Training in progress, step 399, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b141baf18e509bb39df2d9729eac124c18ec0aa71d5f6467ca60c922f1bc344
+oid sha256:509eb7625e5d72697ba45e83da0b1443902752698f83af8ab44a82770761b79b
 size 1342238560

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b683f572ce53fc051b588f35612307ce9f4b76c303143dc022c654908efa664
+oid sha256:73c2a787bdf4530acd24befc2d71249593128706625caddb933a9e454e4d4dbb
 size 674092242

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f52035cf003523191da6704c085aea40d350a3deea0e92e91724980d5259f136
+oid sha256:cc6eb7f81374fe232aa541864941cc2fdba3cd1599eb1d67e6d9663327e9b062
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.0175165278526774,
+  "epoch": 1.020073102043262,
   "eval_steps": 500,
-  "global_step": 398,
+  "global_step": 399,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2793,6 +2793,13 @@
       "learning_rate": 0.00011260997067448683,
       "loss": 0.6486,
       "step": 398
+    },
+    {
+      "epoch": 1.020073102043262,
+      "grad_norm": 0.1075356975197792,
+      "learning_rate": 0.00011231671554252199,
+      "loss": 0.6775,
+      "step": 399
     }
   ],
   "logging_steps": 1,
@@ -2812,7 +2819,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2992603159361946e+18,
+  "total_flos": 1.302288297813934e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null