Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d3124d5fb3a13a9a5d4ef239279632be8d7d427b5585c408c08388e6b5908ee
+oid sha256:2551bca4904088520c6015d446c497d0568f830a7c7fd330b16e1171d06a87b5
 size 72673016

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:891f31b05a0835f1f16ade116db6505b177bd225d6898a18b058dd350e0393e9
+oid sha256:c96241bf468c472cac5346ac7ec3308c004be9a7dd5eb6c621fa82bb6f34ec62
 size 36892116

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a058db9c54d7f1b53d3bad727f4153301963dc03c27b73419a8068cc21981f0
+oid sha256:07c76075dc60dc956ebfb1873f21cf2e223089eed32957f63e252eecb72848e3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9702192071987640411db8cd497f9de57450f22a9586d9cce5affbc116fe7983
+oid sha256:194456d3c9e165255d5406a0f3f62973b0bede79d91784f72431350783e27ae7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.056,
+  "epoch": 0.06,
   "eval_steps": 1000,
-  "global_step": 140,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -847,13 +847,73 @@
       "learning_rate": 1.3793103448275863e-05,
       "loss": 1.8603,
       "step": 140
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.2413793103448277e-05,
+      "loss": 1.7057,
+      "step": 141
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.103448275862069e-05,
+      "loss": 1.6926,
+      "step": 142
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 9.655172413793103e-06,
+      "loss": 1.6525,
+      "step": 143
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 8.275862068965518e-06,
+      "loss": 1.7455,
+      "step": 144
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 6.896551724137932e-06,
+      "loss": 1.775,
+      "step": 145
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 5.517241379310345e-06,
+      "loss": 1.6912,
+      "step": 146
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 4.137931034482759e-06,
+      "loss": 1.8147,
+      "step": 147
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 2.7586206896551725e-06,
+      "loss": 1.8314,
+      "step": 148
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.3793103448275862e-06,
+      "loss": 1.9115,
+      "step": 149
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0,
+      "loss": 1.6862,
+      "step": 150
     }
   ],
   "logging_steps": 1,
   "max_steps": 150,
   "num_train_epochs": 1,
   "save_steps": 10,
-  "total_flos": 7007817370042368.0,
+  "total_flos": 7574630234062848.0,
   "trial_name": null,
   "trial_params": null
 }