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:dfe64f6e173be501b02058f0a2ff37a2e6712b55357640276e24d865ccf38907
+oid sha256:75b5e4c3d4a198d3fbe25bddee933ccefb97e2a249147ec76b747558ba918592
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f88117e493322b41e941b81c0b46b50ecf0846b22bd95bc2eccef377af14014
+oid sha256:c6910ef08496706ae4a9a7c48f3b226d8ace9b9501a8475341ba8e171277ec8c
 size 111142

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9b931b5fc0c1bd85ac8b5cf7dfdfe32425d1d78ecf18cf7fdcddc467f06765e
+oid sha256:56e4c605570ee3c73fe8ff5167e52a53ea3100415d1bfd842431b5b9a62a411e
 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": 0.00581254541051102,
+  "epoch": 0.00871881811576653,
   "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": 92.478,
       "eval_steps_per_second": 46.345,
       "step": 6
+    },
+    {
+      "epoch": 0.006781302978929523,
+      "grad_norm": 0.055705487728118896,
+      "learning_rate": 0.00014,
+      "loss": 10.3714,
+      "step": 7
+    },
+    {
+      "epoch": 0.007750060547348026,
+      "grad_norm": 0.07059347629547119,
+      "learning_rate": 0.00016,
+      "loss": 10.3799,
+      "step": 8
+    },
+    {
+      "epoch": 0.00871881811576653,
+      "grad_norm": 0.0859907865524292,
+      "learning_rate": 0.00018,
+      "loss": 10.3722,
+      "step": 9
+    },
+    {
+      "epoch": 0.00871881811576653,
+      "eval_loss": 10.375100135803223,
+      "eval_runtime": 4.7485,
+      "eval_samples_per_second": 91.609,
+      "eval_steps_per_second": 45.91,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 627629359104.0,
+  "total_flos": 941444038656.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null