Training in progress, step 140, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41fbf3533256819f3f100a22163b1347e5ec366eeebb5d419ea5dff93a58a4e5
+oid sha256:0cc23eb72f46749fcfc528bb4655f0a9e8e52a1732c99da79efb341c19de7408
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7862fa7aee112173b9c4f1218e0f31c8af52209a6cfb659c16ed3f02a5755594
+oid sha256:7e4d87763629aa167751d7202e791130524912699c310ced4ec48a74bd064483
 size 63350356

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acd9b06a21fcf82080ee1e3028a1d0da77d901214b51c999e4aef01ba794228c
+oid sha256:5de00bd1c4d0561944b05f69e20b49da56db8e2875582d2cd83ae415d6a01f93
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f753e28b729aa9f75e1245d98c4a66a151d4403c30b4de19e77340a192ccf5ab
+oid sha256:9702192071987640411db8cd497f9de57450f22a9586d9cce5affbc116fe7983
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.052,
+  "epoch": 0.056,
   "eval_steps": 1000,
-  "global_step": 130,
+  "global_step": 140,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -787,13 +787,73 @@
       "learning_rate": 2.7586206896551727e-05,
       "loss": 2.0021,
       "step": 130
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 2.620689655172414e-05,
+      "loss": 1.7111,
+      "step": 131
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 2.4827586206896553e-05,
+      "loss": 0.9997,
+      "step": 132
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 2.3448275862068967e-05,
+      "loss": 1.1457,
+      "step": 133
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 2.206896551724138e-05,
+      "loss": 1.3816,
+      "step": 134
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 2.0689655172413793e-05,
+      "loss": 1.73,
+      "step": 135
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.9310344827586207e-05,
+      "loss": 1.622,
+      "step": 136
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.793103448275862e-05,
+      "loss": 1.5853,
+      "step": 137
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.6551724137931037e-05,
+      "loss": 1.3064,
+      "step": 138
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.5172413793103448e-05,
+      "loss": 1.663,
+      "step": 139
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.3793103448275863e-05,
+      "loss": 1.5653,
+      "step": 140
     }
   ],
   "logging_steps": 1,
   "max_steps": 150,
   "num_train_epochs": 1,
   "save_steps": 10,
-  "total_flos": 1.6062920583168e+16,
+  "total_flos": 1.721329779259392e+16,
   "trial_name": null,
   "trial_params": null
 }