Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7268fbb42bc51aed25b72d348436e55cdb4976291fa2a64fa5b0cf4b4a346785
+oid sha256:eb655076128f6dc348577c0b96f9b4e0bf150c6ecf9073884e892b922dc0b063
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd132711c3b6526812f323dc27a9a23380aec0247de94e7da0f15433c68c41e3
+oid sha256:731a58cb351f67247be751107190e366e0d07746c73c75b106f21717f0c6febe
 size 170920084

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1aa2f2b8f0acc34f25525370ac47c694bc77de2b2a483c2ca59d5e61a7c2b3c9
+oid sha256:65b7e657ee4d862c53d2ed7eb36592b239642bf4783fdd8f94d0857415ced447
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9421260ddc1f7ea3f664c77307a6e5b30037afc5a204c347c827fe3227c8b77
+oid sha256:fa172a67b17733f4f4576524fa7afa573b19fcbf0bf4ea9f180757ed71fc81e7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.7402405142784119,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.003992454261445867,
+  "best_metric": 0.645350456237793,
+  "best_model_checkpoint": "miner_id_24/checkpoint-100",
+  "epoch": 0.007984908522891734,
   "eval_steps": 50,
-  "global_step": 50,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -30,6 +30,21 @@
       "eval_samples_per_second": 15.001,
       "eval_steps_per_second": 7.501,
       "step": 50
+    },
+    {
+      "epoch": 0.006387926818313388,
+      "grad_norm": 37.602317810058594,
+      "learning_rate": 0.0001,
+      "loss": 5.2458,
+      "step": 80
+    },
+    {
+      "epoch": 0.007984908522891734,
+      "eval_loss": 0.645350456237793,
+      "eval_runtime": 703.8766,
+      "eval_samples_per_second": 14.984,
+      "eval_steps_per_second": 7.493,
+      "step": 100
     }
   ],
   "logging_steps": 40,
@@ -58,7 +73,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.7725519973842944e+16,
+  "total_flos": 3.5406836655980544e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null