,
+      "eval_loss": 11.111372947692871,
+      "eval_runtime": 1.241,
+      "eval_samples_per_second": 298.157,
+      "eval_steps_per_second": 149.079,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 103681622016.0,
+  "total_flos": 151905632256.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null