Training in progress, step 450, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14ba48befd82e4f7c96e57549c11268ac68a7d1f9dc7a4c3f77c1a1398f18b39
+oid sha256:17cadc048220e3a70472c6de341215e22785ef389947a3f2cb5021ff19c9a727
 size 912336848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6954946c8cd2779891edd1a200d0b7a1ecf43e4342d859140814b57116a8b1d1
+oid sha256:de26fd62dc109df9ed6159f8144e2859bbd1afa933f83df1a105e9493e6eee85
 size 463916756

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7f675f04305c476590630ac04744c733a90f052099537a9d606ac17e814ed5e
+oid sha256:09cbf29821d67ea37a69b5596a2b6b019c1fa77850ddbf4f16c024c353bd8c68
 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": 0.6076525449752808,
-  "best_model_checkpoint": "miner_id_24/checkpoint-400",
-  "epoch": 0.18867924528301888,
+  "best_metric": 0.549039363861084,
+  "best_model_checkpoint": "miner_id_24/checkpoint-450",
+  "epoch": 0.21226415094339623,
   "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": 11.265,
       "eval_steps_per_second": 2.826,
       "step": 400
+    },
+    {
+      "epoch": 0.19339622641509435,
+      "grad_norm": 2.413058280944824,
+      "learning_rate": 2.0148707093443057e-05,
+      "loss": 1.5055,
+      "step": 410
+    },
+    {
+      "epoch": 0.19811320754716982,
+      "grad_norm": 2.6474435329437256,
+      "learning_rate": 1.603092585549706e-05,
+      "loss": 1.4478,
+      "step": 420
+    },
+    {
+      "epoch": 0.2028301886792453,
+      "grad_norm": 2.5455524921417236,
+      "learning_rate": 1.2349028953383204e-05,
+      "loss": 1.5041,
+      "step": 430
+    },
+    {
+      "epoch": 0.20754716981132076,
+      "grad_norm": 64.91968536376953,
+      "learning_rate": 9.120954218705596e-06,
+      "loss": 10.0888,
+      "step": 440
+    },
+    {
+      "epoch": 0.21226415094339623,
+      "grad_norm": 0.0022940777707844973,
+      "learning_rate": 6.362428507086673e-06,
+      "loss": 0.0065,
+      "step": 450
+    },
+    {
+      "epoch": 0.21226415094339623,
+      "eval_loss": 0.549039363861084,
+      "eval_runtime": 79.325,
+      "eval_samples_per_second": 11.257,
+      "eval_steps_per_second": 2.824,
+      "step": 450
     }
   ],
   "logging_steps": 10,
@@ -387,7 +430,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.16045503266816e+17,
+  "total_flos": 1.30551191175168e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null