Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d475566a10a105076eb1c3c8d8c07ebc88518ebefca06ee6fc007716d2bf5e7
+oid sha256:9ff5cfd6a3431962d1c06b391cbb122da971aed8735fe3b3d2b9837881a0162a
 size 6804608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f855b4f3440f33ffc86a63aa38819c14fa541d9a0ae5dbdb47f4ec48bdf0bddb
+oid sha256:da6e93e46fbfad6dbadc77d24136041d4d0f4ac3136e67f3841574166f6a671f
 size 3633530

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b712fd3c8ee779c3ef6b8a6d440fef6a1c9b80260faa1a050b577352a25547b7
+oid sha256:ce48dec86ac6000671bbcda61602ac669c6643b660b3c79e45fe5bfda138dc71
 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": 0.014431749849669273,
+  "epoch": 0.02164762477450391,
   "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": 102.866,
       "eval_steps_per_second": 51.727,
       "step": 6
+    },
+    {
+      "epoch": 0.01683704149128082,
+      "grad_norm": 0.641490638256073,
+      "learning_rate": 0.00014,
+      "loss": 2.6408,
+      "step": 7
+    },
+    {
+      "epoch": 0.019242333132892364,
+      "grad_norm": 0.8065205216407776,
+      "learning_rate": 0.00016,
+      "loss": 2.6962,
+      "step": 8
+    },
+    {
+      "epoch": 0.02164762477450391,
+      "grad_norm": 0.5643328428268433,
+      "learning_rate": 0.00018,
+      "loss": 2.5749,
+      "step": 9
+    },
+    {
+      "epoch": 0.02164762477450391,
+      "eval_loss": 2.298651933670044,
+      "eval_runtime": 1.6814,
+      "eval_samples_per_second": 104.081,
+      "eval_steps_per_second": 52.338,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 27434120380416.0,
+  "total_flos": 37721915523072.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null