Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:935f87d5746c44d52eb07087318d4db444db0e8ef229a84ae54657371772d39a
+oid sha256:fcfdd85f653319038f128c7ff241c38127e8d7ac26f881d678a9a88622e067b1
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb398cf1005c6dfb9f0f684b4044bc0dcb1f58c0b21a2c1fb4e2ad62bbc98a9c
+oid sha256:efe210c4173606903b195784de9d8f69055b82be5b028a1dc0d089f02cda7a4a
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fdca83b5e2b075ac21130c037c6274d19f216f877124f0ce076aae0aac64f91
+oid sha256:05db6b3703f656e0db66b032e0185fd50565c34feed18f347061030838adc6f0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.5946590900421143,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0007427627058845376,
+  "best_metric": 1.5074851512908936,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0014855254117690751,
   "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": 7.788,
       "eval_steps_per_second": 3.895,
       "step": 10
+    },
+    {
+      "epoch": 0.000891315247061445,
+      "grad_norm": 13.892797470092773,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 6.251,
+      "step": 12
+    },
+    {
+      "epoch": 0.0011141440588268063,
+      "grad_norm": 7.632380962371826,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 6.082,
+      "step": 15
+    },
+    {
+      "epoch": 0.0011141440588268063,
+      "eval_loss": 1.5541844367980957,
+      "eval_runtime": 728.0052,
+      "eval_samples_per_second": 7.787,
+      "eval_steps_per_second": 3.894,
+      "step": 15
+    },
+    {
+      "epoch": 0.0013369728705921677,
+      "grad_norm": 8.058558464050293,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 6.2013,
+      "step": 18
+    },
+    {
+      "epoch": 0.0014855254117690751,
+      "eval_loss": 1.5074851512908936,
+      "eval_runtime": 727.2543,
+      "eval_samples_per_second": 7.795,
+      "eval_steps_per_second": 3.898,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3691434095935488.0,
+  "total_flos": 7382868191870976.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null