Training in progress, step 1320, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c65f926eef3faa5033b69ee958b998c89b34591bf1f62bdc681640723e75968
+oid sha256:f11665d8738bbd240d3d64a2d0c1f1d475eca89083c256901ae805bbe967af82
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5aa31c8a63e02c7387dc9928dfa20330e1c75278cd9fefa839ff3d5a21b72444
+oid sha256:cbc2f3fdb0d50fd60d43dd5cec54d8b57e44e12546132c2401b5262cbdbd22a8
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d8fa792f2351d5e4e8aafd11b207232de2cdf3c34d7ec1a334b68737f7ab0f5
+oid sha256:ae7829701acac442ef32175bc209c900d8742812b8a1a981592f253b573d17b2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cad57d29213112171f13677d0349d1d18af1003cdb12465ba700cb85d45f5ce4
+oid sha256:7a38e6a44e6657eed373e3587573685b30a045b1ada672c0864a1f76b235fdfd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.46511627906976744,
+  "epoch": 0.47227191413237923,
   "eval_steps": 500,
-  "global_step": 1300,
+  "global_step": 1320,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1047,14 +1047,30 @@
       "loss": 0.3984,
       "num_input_tokens_seen": 873855,
       "step": 1300
+    },
+    {
+      "epoch": 0.46869409660107336,
+      "grad_norm": 0.31822851300239563,
+      "learning_rate": 0.00010626118067978535,
+      "loss": 0.4162,
+      "num_input_tokens_seen": 881261,
+      "step": 1310
+    },
+    {
+      "epoch": 0.47227191413237923,
+      "grad_norm": 0.2756568193435669,
+      "learning_rate": 0.00010554561717352415,
+      "loss": 0.4092,
+      "num_input_tokens_seen": 888281,
+      "step": 1320
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 873855,
+  "num_input_tokens_seen": 888281,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 1.964991302544384e+16,
+  "total_flos": 1.997430282158285e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null