Training in progress, step 11400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e978a3dd631581b3085b0ba38c6e47c5baef5e3766e2ff1b44fe2bab4c83f0b4
+oid sha256:ac7e07e5bb14a4a4cc0964f7cd728e86c6dd0e469b29f0710b6d7a1c335fbffc
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cdc657b03435bb6036ff9119a02ab148c9d23c955e9af628c8f81d4a57890a66
+oid sha256:f0f695b9724dd9d30c7d12e2655c18b7ebd533daeee1146ff450bbab43e321fb
 size 84581014

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c99279038b507bc5d43a7a4b5bc357533051098093ca7eb76dbe75fa2a95d6f
+oid sha256:66ec65a4ec9e27552c1d645b591799723672eef7af9c95a4e66173a21b097caf
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c195caf8ca639dd51bdc47a7a6d637f5c72f6cdcb49eec092ef0892b56f6e72
+oid sha256:b40e1ebe979c78c76ee0b89adbef70ff0ea3286d5b63b173abcc348d810db8e6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.008329026284770896,
+  "epoch": 0.008477758896998948,
   "eval_steps": 2000,
-  "global_step": 11200,
+  "global_step": 11400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -399,6 +399,13 @@
       "learning_rate": 1.9999863357206127e-05,
       "loss": 1.5328,
       "step": 11200
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 5.111497402191162,
+      "learning_rate": 1.9999858428217852e-05,
+      "loss": 1.6124,
+      "step": 11400
     }
   ],
   "logging_steps": 200,
@@ -406,7 +413,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 200,
-  "total_flos": 1.463004983428055e+17,
+  "total_flos": 1.4908117193876275e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null