Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30055bd71829ebfab820f875e833fe6accba0aeaaf0ba34458f8b48a21e8369a
+oid sha256:41cffc0b0e672936effdb47f97b322b70578230158066ace556cfd6219dccd6a
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:587c7bb72ad132c0a1fc7523f929bde457698f51ce15f28ae71810bf7c6d7a3d
+oid sha256:1f34b4f45e850bcd36eab0112eb58de21ba4990fa604a609960ce6f85d1c8360
 size 325339796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36f9d4df5fa80b8af0ae9e036c834f318a3d9c628c3b781762ee3d1f9db0527c
+oid sha256:0fc2cf6684b4b4476cd2888efa54a33bf379ef1e654c5e672ef4c940dae96161
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70f9eefb79e5a651e4979588997923d1fc997984394f03e9fb61aca38c6bee05
+oid sha256:e6da36b358afefa2fe6fe8e3889efc77dfb89ac577ed7bb55c631123a9ebe149
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.5543313026428223,
-  "best_model_checkpoint": "miner_id_24/checkpoint-100",
-  "epoch": 0.0859106529209622,
+  "best_metric": 1.5382037162780762,
+  "best_model_checkpoint": "miner_id_24/checkpoint-150",
+  "epoch": 0.12886597938144329,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 13.439,
       "eval_steps_per_second": 3.373,
       "step": 100
+    },
+    {
+      "epoch": 0.09450171821305842,
+      "grad_norm": 0.41234856843948364,
+      "learning_rate": 5.05e-06,
+      "loss": 1.4694,
+      "step": 110
+    },
+    {
+      "epoch": 0.10309278350515463,
+      "grad_norm": 0.45751872658729553,
+      "learning_rate": 4.488888888888889e-06,
+      "loss": 1.5459,
+      "step": 120
+    },
+    {
+      "epoch": 0.11168384879725086,
+      "grad_norm": 0.4848977327346802,
+      "learning_rate": 3.927777777777778e-06,
+      "loss": 1.4818,
+      "step": 130
+    },
+    {
+      "epoch": 0.12027491408934708,
+      "grad_norm": 0.6670855283737183,
+      "learning_rate": 3.3666666666666665e-06,
+      "loss": 1.5387,
+      "step": 140
+    },
+    {
+      "epoch": 0.12886597938144329,
+      "grad_norm": 1.1316231489181519,
+      "learning_rate": 2.8055555555555555e-06,
+      "loss": 1.5887,
+      "step": 150
+    },
+    {
+      "epoch": 0.12886597938144329,
+      "eval_loss": 1.5382037162780762,
+      "eval_runtime": 36.6812,
+      "eval_samples_per_second": 13.358,
+      "eval_steps_per_second": 3.353,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -129,7 +172,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.9793401356288e+16,
+  "total_flos": 7.4690102034432e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null