Training in progress, step 450, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5be06d89636136f65723801547e9387887f12e3651b7be197af26ba4e1e2eeea
+oid sha256:93ea8994e37e61a66bd6add0c072f1d8a5c3654eced90170effdcf95cb6da80d
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce932894d403155e8c034c3855311100c52f923afc18c0a79b27bf478167c715
+oid sha256:f1cabd44590080c7a3c1758bd06acda11d17e7fecbd3fece13b22d9139765bec
 size 341314644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8d49a562b2fcf037d4f0d8fc6a0a49bb0f67ceec737e0d51bc552357f1531b2
+oid sha256:4d9c4c2fe48f9cad88212b05e4eb04c6d59c6f3daaab9f786cf98b22056361f9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3090df11bc2445b62bc263a9812782b2cdb94f2d343087e4b12056e17b9122a5
+oid sha256:2e959ae44ed59e1d9df727fe405a413d7ba7165046402e1b6aa379cddd545297
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.1870886087417603,
-  "best_model_checkpoint": "miner_id_24/checkpoint-400",
-  "epoch": 0.00602237311612641,
+  "best_metric": 1.1760796308517456,
+  "best_model_checkpoint": "miner_id_24/checkpoint-450",
+  "epoch": 0.00677516975564221,
   "eval_steps": 50,
-  "global_step": 400,
+  "global_step": 450,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -359,6 +359,49 @@
       "eval_samples_per_second": 14.446,
       "eval_steps_per_second": 3.612,
       "step": 400
+    },
+    {
+      "epoch": 0.00617293244402957,
+      "grad_norm": 0.8027336597442627,
+      "learning_rate": 2.0148707093443057e-05,
+      "loss": 0.7747,
+      "step": 410
+    },
+    {
+      "epoch": 0.00632349177193273,
+      "grad_norm": 1.1250958442687988,
+      "learning_rate": 1.603092585549706e-05,
+      "loss": 1.0024,
+      "step": 420
+    },
+    {
+      "epoch": 0.00647405109983589,
+      "grad_norm": 1.6558661460876465,
+      "learning_rate": 1.2349028953383204e-05,
+      "loss": 1.3001,
+      "step": 430
+    },
+    {
+      "epoch": 0.00662461042773905,
+      "grad_norm": 3.063714027404785,
+      "learning_rate": 9.120954218705596e-06,
+      "loss": 1.3263,
+      "step": 440
+    },
+    {
+      "epoch": 0.00677516975564221,
+      "grad_norm": 4.5941290855407715,
+      "learning_rate": 6.362428507086673e-06,
+      "loss": 1.2862,
+      "step": 450
+    },
+    {
+      "epoch": 0.00677516975564221,
+      "eval_loss": 1.1760796308517456,
+      "eval_runtime": 1939.0126,
+      "eval_samples_per_second": 14.423,
+      "eval_steps_per_second": 3.606,
+      "step": 450
     }
   ],
   "logging_steps": 10,
@@ -387,7 +430,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.66452486792151e+16,
+  "total_flos": 9.77705363224658e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null