Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f914ea3dc68224bd55d7107b08f59ed23bf5bf397814ee9b20fe839f6a26204
+oid sha256:b8e1c20abbd59ca14f9a033fd14a4663383180e845c8801b2b6c13447187aa39
 size 536906096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cf21319f12883ef19a21dd10c8f43a0a77836b0ede2357a2fb6f15dc87066b3
+oid sha256:8f319714e866b4cbbf9637ffb96ab4de5195d98505c9097f66d2915b36985c73
 size 269267284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5241e37cffc4e4b4f74447637f4dfcba8fa80c5a3822bf57d56e725a1724e3b
+oid sha256:b7f56ce794835ccb5c9bd1d182f355b5b11ffc2a95e12b59b8dc04506e276e44
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aee2b620608ef64c9c8f70ed72f3a0e1bf233746a6ec27ad47abebf797bd2580
+oid sha256:81007ec48272bbdc4f9622c046f9c026bf8120ed11d1398fd97bb5168a6f3dda
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3,
+  "epoch": 0.4,
   "eval_steps": 500,
-  "global_step": 75,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -457,13 +457,163 @@
       "learning_rate": 0.0002,
       "loss": 0.4551,
       "step": 75
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0002,
+      "loss": 0.4208,
+      "step": 76
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0002,
+      "loss": 0.4548,
+      "step": 77
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0002,
+      "loss": 0.4259,
+      "step": 78
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0002,
+      "loss": 0.4031,
+      "step": 79
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0002,
+      "loss": 0.3806,
+      "step": 80
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0002,
+      "loss": 0.4023,
+      "step": 81
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0002,
+      "loss": 0.4011,
+      "step": 82
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0002,
+      "loss": 0.4161,
+      "step": 83
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0002,
+      "loss": 0.3832,
+      "step": 84
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0002,
+      "loss": 0.3898,
+      "step": 85
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0002,
+      "loss": 0.3118,
+      "step": 86
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0002,
+      "loss": 0.3989,
+      "step": 87
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0002,
+      "loss": 0.4115,
+      "step": 88
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0002,
+      "loss": 0.3554,
+      "step": 89
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0002,
+      "loss": 0.3859,
+      "step": 90
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0002,
+      "loss": 0.3187,
+      "step": 91
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0002,
+      "loss": 0.3141,
+      "step": 92
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0002,
+      "loss": 0.3413,
+      "step": 93
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0002,
+      "loss": 0.3262,
+      "step": 94
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0002,
+      "loss": 0.3795,
+      "step": 95
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0002,
+      "loss": 0.2989,
+      "step": 96
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0002,
+      "loss": 0.2695,
+      "step": 97
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0002,
+      "loss": 0.2995,
+      "step": 98
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0002,
+      "loss": 0.2987,
+      "step": 99
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0002,
+      "loss": 0.3816,
+      "step": 100
     }
   ],
   "logging_steps": 1,
   "max_steps": 250,
   "num_train_epochs": 1,
   "save_steps": 25,
-  "total_flos": 6048210105630720.0,
+  "total_flos": 7745482088939520.0,
   "trial_name": null,
   "trial_params": null
 }