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:ffd5e3107a7b90741351e397be451802eea48b3ebbc33471945c7e4b760e9c74
+oid sha256:a2b12f7c93435b1f66c0ec9501c82c5e38423d221095a0bba6ea46744daf2587
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8c06d7063d2860044695303c365e46e346d7d2f63b6dd15417910cb10e505cd
+oid sha256:6bf0326d405c3a67fe3bbe24c9db3cff8100fa101b88948087602c17dfbe18f1
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e24d535c5c1523f0486038b5930228f33566ca520ba04d10e88741a42965211
+oid sha256:a6150013c5a55351ef3c08536ad845f39a1b502b4c12c8f5e7721ae4addf788a
 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": 0.7675538063049316,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0029996250468691415,
+  "best_metric": 0.5726799964904785,
+  "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": 9.391,
       "eval_steps_per_second": 4.696,
       "step": 10
+    },
+    {
+      "epoch": 0.0035995500562429695,
+      "grad_norm": 0.20542992651462555,
+      "learning_rate": 0.000163742398974869,
+      "loss": 0.7725,
+      "step": 12
+    },
+    {
+      "epoch": 0.0044994375703037125,
+      "grad_norm": 0.1967163383960724,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.6925,
+      "step": 15
+    },
+    {
+      "epoch": 0.0044994375703037125,
+      "eval_loss": 0.641910195350647,
+      "eval_runtime": 149.4727,
+      "eval_samples_per_second": 9.393,
+      "eval_steps_per_second": 4.697,
+      "step": 15
+    },
+    {
+      "epoch": 0.005399325084364455,
+      "grad_norm": 0.23644839227199554,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 0.6245,
+      "step": 18
+    },
+    {
+      "epoch": 0.005999250093738283,
+      "eval_loss": 0.5726799964904785,
+      "eval_runtime": 149.4101,
+      "eval_samples_per_second": 9.397,
+      "eval_steps_per_second": 4.698,
+      "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