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:fd3e4600a34d5223f42338e12a2774740a4bf89e13e345f458c59ed06a7734af
+oid sha256:0d47800fd7b2372b988dc3c344a939b92ccc7537aa031f947529baf509a4f155
 size 25192592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88d460be70b1b629e4229a7b3a2af5c85a1aa490fb1016f9c4a7c1aa97e8b5d0
+oid sha256:1420074370493ac7568e8d8aa56e07cabe5d75adcb9b56d4d4be1129b9fcb090
 size 50493050

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f84b7eed8ce383f213fa2c01c69e8fe6d926bcb9bee31ed27ce8dad8d9e48e50
+oid sha256:8ac9ef8a8d750dd06f1b2f32aa7dc4ccd0792acf7e63e2006163d178a7597fee
 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": 3.788233757019043,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0017146776406035665,
+  "best_metric": 3.6078875064849854,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.003429355281207133,
   "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": 77.753,
       "eval_steps_per_second": 38.876,
       "step": 10
+    },
+    {
+      "epoch": 0.00205761316872428,
+      "grad_norm": 79.7057876586914,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 14.7597,
+      "step": 12
+    },
+    {
+      "epoch": 0.00257201646090535,
+      "grad_norm": 70.68734741210938,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 14.6524,
+      "step": 15
+    },
+    {
+      "epoch": 0.00257201646090535,
+      "eval_loss": 3.66300630569458,
+      "eval_runtime": 32.4865,
+      "eval_samples_per_second": 75.601,
+      "eval_steps_per_second": 37.8,
+      "step": 15
+    },
+    {
+      "epoch": 0.0030864197530864196,
+      "grad_norm": 99.36012268066406,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 15.8241,
+      "step": 18
+    },
+    {
+      "epoch": 0.003429355281207133,
+      "eval_loss": 3.6078875064849854,
+      "eval_runtime": 31.6607,
+      "eval_samples_per_second": 77.572,
+      "eval_steps_per_second": 38.786,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 177003319787520.0,
+  "total_flos": 354006639575040.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null