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:f36ecf7153e9ceeb5e74ecaab98e7551c16b4977e6418ac7c091b47e0a4dcfab
+oid sha256:b87c5255c08dfb785b38f94676b64ae5f69c37f1b1eaf1e74ff80d9fc7a6bd2d
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ffa590b9affc6d842ee0bda9690374616226de554d14b108d2e89d55fda3abd
+oid sha256:a4cbbf6bce86b8b18f8947810c3b186cce6a01b91520055147ba17b94e041ed7
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b058e3f4efb72d1010e7edcd9a82b5cfd988e6f9f5d042e61b36316850284f75
+oid sha256:f88431b600c091712847abac58452223fc04768337c0a249239a522c8ce713ff
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c188a6a4749e6ca627bb6d536eb7443f499d5b1b88d98a78f9c713443e010d9c
+oid sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.7666887044906616,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0029996250468691415,
+  "best_metric": 0.5715872049331665,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.005999250093738283,
   "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": 4.205,
       "eval_steps_per_second": 2.103,
       "step": 10
+    },
+    {
+      "epoch": 0.0035995500562429695,
+      "grad_norm": 0.19681283831596375,
+      "learning_rate": 0.000163742398974869,
+      "loss": 0.7716,
+      "step": 12
+    },
+    {
+      "epoch": 0.0044994375703037125,
+      "grad_norm": 0.20338043570518494,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.692,
+      "step": 15
+    },
+    {
+      "epoch": 0.0044994375703037125,
+      "eval_loss": 0.6406676173210144,
+      "eval_runtime": 333.5289,
+      "eval_samples_per_second": 4.21,
+      "eval_steps_per_second": 2.105,
+      "step": 15
+    },
+    {
+      "epoch": 0.005399325084364455,
+      "grad_norm": 0.2436366081237793,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 0.6236,
+      "step": 18
+    },
+    {
+      "epoch": 0.005999250093738283,
+      "eval_loss": 0.5715872049331665,
+      "eval_runtime": 333.2257,
+      "eval_samples_per_second": 4.213,
+      "eval_steps_per_second": 2.107,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6534582019031040.0,
+  "total_flos": 1.306916403806208e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null