Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:363c1d848f384096d1cc941651f262b359bb9d8fc86766e03a7d9667dbdbe423
+oid sha256:800029a0463f2bc279446f3fe604f8fe03a16152a16295d96c38ff66d8ec161f
 size 3152296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1dbb978999ef3039e36faf6551c7c2e89c10db8aaf82e0a1fae17a63718fb8cb
+oid sha256:596917b14b54ed7f591cc8661e19ec1368361ea82e4e01e81e1f600747b8de7a
 size 6332154

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a99d87caccc2bcae5ae88e52d58394b1b32fee39ccefdb775492cc5361c5419
+oid sha256:289efec8f9d3fa8892bdf0ec0bb4cdacaca7b8da2103559050f4c88cab6a7fa6
 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": 7.482970714569092,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.00320666987333654,
+  "best_metric": 7.447418689727783,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.00641333974667308,
   "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": 164.717,
       "eval_steps_per_second": 41.211,
       "step": 10
+    },
+    {
+      "epoch": 0.003848003848003848,
+      "grad_norm": 700.9580078125,
+      "learning_rate": 0.000163742398974869,
+      "loss": 21.8468,
+      "step": 12
+    },
+    {
+      "epoch": 0.00481000481000481,
+      "grad_norm": 820.9585571289062,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 24.7721,
+      "step": 15
+    },
+    {
+      "epoch": 0.00481000481000481,
+      "eval_loss": 7.462524890899658,
+      "eval_runtime": 16.1107,
+      "eval_samples_per_second": 162.997,
+      "eval_steps_per_second": 40.78,
+      "step": 15
+    },
+    {
+      "epoch": 0.005772005772005772,
+      "grad_norm": 1017.3225708007812,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 26.0574,
+      "step": 18
+    },
+    {
+      "epoch": 0.00641333974667308,
+      "eval_loss": 7.447418689727783,
+      "eval_runtime": 16.1836,
+      "eval_samples_per_second": 162.263,
+      "eval_steps_per_second": 40.597,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 89372900720640.0,
+  "total_flos": 147465286189056.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null