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:c568f9a7d3f7320dc968b2fe1b6236f889013f157d0e205e74348bb9382efd2a
+oid sha256:63a806eebec539f1560091c61b5977113bc4a2b20c058b0bbd74a28ea0c70fc0
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8793ba32a1d75db3e5b02135b4451672c7d1d2ade6c5807b1aad863993b71dc8
+oid sha256:8460f3b246ca29edec631a2d7b816563df8b0baa22035a163639c8c0ec5a94a4
 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": 0.013318534961154272,
+  "epoch": 0.01997780244173141,
   "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": 149.84,
       "eval_steps_per_second": 74.92,
       "step": 6
+    },
+    {
+      "epoch": 0.01553829078801332,
+      "grad_norm": 0.025994783267378807,
+      "learning_rate": 0.00014,
+      "loss": 10.379,
+      "step": 7
+    },
+    {
+      "epoch": 0.017758046614872364,
+      "grad_norm": 0.025559840723872185,
+      "learning_rate": 0.00016,
+      "loss": 10.3769,
+      "step": 8
+    },
+    {
+      "epoch": 0.01997780244173141,
+      "grad_norm": 0.020570356398820877,
+      "learning_rate": 0.00018,
+      "loss": 10.3795,
+      "step": 9
+    },
+    {
+      "epoch": 0.01997780244173141,
+      "eval_loss": 10.37732982635498,
+      "eval_runtime": 1.2633,
+      "eval_samples_per_second": 150.402,
+      "eval_steps_per_second": 75.201,
+      "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