Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86197a5eed36787d98ac2ae128acc11f57bd438cd1e7108829a239d3258b4d1d
+oid sha256:23cabbf0358b6ae7037832406af074a145020c26a154b886180ec7b0321323ae
 size 25192592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b105aa8a65d475e6a687164a296a152b640f67a99494bbd48e275d6a43a9d9bd
+oid sha256:29070380fa76f1a540d411e124bb4125ac5bed5f4686080cad2c4f556423474d
 size 50493050

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec134605e1e781fc705a3279e09b0cbaee66f077da601816e59f2b3169ff7952
+oid sha256:326b940c26441f9cc805b55861d6ba1368323749e2ade38b0a118c4c7d409c57
 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": 3.8164217472076416,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0017146776406035665,
+  "best_metric": 3.5884788036346436,
+  "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": 49.672,
       "eval_steps_per_second": 24.836,
       "step": 10
+    },
+    {
+      "epoch": 0.00205761316872428,
+      "grad_norm": 60.8523063659668,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 14.8321,
+      "step": 12
+    },
+    {
+      "epoch": 0.00257201646090535,
+      "grad_norm": 64.35668182373047,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 14.7542,
+      "step": 15
+    },
+    {
+      "epoch": 0.00257201646090535,
+      "eval_loss": 3.6742002964019775,
+      "eval_runtime": 52.3218,
+      "eval_samples_per_second": 46.94,
+      "eval_steps_per_second": 23.47,
+      "step": 15
+    },
+    {
+      "epoch": 0.0030864197530864196,
+      "grad_norm": 63.078304290771484,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 15.7294,
+      "step": 18
+    },
+    {
+      "epoch": 0.003429355281207133,
+      "eval_loss": 3.5884788036346436,
+      "eval_runtime": 49.8784,
+      "eval_samples_per_second": 49.24,
+      "eval_steps_per_second": 24.62,
+      "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