Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ddb0a3040e4bc33b45e5f683357414fba640069beb3aef7d35d83b45853605b
+oid sha256:034e187a68a928df60de8335d8df6f9d752c366c792ade88c4c13240c4166357
 size 536906096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df7c014a1bf191c56fdbf386cd19429a2f9f3882d634e9dfcfb1f27ac32ff6ba
+oid sha256:e325c8d6e17b7311ab280d18a60d02cca13364708dc86af9066b50e60d2b98d3
 size 269267284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8cc3c3121e910c0b9dfe5b58766894e33e13b11c23a5da31d662071e56c6dec
+oid sha256:21d1ae586164ef573a6c2ef2af404c49503a0d50cf74be438545d9458602c094
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efdbfe8676cd24a75fed7e6e38125bb1bb838a4b70c0fbf7469557659d9b1fec
+oid sha256:d31dc31a119769737d72f3df4c8cdf99522596cafc12bf2eea05a4ff374f599c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5,
+  "epoch": 0.6,
   "eval_steps": 500,
-  "global_step": 125,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -757,13 +757,163 @@
       "learning_rate": 0.0002,
       "loss": 0.4266,
       "step": 125
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0002,
+      "loss": 0.4661,
+      "step": 126
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0002,
+      "loss": 0.3564,
+      "step": 127
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0002,
+      "loss": 0.3744,
+      "step": 128
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0002,
+      "loss": 0.3771,
+      "step": 129
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0002,
+      "loss": 0.4058,
+      "step": 130
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0002,
+      "loss": 0.3986,
+      "step": 131
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0002,
+      "loss": 0.3803,
+      "step": 132
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0002,
+      "loss": 0.4069,
+      "step": 133
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0002,
+      "loss": 0.3484,
+      "step": 134
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0002,
+      "loss": 0.3777,
+      "step": 135
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0002,
+      "loss": 0.3637,
+      "step": 136
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0002,
+      "loss": 0.4426,
+      "step": 137
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0002,
+      "loss": 0.3648,
+      "step": 138
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0002,
+      "loss": 0.3665,
+      "step": 139
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0002,
+      "loss": 0.3592,
+      "step": 140
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0002,
+      "loss": 0.3375,
+      "step": 141
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0002,
+      "loss": 0.3669,
+      "step": 142
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0002,
+      "loss": 0.3499,
+      "step": 143
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0002,
+      "loss": 0.3832,
+      "step": 144
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0002,
+      "loss": 0.2947,
+      "step": 145
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0002,
+      "loss": 0.3493,
+      "step": 146
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0002,
+      "loss": 0.2903,
+      "step": 147
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0002,
+      "loss": 0.2703,
+      "step": 148
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0002,
+      "loss": 0.2989,
+      "step": 149
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0002,
+      "loss": 0.2957,
+      "step": 150
     }
   ],
   "logging_steps": 1,
   "max_steps": 250,
   "num_train_epochs": 1,
   "save_steps": 25,
-  "total_flos": 9948052490158080.0,
+  "total_flos": 1.165066384195584e+16,
   "trial_name": null,
   "trial_params": null
 }