Training in progress, step 360, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f783b68bc77d003b2ec2afb55e3fb0efe7ee75df1d06ba594d78823f698ccfe
+oid sha256:e02434f63bb76768d0764fb21761fc6bc5a8c5697635718d6ef1c79a814a08e1
 size 8077608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5da3725baf6ae3fc5ba109f906586a34cd88ba766fbb6ad5c773ae39077b66be
+oid sha256:71b11e37189ca2b87525395bedccb828279727662e1a1b44bc3e761c6ac638b2
 size 4052500

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac7e5dca6ac0db5488e28541bc9506788bda445f4514abf096440be8842962c7
+oid sha256:cf59311c497c1cc7e6cd717401fb1271b7c3333ced1b25ea886a7983f576a568
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0064,
+  "epoch": 0.0072,
   "eval_steps": 500,
-  "global_step": 320,
+  "global_step": 360,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -119,6 +119,20 @@
       "learning_rate": 1.6e-05,
       "loss": 4.5021,
       "step": 320
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 91.0234146118164,
+      "learning_rate": 1.7e-05,
+      "loss": 4.5546,
+      "step": 340
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 78.24981689453125,
+      "learning_rate": 1.8e-05,
+      "loss": 4.3795,
+      "step": 360
     }
   ],
   "logging_steps": 20,
@@ -126,7 +140,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 110841162694656.0,
+  "total_flos": 127576999796736.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null