Training in progress, step 60, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c05b93acda6a7b2f81f0afd85f5badfd9cfa3a6e9e1606092480a0fbff648c88
+oid sha256:888d6b2d183be0ad051b69e15bacc2f610a2138674c1cefb759c0b5ea44fb84b
 size 4725640

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1a8fd6c5ca33512dfe3433cf2f0529599bf80a58b48b2d72c40c244f1ff4d38
+oid sha256:3da76e9afdf003a898a487820cd7ea1d43e840d64f8865874b93117bab741801
 size 2423738

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87627699ac0553b87adb61769764b7859db5e6139e1fca8eca54989ab707ce0d
+oid sha256:28d42be630248a5213a70ba5e163d2391a05816dbb273d1b7b48dcd47e871fb4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba9088914de78dc99d767c21058d110a360c0bb50564c9ed4886490601d97b6d
+oid sha256:da2b3df137afc8ce0bf3abe9574aa4eb50b6c5bd11e6952c66c439eade1cc134
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.1130100472399276e-05,
+  "epoch": 4.669515070859891e-05,
   "eval_steps": 500,
-  "global_step": 40,
+  "global_step": 60,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -21,6 +21,13 @@
       "learning_rate": 3.2500000000000002e-06,
       "loss": 3.6056,
       "step": 40
+    },
+    {
+      "epoch": 0.0,
+      "grad_norm": 1.030365228652954,
+      "learning_rate": 4.9166666666666665e-06,
+      "loss": 3.526,
+      "step": 60
     }
   ],
   "logging_steps": 20,
@@ -28,7 +35,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 24304518549504.0,
+  "total_flos": 35326762795008.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null