Training in progress, step 11600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac7e07e5bb14a4a4cc0964f7cd728e86c6dd0e469b29f0710b6d7a1c335fbffc
+oid sha256:8b74082b50533e4333b88e29acd5ec8eecf39804ba0295840da3c866df5050cc
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0f695b9724dd9d30c7d12e2655c18b7ebd533daeee1146ff450bbab43e321fb
+oid sha256:a4f867fe76c879c3168a89d511c76e1fa1b26ec6a18b25ec83cf06f006a135e0
 size 84581014

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66ec65a4ec9e27552c1d645b591799723672eef7af9c95a4e66173a21b097caf
+oid sha256:68341ef163cc0109a8713173add8dbcfd98bf67468e1a64939a8b03523666bf9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b40e1ebe979c78c76ee0b89adbef70ff0ea3286d5b63b173abcc348d810db8e6
+oid sha256:c6fa196d6a1215f8cb5411f481e0c89a67b0e9876e4efe3f1ada6c1ba44ba0a3
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.008477758896998948,
+  "epoch": 0.008626491509226999,
   "eval_steps": 2000,
-  "global_step": 11400,
+  "global_step": 11600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -406,6 +406,13 @@
       "learning_rate": 1.9999858428217852e-05,
       "loss": 1.6124,
       "step": 11400
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 3.860379219055176,
+      "learning_rate": 1.9999853411898932e-05,
+      "loss": 1.5097,
+      "step": 11600
     }
   ],
   "logging_steps": 200,
@@ -413,7 +420,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 200,
-  "total_flos": 1.4908117193876275e+17,
+  "total_flos": 1.5179994612574618e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null