Training in progress, step 250, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec12c9880ca9278de2fd154e2cec12e50b3ce03645100d9aefd09317e446c2ec
+oid sha256:f476c14f58ba0837919df0c4566393a424c0f18ea175a9197d55c8ee490a7ecb
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4708c75106f3317c6b5057284ce8b3fc9a7dbe40061f0d6dcfca2976a00512e6
+oid sha256:bb22a84216ab857e57f3489e07ead6224109b073a16d42f90998729a52446b4e
 size 82460660

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8b5daeff2c604fbc5db6562bda0b1a93f0aa77f364615e478712a03bb721857
+oid sha256:8a6acff0a45e8376b10f910d417b43933611365487e290e196349a7418f332fe
 size 14308

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1782a34e31686f496476697aa213a8a4eb0ce51a76589caf9070e07b3ee2de6a
+oid sha256:19982defd909244c1a267113c1b0599a7e78f1ad3657e653842b9f7b9c37fd25
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.3707703351974487,
-  "best_model_checkpoint": "miner_id_24/checkpoint-200",
-  "epoch": 0.11524056467876692,
+  "best_metric": 1.3522343635559082,
+  "best_model_checkpoint": "miner_id_24/checkpoint-250",
+  "epoch": 0.14405070584845867,
   "eval_steps": 50,
-  "global_step": 200,
+  "global_step": 250,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -187,6 +187,49 @@
       "eval_samples_per_second": 16.283,
       "eval_steps_per_second": 4.076,
       "step": 200
+    },
+    {
+      "epoch": 0.12100259291270528,
+      "grad_norm": 0.5921943783760071,
+      "learning_rate": 0.0001546248982798258,
+      "loss": 1.7297,
+      "step": 210
+    },
+    {
+      "epoch": 0.1267646211466436,
+      "grad_norm": 0.6880895495414734,
+      "learning_rate": 0.00014777020879221055,
+      "loss": 1.5429,
+      "step": 220
+    },
+    {
+      "epoch": 0.13252664938058195,
+      "grad_norm": 1.1970090866088867,
+      "learning_rate": 0.00014071932689530684,
+      "loss": 1.3795,
+      "step": 230
+    },
+    {
+      "epoch": 0.13828867761452032,
+      "grad_norm": 1.1682662963867188,
+      "learning_rate": 0.00013350660377696428,
+      "loss": 1.113,
+      "step": 240
+    },
+    {
+      "epoch": 0.14405070584845867,
+      "grad_norm": 1.2679342031478882,
+      "learning_rate": 0.00012616717909919503,
+      "loss": 0.7694,
+      "step": 250
+    },
+    {
+      "epoch": 0.14405070584845867,
+      "eval_loss": 1.3522343635559082,
+      "eval_runtime": 44.9013,
+      "eval_samples_per_second": 16.28,
+      "eval_steps_per_second": 4.076,
+      "step": 250
     }
   ],
   "logging_steps": 10,
@@ -215,7 +258,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.626263221633024e+16,
+  "total_flos": 4.535013522957926e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null