Training in progress, step 1300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d5067b1a890360f337cf6445bbde7702bf4d94ba19dcbad5ec3fde5ed47b77b
+oid sha256:4c65f926eef3faa5033b69ee958b998c89b34591bf1f62bdc681640723e75968
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:221a3c11dc01f47bbfd2f4679f77f9469ee258a3a5acd5d4d4ab58e32b9cc65b
+oid sha256:5aa31c8a63e02c7387dc9928dfa20330e1c75278cd9fefa839ff3d5a21b72444
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2dffb25eadcc0c14a11d06ce2959da02a95556098d9b1b694401b6585e76c1de
+oid sha256:2d8fa792f2351d5e4e8aafd11b207232de2cdf3c34d7ec1a334b68737f7ab0f5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56c936539488437eac974e0855f3113cbe40b51763be54460e94d4c5de858482
+oid sha256:cad57d29213112171f13677d0349d1d18af1003cdb12465ba700cb85d45f5ce4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.45796064400715564,
+  "epoch": 0.46511627906976744,
   "eval_steps": 500,
-  "global_step": 1280,
+  "global_step": 1300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1031,14 +1031,30 @@
       "loss": 0.3947,
       "num_input_tokens_seen": 860605,
       "step": 1280
+    },
+    {
+      "epoch": 0.46153846153846156,
+      "grad_norm": 0.43886885046958923,
+      "learning_rate": 0.0001076923076923077,
+      "loss": 0.4053,
+      "num_input_tokens_seen": 867693,
+      "step": 1290
+    },
+    {
+      "epoch": 0.46511627906976744,
+      "grad_norm": 0.33564773201942444,
+      "learning_rate": 0.00010697674418604651,
+      "loss": 0.3984,
+      "num_input_tokens_seen": 873855,
+      "step": 1300
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 860605,
+  "num_input_tokens_seen": 873855,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 1.935196731638784e+16,
+  "total_flos": 1.964991302544384e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null