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:b699ad2f435d7c0ff9f5cb41490e366b51002865b3c6f8aad740f65632c4cc52
+oid sha256:80b9847510fba97356841de685ac84b6accf281efdb38e046d4bcc201e9c7aa3
 size 159712

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e88aa6f607e784d7d0afb0ab6a4b06239cea573c4d245e4dbab5830e2f5637dd
+oid sha256:8bd0044c13a5e02b73220dfb979b96f95a137439e8f2daf793a26e1fb1cf7ce5
 size 336202

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e97ead28242dd097af80112cb3bd8d751944021cbf255fca1535e0f2a22344d9
+oid sha256:c5288ed9323916daf49e9e619b5ce81ab40c19e01021e3ee0c12210ac8bab7de
 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": 10.800826072692871,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.013364517206815904,
+  "best_metric": 10.780200004577637,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.026729034413631808,
   "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": 153.515,
       "eval_steps_per_second": 77.001,
       "step": 10
+    },
+    {
+      "epoch": 0.016037420648179083,
+      "grad_norm": 0.2091740220785141,
+      "learning_rate": 0.000163742398974869,
+      "loss": 10.8,
+      "step": 12
+    },
+    {
+      "epoch": 0.020046775810223856,
+      "grad_norm": 0.20673868060112,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 10.7941,
+      "step": 15
+    },
+    {
+      "epoch": 0.020046775810223856,
+      "eval_loss": 10.788802146911621,
+      "eval_runtime": 2.0783,
+      "eval_samples_per_second": 151.565,
+      "eval_steps_per_second": 76.023,
+      "step": 15
+    },
+    {
+      "epoch": 0.024056130972268625,
+      "grad_norm": 0.21553605794906616,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 10.785,
+      "step": 18
+    },
+    {
+      "epoch": 0.026729034413631808,
+      "eval_loss": 10.780200004577637,
+      "eval_runtime": 2.101,
+      "eval_samples_per_second": 149.925,
+      "eval_steps_per_second": 75.201,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3259117338624.0,
+  "total_flos": 6559489327104.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null