Training in progress, step 300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2245154e86cfc0620e9548fd4159206aae2de3b21ba48f94df102e9dac72a4f
+oid sha256:7a7c2e20a926129d29a08acb7bc3ad7473fcdef597915c6d28d89bedc694a6ec
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82c34aa219f3b252bfb1eea4d56a9762eb25fa457aefbe1745f978607f31db0c
-size 328468404
+oid sha256:f993ff850d525263c9ec68a03eb27bf7ab20b42446876d807fbb312674ae280b
+size 328468852

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:466f77911b2363e9039eb587c905ca68553d2acfdd4167c910996a379579799a
+oid sha256:256f6f2952f913c7f60ec5567b86f4d6fc189f83109a141672b19e11afb733ca
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c025e03e0d8ded968e4f23b186aaafce8f23c2a50b134c4f77cea95627049ac8
+oid sha256:09bf653dc25e0c029a8db4ba507ae3589e41445bb2b0fcc38f99c09150129f49
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.259118914604187,
-  "best_model_checkpoint": "miner_id_24/checkpoint-250",
-  "epoch": 0.27188689505165853,
+  "best_metric": 0.22318749129772186,
+  "best_model_checkpoint": "miner_id_24/checkpoint-300",
+  "epoch": 0.3262642740619902,
   "eval_steps": 50,
-  "global_step": 250,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -230,6 +230,49 @@
       "eval_samples_per_second": 17.003,
       "eval_steps_per_second": 4.251,
       "step": 250
+    },
+    {
+      "epoch": 0.28276237085372485,
+      "grad_norm": 0.4750421941280365,
+      "learning_rate": 0.00011597548864310363,
+      "loss": 0.1849,
+      "step": 260
+    },
+    {
+      "epoch": 0.2936378466557912,
+      "grad_norm": 0.6818949580192566,
+      "learning_rate": 0.00010866444715376263,
+      "loss": 0.1809,
+      "step": 270
+    },
+    {
+      "epoch": 0.3045133224578575,
+      "grad_norm": 0.9162408113479614,
+      "learning_rate": 0.00010133555284623744,
+      "loss": 0.0971,
+      "step": 280
+    },
+    {
+      "epoch": 0.3153887982599239,
+      "grad_norm": 1.3977360725402832,
+      "learning_rate": 9.402451135689641e-05,
+      "loss": 0.2537,
+      "step": 290
+    },
+    {
+      "epoch": 0.3262642740619902,
+      "grad_norm": 3.654791831970215,
+      "learning_rate": 8.676694134497232e-05,
+      "loss": 0.3683,
+      "step": 300
+    },
+    {
+      "epoch": 0.3262642740619902,
+      "eval_loss": 0.22318749129772186,
+      "eval_runtime": 22.8297,
+      "eval_samples_per_second": 16.995,
+      "eval_steps_per_second": 4.249,
+      "step": 300
     }
   ],
   "logging_steps": 10,
@@ -258,7 +301,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.505609771679744e+16,
+  "total_flos": 5.412063808585728e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null