Training in progress, step 1560, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b3ff122300a18d57c853e25e590e16786c7ad419f48524c7cbf11ccb071c190
+oid sha256:534add263f0ab1fce24fa011018eefdd2dcddfad7e6b3e3167b8b88e43d1d335
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:636171340db7557397e62ad8d25bdf32a718d2d9d58de677060e6a51a635f297
+oid sha256:aae8e9e48314c3831c9e9b379cf12dda16febba948f23260c667cfcefdb811cd
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7156da34db6a913e161eace9419c4bd917f16d306983c0686b60a669b6fb753
+oid sha256:2490d49251dc1bfa591e0e3acdc7c7d22ca5de91839e3e61e572022e72d3d8d2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea3157897b0fd7796a4bb8ecade679914447a9babe2f9fec4f85adecca7e3f9d
+oid sha256:4a759d59fcc4923d52863d19dcf59b3835205ae6c3c6035bc1e96d3a9ecd6ff0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5509838998211091,
+  "epoch": 0.5581395348837209,
   "eval_steps": 500,
-  "global_step": 1540,
+  "global_step": 1560,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1239,14 +1239,30 @@
       "loss": 0.4164,
       "num_input_tokens_seen": 1035252,
       "step": 1540
+    },
+    {
+      "epoch": 0.554561717352415,
+      "grad_norm": 0.27858543395996094,
+      "learning_rate": 8.9087656529517e-05,
+      "loss": 0.3976,
+      "num_input_tokens_seen": 1041187,
+      "step": 1550
+    },
+    {
+      "epoch": 0.5581395348837209,
+      "grad_norm": 0.34940874576568604,
+      "learning_rate": 8.837209302325582e-05,
+      "loss": 0.3889,
+      "num_input_tokens_seen": 1047255,
+      "step": 1560
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 1035252,
+  "num_input_tokens_seen": 1047255,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 2.3279161599369216e+16,
+  "total_flos": 2.354906668207104e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null