Training in progress, step 80, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b5e1d7fec5642c5a7eebc261811b86c8379352efb270f0d53c3bdd0277083ab
+oid sha256:c7ee9480b07a97ed961d66de3a6ff39cedb681d80c5332fe03877965d568fe2d
 size 8077608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c295c871992ea2658a9d7ad487d59b40db23c7cfbb6615cf5f83edf6deb52d2c
+oid sha256:30f645627c18c4b8cb58363fe0c5c3070d06473a66ad437a5b7253736d14984b
 size 4052500

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b215c0947378bd341b267cea5a7112696ec035345c849e38fb6a3c58f28d2185
+oid sha256:ab1f1d04329bc451c7c78c5bce0db7f51dcc9f7a9ad209a2f8f04db2f833c7a0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0012,
+  "epoch": 0.0016,
   "eval_steps": 500,
-  "global_step": 60,
+  "global_step": 80,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -28,6 +28,13 @@
       "learning_rate": 3e-06,
       "loss": 4.8171,
       "step": 60
+    },
+    {
+      "epoch": 0.0,
+      "grad_norm": 207.87796020507812,
+      "learning_rate": 4e-06,
+      "loss": 4.6765,
+      "step": 80
     }
   ],
   "logging_steps": 20,
@@ -35,7 +42,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 19812939669504.0,
+  "total_flos": 26327231275008.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null