Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06bf033dddd9681dd34d1bae6599ab6b3536a7f3159135061fca76811bfea1f8
+oid sha256:b6338bb0f62bf9308723dea6cde721437ea8f6a4b2ad4cb67c84234361eaca4f
 size 26008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce9f137df81ac8c257eb4cc9d1e1d908080facc08423e853dcff61d473cc46fa
+oid sha256:8b9fcadaff7138d9b455fb48d1a62da86b530c1696dfb76318077e2775ac98ca
 size 68874

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f258b2c1b403a81446679141f13e99eda29a6d0d9ef461846ec67dd7c319f6a
+oid sha256:e32f10154a5b77b0c925a53d1da7325b4357fe6698098b50190974355eeaec1b
 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": 11.932486534118652,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.008528784648187633,
+  "best_metric": 11.93227481842041,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.017057569296375266,
   "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": 78.26,
       "eval_steps_per_second": 19.565,
       "step": 10
+    },
+    {
+      "epoch": 0.01023454157782516,
+      "grad_norm": 0.01528004091233015,
+      "learning_rate": 0.000163742398974869,
+      "loss": 11.9347,
+      "step": 12
+    },
+    {
+      "epoch": 0.01279317697228145,
+      "grad_norm": 0.016175327822566032,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 11.9337,
+      "step": 15
+    },
+    {
+      "epoch": 0.01279317697228145,
+      "eval_loss": 11.932391166687012,
+      "eval_runtime": 12.346,
+      "eval_samples_per_second": 80.026,
+      "eval_steps_per_second": 20.006,
+      "step": 15
+    },
+    {
+      "epoch": 0.01535181236673774,
+      "grad_norm": 0.012100557796657085,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 11.9335,
+      "step": 18
+    },
+    {
+      "epoch": 0.017057569296375266,
+      "eval_loss": 11.93227481842041,
+      "eval_runtime": 12.6963,
+      "eval_samples_per_second": 77.818,
+      "eval_steps_per_second": 19.454,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7682064384.0,
+  "total_flos": 15176761344.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null