Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d313b4adf5171dfe4fbdc8f8faaa2be2e744eb82bb0532fd28fd5beeda5f983a
+oid sha256:fab3134a73ebaab8fdd80b08e343af89a367abbf983975951d42305e9f4b1a19
 size 838904832

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e604338417c8ba1d7a026714a25e894eb6504d8c420a130e2254cd8fee826bf5
+oid sha256:ccb014d43e78a1ac6ee0fc089ed64494033b0ebbb44670a9ee58bb714125b84a
 size 420633876

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fafcfbfcbbeeafd448436aa0a903f9057fb3e75dd3e8d79ac973fce8af150ecd
+oid sha256:8972305b9bf020a4bb38ed00ecea6ce1d19052e69a3ddd5a8bf5840e137d0fb9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b80fcc7599efca0c6313d990c467c2eb3001742b23ddaadc22e3499c12cea79
+oid sha256:aee2b620608ef64c9c8f70ed72f3a0e1bf233746a6ec27ad47abebf797bd2580
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2,
+  "epoch": 0.3,
   "eval_steps": 500,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -307,13 +307,163 @@
       "learning_rate": 0.0002,
       "loss": 0.4392,
       "step": 50
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0002,
+      "loss": 0.9009,
+      "step": 51
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0002,
+      "loss": 0.7807,
+      "step": 52
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0002,
+      "loss": 0.6645,
+      "step": 53
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0002,
+      "loss": 0.6614,
+      "step": 54
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0002,
+      "loss": 0.6729,
+      "step": 55
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0002,
+      "loss": 0.6466,
+      "step": 56
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0002,
+      "loss": 0.6916,
+      "step": 57
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0002,
+      "loss": 0.6067,
+      "step": 58
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0002,
+      "loss": 0.623,
+      "step": 59
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0002,
+      "loss": 0.5987,
+      "step": 60
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0002,
+      "loss": 0.6124,
+      "step": 61
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0002,
+      "loss": 0.561,
+      "step": 62
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0002,
+      "loss": 0.6036,
+      "step": 63
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0002,
+      "loss": 0.6038,
+      "step": 64
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0002,
+      "loss": 0.5408,
+      "step": 65
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0002,
+      "loss": 0.5779,
+      "step": 66
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0002,
+      "loss": 0.5617,
+      "step": 67
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0002,
+      "loss": 0.608,
+      "step": 68
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0002,
+      "loss": 0.5205,
+      "step": 69
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0002,
+      "loss": 0.599,
+      "step": 70
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0002,
+      "loss": 0.5013,
+      "step": 71
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0002,
+      "loss": 0.5672,
+      "step": 72
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0002,
+      "loss": 0.5373,
+      "step": 73
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0002,
+      "loss": 0.5397,
+      "step": 74
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0002,
+      "loss": 0.531,
+      "step": 75
     }
   ],
   "logging_steps": 1,
   "max_steps": 250,
   "num_train_epochs": 1,
   "save_steps": 25,
-  "total_flos": 6020416979558400.0,
+  "total_flos": 9338307805470720.0,
   "trial_name": null,
   "trial_params": null
 }