Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f5c1c25760001d490d3fc4cb0b52082956acd61068023f9d025e36054d66a1f
+oid sha256:19b882ebee58f6b40be573ecb6f366e2ec49ee018dd2d695336f2444187ea91f
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1fef78c229c78543706263df0fb4371cd95f8b28561997f93be9c4af7a0fef4
+oid sha256:17dd53c796ab2ea2d2379c6a5d8250166de88050ffb945505d5f9d07c1dda7c9
 size 320082106

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:091910c241c3e76bbf28530292bd6294407b130962058e2c0c529dc65c8c6263
+oid sha256:4d9d9e169e94fca4b8974ac069cd6054eb9406ff260f6ef065c41d763eacf448
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d46ef0f8a7945706ef65ae5e8be31402361869b6b4c8ecb8ef0263696377404
+oid sha256:e2eb657255baf6b1420bbcfab19529abd45c6011f0c415bddb3c278a51f7f142
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.1891251802444458,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.036596523330283626,
+  "best_metric": 0.8226829767227173,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.07319304666056725,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,43 @@
       "eval_samples_per_second": 4.242,
       "eval_steps_per_second": 2.14,
       "step": 10
+    },
+    {
+      "epoch": 0.04391582799634035,
+      "grad_norm": 1.1146501302719116,
+      "learning_rate": 8.18711994874345e-05,
+      "loss": 1.2096,
+      "step": 12
+    },
+    {
+      "epoch": 0.05489478499542543,
+      "grad_norm": 0.576822817325592,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.972,
+      "step": 15
+    },
+    {
+      "epoch": 0.05489478499542543,
+      "eval_loss": 0.8610323667526245,
+      "eval_runtime": 27.0933,
+      "eval_samples_per_second": 4.245,
+      "eval_steps_per_second": 2.141,
+      "step": 15
+    },
+    {
+      "epoch": 0.06587374199451052,
+      "grad_norm": 0.5784576535224915,
+      "learning_rate": 4.6860474023534335e-05,
+      "loss": 0.8944,
+      "step": 18
+    },
+    {
+      "epoch": 0.07319304666056725,
+      "eval_loss": 0.8226829767227173,
+      "eval_runtime": 27.1025,
+      "eval_samples_per_second": 4.243,
+      "eval_steps_per_second": 2.14,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3305470584422400.0,
+  "total_flos": 6610941168844800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null