Training in progress, step 125, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8e1c20abbd59ca14f9a033fd14a4663383180e845c8801b2b6c13447187aa39
+oid sha256:7ddb0a3040e4bc33b45e5f683357414fba640069beb3aef7d35d83b45853605b
 size 536906096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f319714e866b4cbbf9637ffb96ab4de5195d98505c9097f66d2915b36985c73
+oid sha256:df7c014a1bf191c56fdbf386cd19429a2f9f3882d634e9dfcfb1f27ac32ff6ba
 size 269267284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7f56ce794835ccb5c9bd1d182f355b5b11ffc2a95e12b59b8dc04506e276e44
+oid sha256:d8cc3c3121e910c0b9dfe5b58766894e33e13b11c23a5da31d662071e56c6dec
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81007ec48272bbdc4f9622c046f9c026bf8120ed11d1398fd97bb5168a6f3dda
+oid sha256:efdbfe8676cd24a75fed7e6e38125bb1bb838a4b70c0fbf7469557659d9b1fec
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4,
+  "epoch": 0.5,
   "eval_steps": 500,
-  "global_step": 100,
+  "global_step": 125,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -607,13 +607,163 @@
       "learning_rate": 0.0002,
       "loss": 0.3816,
       "step": 100
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0002,
+      "loss": 0.6736,
+      "step": 101
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0002,
+      "loss": 0.5777,
+      "step": 102
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0002,
+      "loss": 0.567,
+      "step": 103
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0002,
+      "loss": 0.5903,
+      "step": 104
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0002,
+      "loss": 0.5656,
+      "step": 105
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0002,
+      "loss": 0.5903,
+      "step": 106
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0002,
+      "loss": 0.5514,
+      "step": 107
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0002,
+      "loss": 0.5188,
+      "step": 108
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0002,
+      "loss": 0.4504,
+      "step": 109
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0002,
+      "loss": 0.4714,
+      "step": 110
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0002,
+      "loss": 0.5389,
+      "step": 111
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0002,
+      "loss": 0.4501,
+      "step": 112
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0002,
+      "loss": 0.5058,
+      "step": 113
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0002,
+      "loss": 0.5037,
+      "step": 114
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0002,
+      "loss": 0.506,
+      "step": 115
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0002,
+      "loss": 0.4237,
+      "step": 116
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0002,
+      "loss": 0.505,
+      "step": 117
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0002,
+      "loss": 0.4254,
+      "step": 118
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0002,
+      "loss": 0.4155,
+      "step": 119
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0002,
+      "loss": 0.4948,
+      "step": 120
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0002,
+      "loss": 0.4181,
+      "step": 121
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0002,
+      "loss": 0.4383,
+      "step": 122
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0002,
+      "loss": 0.3929,
+      "step": 123
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0002,
+      "loss": 0.4445,
+      "step": 124
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0002,
+      "loss": 0.4266,
+      "step": 125
     }
   ],
   "logging_steps": 1,
   "max_steps": 250,
   "num_train_epochs": 1,
   "save_steps": 25,
-  "total_flos": 7745482088939520.0,
+  "total_flos": 9948052490158080.0,
   "trial_name": null,
   "trial_params": null
 }