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:c2a0e9101060b204be6a16b690e019d834fa0766aaf2299391407aa97665276a
+oid sha256:7b62b8b91228dc9599bcfac12a5216824474c0d9793c439f02ec32148339bd4c
 size 800116456

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1aa1a207edd26c3614c57078c6097a507caa520dacb367243d9f7e96c7767541
+oid sha256:7e313f2d8aa14524c2687300de8ec529b28ece9360c7093726a63f2b8eb7bd43
 size 406743412

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a1afc67d8443c7d735bd225b28b031da4967c4f9edd23293f4559934baf5bea
+oid sha256:b1851d1505f0cd3a6fd1c87c8576b78d87bc7cae7f240dc9cd241fbfe1d155fe
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:152cf5e1f9adf3dc2c608dbb3e394e09940ab42688cdb5a07d89f1cccb7f89a5
+oid sha256:d4d0f57336dd58c2282a758b1873df2644647c71e8296b0dab58cb3a9f5f7c78
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.4909262657165527,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.028409090909090908,
+  "best_metric": 2.180443048477173,
+  "best_model_checkpoint": "miner_id_24/checkpoint-100",
+  "epoch": 0.056818181818181816,
   "eval_steps": 50,
-  "global_step": 50,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,49 @@
       "eval_samples_per_second": 15.588,
       "eval_steps_per_second": 3.913,
       "step": 50
+    },
+    {
+      "epoch": 0.03409090909090909,
+      "grad_norm": 6.00586462020874,
+      "learning_rate": 6.992307692307692e-06,
+      "loss": 2.9064,
+      "step": 60
+    },
+    {
+      "epoch": 0.03977272727272727,
+      "grad_norm": 6.616552352905273,
+      "learning_rate": 6.215384615384615e-06,
+      "loss": 2.5966,
+      "step": 70
+    },
+    {
+      "epoch": 0.045454545454545456,
+      "grad_norm": 7.654419898986816,
+      "learning_rate": 5.438461538461538e-06,
+      "loss": 2.2871,
+      "step": 80
+    },
+    {
+      "epoch": 0.05113636363636364,
+      "grad_norm": 6.925200939178467,
+      "learning_rate": 4.661538461538462e-06,
+      "loss": 1.8554,
+      "step": 90
+    },
+    {
+      "epoch": 0.056818181818181816,
+      "grad_norm": 13.769781112670898,
+      "learning_rate": 3.884615384615385e-06,
+      "loss": 1.2905,
+      "step": 100
+    },
+    {
+      "epoch": 0.056818181818181816,
+      "eval_loss": 2.180443048477173,
+      "eval_runtime": 47.2352,
+      "eval_samples_per_second": 15.687,
+      "eval_steps_per_second": 3.938,
+      "step": 100
     }
   ],
   "logging_steps": 10,
@@ -86,7 +129,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.9931848859713536e+16,
+  "total_flos": 3.986369771942707e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null