Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77880fb1a409712f822a78185db817c4035a8a37a465b66a51e112ce5e811d77
+oid sha256:f09b951587d74364ff59622d394c4ed26a7a91ecfd719f22341ccbdd9b271d50
 size 216151256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7fd62e2675ab5063d937405ca39007bf001c0bd0da9c01fa1d68351028c3dd5
+oid sha256:796e7e8bf11ec23e2356381ee5e8a98cde4c78c789dbf2df57248716eeb6f54f
 size 432640054

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb7825a666554637881b5ed7bf32ff38578d3e487d2f05776ae43bc87d8311d1
+oid sha256:e5a1359d1b4ebdff24847faf107f09b16b17e59b2ba40f0dcd5e055640303f20
 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": 1.4374616146087646,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.00586596275113653,
+  "best_metric": 1.332247018814087,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.01173192550227306,
   "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": 11.34,
       "eval_steps_per_second": 2.835,
       "step": 10
+    },
+    {
+      "epoch": 0.007039155301363837,
+      "grad_norm": 0.4109272062778473,
+      "learning_rate": 0.000163742398974869,
+      "loss": 1.1459,
+      "step": 12
+    },
+    {
+      "epoch": 0.008798944126704795,
+      "grad_norm": 0.48281750082969666,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.1612,
+      "step": 15
+    },
+    {
+      "epoch": 0.008798944126704795,
+      "eval_loss": 1.3618714809417725,
+      "eval_runtime": 126.6869,
+      "eval_samples_per_second": 11.335,
+      "eval_steps_per_second": 2.834,
+      "step": 15
+    },
+    {
+      "epoch": 0.010558732952045754,
+      "grad_norm": 0.4684368371963501,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 1.1017,
+      "step": 18
+    },
+    {
+      "epoch": 0.01173192550227306,
+      "eval_loss": 1.332247018814087,
+      "eval_runtime": 126.6631,
+      "eval_samples_per_second": 11.337,
+      "eval_steps_per_second": 2.834,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8442028555763712.0,
+  "total_flos": 1.6678153976020992e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null