Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86e374c8dc7670e113009cd1fdfda77981cea1eaaf2ad23a2d3bed74d7e78c3e
+oid sha256:c20844f42c9b93f8267b12ae97e2c4b934beb498ba4e0a7ea41e6234c0ed18b7
 size 1822093912

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcf0d8e8f1f3112975af58007b6082535a22615fa7b80bd89786ecd57d63dae8
+oid sha256:56e97d8bbeea278080342591be0d762b3aea4c5972203388498704771c3259f8
 size 650679452

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7b4b635714e5c492f91ef8f4c0ec9baf619449d326b7e622ba9e43b98d6b0e5
+oid sha256:17623c77e12578c6ece88c5a168fe7d884bdd692e2133596e023b617714e6485
 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": 0.6,
+  "epoch": 0.8,
   "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": 0.5811,
       "step": 75
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0002,
+      "loss": 0.5042,
+      "step": 76
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0002,
+      "loss": 0.4639,
+      "step": 77
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0002,
+      "loss": 0.489,
+      "step": 78
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0002,
+      "loss": 0.4993,
+      "step": 79
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0002,
+      "loss": 0.5359,
+      "step": 80
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0002,
+      "loss": 0.4741,
+      "step": 81
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0002,
+      "loss": 0.4857,
+      "step": 82
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0002,
+      "loss": 0.4896,
+      "step": 83
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0002,
+      "loss": 0.4386,
+      "step": 84
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0002,
+      "loss": 0.4184,
+      "step": 85
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0002,
+      "loss": 0.4119,
+      "step": 86
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0002,
+      "loss": 0.4549,
+      "step": 87
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0002,
+      "loss": 0.4056,
+      "step": 88
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0002,
+      "loss": 0.3885,
+      "step": 89
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0002,
+      "loss": 0.3585,
+      "step": 90
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0002,
+      "loss": 0.4061,
+      "step": 91
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0002,
+      "loss": 0.3935,
+      "step": 92
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0002,
+      "loss": 0.3814,
+      "step": 93
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0002,
+      "loss": 0.7408,
+      "step": 94
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0002,
+      "loss": 0.7369,
+      "step": 95
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0002,
+      "loss": 0.6254,
+      "step": 96
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0002,
+      "loss": 0.6206,
+      "step": 97
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0002,
+      "loss": 0.5881,
+      "step": 98
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0002,
+      "loss": 0.6188,
+      "step": 99
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0002,
+      "loss": 0.5896,
+      "step": 100
     }
   ],
   "logging_steps": 1,
   "max_steps": 125,
   "num_train_epochs": 1,
   "save_steps": 25,
-  "total_flos": 9865641429368832.0,
+  "total_flos": 1.3033187428073472e+16,
   "trial_name": null,
   "trial_params": null
 }