Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65801e4329ef9e1c4ff5a7cd689a57598a7d124cdf6d2eb844f2787443b4be78
+oid sha256:e3f5e1a25d00fb044c5174cfbe997d268662348e94433f586dfab34bc54abbad
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09cfdc8dad8f5f8e278ca59ec5c204e17ad0ab6c4389e40122ca6aac86b37b5b
+oid sha256:10bcaaa593526282bb89d97c7f8a4e45bd4839d8020f6c22156e5d6e8fa6aca5
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91e21b3e69e55e0e8e09fb70ac5fe073e530d2e62917f95572d9ed078668e717
+oid sha256:00b243aea78e1eb9c2783b2ede924fa98ed34ea4662672ae5272ac00736eb8da
 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": 1.063054084777832,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.005889281507656066,
+  "best_metric": 0.9963037371635437,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.011778563015312132,
   "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": 2.847,
       "eval_steps_per_second": 0.713,
       "step": 10
+    },
+    {
+      "epoch": 0.007067137809187279,
+      "grad_norm": 0.6839013695716858,
+      "learning_rate": 0.000163742398974869,
+      "loss": 4.2181,
+      "step": 12
+    },
+    {
+      "epoch": 0.0088339222614841,
+      "grad_norm": 0.757274866104126,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 4.2507,
+      "step": 15
+    },
+    {
+      "epoch": 0.0088339222614841,
+      "eval_loss": 1.0176669359207153,
+      "eval_runtime": 500.0195,
+      "eval_samples_per_second": 2.86,
+      "eval_steps_per_second": 0.716,
+      "step": 15
+    },
+    {
+      "epoch": 0.01060070671378092,
+      "grad_norm": 0.7244177460670471,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 3.94,
+      "step": 18
+    },
+    {
+      "epoch": 0.011778563015312132,
+      "eval_loss": 0.9963037371635437,
+      "eval_runtime": 499.8463,
+      "eval_samples_per_second": 2.861,
+      "eval_steps_per_second": 0.716,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.5391158788096e+16,
+  "total_flos": 5.0782317576192e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null