Training in progress, step 135, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee13e110c1c3af0ec71512dc59558551d08dda01037c1eccbe6b6ef0f72e7315
+oid sha256:ef8d9ded12c76a8b3753f5496f747f5d54b587dfa5a0dd92864c200e37197abf
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a2b7c2f79bc53fe9158a9b6fbab18fc993b84493d9eaa04fc1785f8c01e0335
+oid sha256:3b845b4baf2873f80c027630755e0198ffc872961126a3bc94b9e2d6013c1f28
 size 37430836

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6009ae40798aec9a3455348f09e711b9c4dcc5cd20a9ed3080b9d3eb4bbbcea
+oid sha256:3fd45d4f240804cfeb9916d9da99f972c1a7356bd01065cf4e24cc4d37c9bb89
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.35390946502057613,
+  "epoch": 0.37037037037037035,
   "eval_steps": 500,
-  "global_step": 129,
+  "global_step": 135,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -910,6 +910,48 @@
       "learning_rate": 0.00017803030303030303,
       "loss": 1.3234,
       "step": 129
+    },
+    {
+      "epoch": 0.35665294924554186,
+      "grad_norm": 0.15233512222766876,
+      "learning_rate": 0.00017727272727272728,
+      "loss": 1.2672,
+      "step": 130
+    },
+    {
+      "epoch": 0.35939643347050754,
+      "grad_norm": 0.16545739769935608,
+      "learning_rate": 0.00017651515151515153,
+      "loss": 1.175,
+      "step": 131
+    },
+    {
+      "epoch": 0.36213991769547327,
+      "grad_norm": 0.13627974689006805,
+      "learning_rate": 0.00017575757575757578,
+      "loss": 1.2611,
+      "step": 132
+    },
+    {
+      "epoch": 0.36488340192043894,
+      "grad_norm": 0.1535719484090805,
+      "learning_rate": 0.000175,
+      "loss": 1.2334,
+      "step": 133
+    },
+    {
+      "epoch": 0.3676268861454047,
+      "grad_norm": 0.1347316950559616,
+      "learning_rate": 0.00017424242424242425,
+      "loss": 1.2259,
+      "step": 134
+    },
+    {
+      "epoch": 0.37037037037037035,
+      "grad_norm": 0.1347058117389679,
+      "learning_rate": 0.0001734848484848485,
+      "loss": 1.135,
+      "step": 135
     }
   ],
   "logging_steps": 1,
@@ -929,7 +971,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.6023428209154458e+17,
+  "total_flos": 1.6762622601929933e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null