Training in progress, step 153, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e476837c264c187d86e0fad575c9ce12c9e61fb9e5ad9867160b79e2ffd22dd1
+oid sha256:76166dd110f948403481a165ffeebc91d567372862f2190fa405fdccf5b75ac8
 size 34793120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbcd527c4a25607f123a9175463e52fecf4cbf19113043db3c3d264cf07577b9
+oid sha256:4fe2a73336e970b01cddbe4a75cec8fbc38f1a771c15ecd6bb8a9c4d423c3af4
 size 18132116

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:691c06ffc8e47879d3e6ee441edbd180275d54de37278fc931ad6385e3470814
+oid sha256:7a54b2066ddb168e0e8a2c8b49e5058dff33453160b388ac489494504a9cf08e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd0ef2a827b219b75915f5a88a30c53ebe86f536eec93a6252baab983329eb7
+oid sha256:7d99dc7a150ff6ed818c8735e9e9061e757b4b841b8d74bde2c9d7a2195ff136
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7503448275862069,
+  "epoch": 0.8441379310344828,
   "eval_steps": 17,
-  "global_step": 136,
+  "global_step": 153,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -394,6 +394,56 @@
       "eval_samples_per_second": 68.417,
       "eval_steps_per_second": 8.748,
       "step": 136
+    },
+    {
+      "epoch": 0.7613793103448275,
+      "grad_norm": 0.5550276637077332,
+      "learning_rate": 2.405152131093926e-05,
+      "loss": 2.0373,
+      "step": 138
+    },
+    {
+      "epoch": 0.7779310344827586,
+      "grad_norm": 0.5338502526283264,
+      "learning_rate": 2.196424713241637e-05,
+      "loss": 2.1343,
+      "step": 141
+    },
+    {
+      "epoch": 0.7944827586206896,
+      "grad_norm": 0.47092920541763306,
+      "learning_rate": 1.9945942635848748e-05,
+      "loss": 1.9688,
+      "step": 144
+    },
+    {
+      "epoch": 0.8110344827586207,
+      "grad_norm": 0.5254806876182556,
+      "learning_rate": 1.800157297483417e-05,
+      "loss": 2.0718,
+      "step": 147
+    },
+    {
+      "epoch": 0.8275862068965517,
+      "grad_norm": 0.5177105069160461,
+      "learning_rate": 1.6135921418712956e-05,
+      "loss": 2.188,
+      "step": 150
+    },
+    {
+      "epoch": 0.8441379310344828,
+      "grad_norm": 0.49027958512306213,
+      "learning_rate": 1.435357758543015e-05,
+      "loss": 2.1538,
+      "step": 153
+    },
+    {
+      "epoch": 0.8441379310344828,
+      "eval_loss": 2.107172966003418,
+      "eval_runtime": 4.4092,
+      "eval_samples_per_second": 69.174,
+      "eval_steps_per_second": 8.845,
+      "step": 153
     }
   ],
   "logging_steps": 3,
@@ -413,7 +463,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8645118378639360.0,
+  "total_flos": 9725758175969280.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null