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:a38ae9b6d7dd6a2134011072255d01252c347a08f9d66f78e60bdc102ee55547
+oid sha256:4c8f60d3fa23fa2a39f53ea9e95df98ff6f0c56312790acd3f013ec94e014da4
 size 522227376

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebdbd92097a4de62af1c8429859e237321fdaaf8ff9bcd28264e1f70cec8df56
+oid sha256:e49d1d44a09e2fda87cce89974b96e63ed832d170f3d4983f263ce81e88efbb4
 size 265476692

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efd037109675157bac8d9d0f359c6178fa8f29b572f1988cdb5dfd3d74bb0d0b
+oid sha256:aef1809ee9f39e0d97b8c2069b51ce98ab74705ce0cfc31e4dad4c3086a18da2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c0c9560ea4ec378bff0927b20fa3ef4645adc76e93a49024ae06865cbf33e40
+oid sha256:de68da4a411755dd89261d95dc85b46978ce68b71b6b640a5e732fce38d3ca1d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.49377894401550293,
-  "best_model_checkpoint": "miner_id_24/checkpoint-400",
-  "epoch": 0.0821186614658181,
+  "best_metric": 0.4664444029331207,
+  "best_model_checkpoint": "miner_id_24/checkpoint-450",
+  "epoch": 0.09238349414904537,
   "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": 19.496,
       "eval_steps_per_second": 4.876,
       "step": 400
+    },
+    {
+      "epoch": 0.08417162800246356,
+      "grad_norm": 0.9373986721038818,
+      "learning_rate": 1.9193792065317794e-05,
+      "loss": 0.9801,
+      "step": 410
+    },
+    {
+      "epoch": 0.08622459453910901,
+      "grad_norm": 1.0940189361572266,
+      "learning_rate": 1.5271166336279193e-05,
+      "loss": 0.8796,
+      "step": 420
+    },
+    {
+      "epoch": 0.08827756107575446,
+      "grad_norm": 1.5621163845062256,
+      "learning_rate": 1.1763766917677837e-05,
+      "loss": 0.9008,
+      "step": 430
+    },
+    {
+      "epoch": 0.09033052761239992,
+      "grad_norm": 1.7984567880630493,
+      "learning_rate": 8.688681506918602e-06,
+      "loss": 0.9493,
+      "step": 440
+    },
+    {
+      "epoch": 0.09238349414904537,
+      "grad_norm": 2.2290990352630615,
+      "learning_rate": 6.060891611016215e-06,
+      "loss": 0.9034,
+      "step": 450
+    },
+    {
+      "epoch": 0.09238349414904537,
+      "eval_loss": 0.4664444029331207,
+      "eval_runtime": 105.4397,
+      "eval_samples_per_second": 19.452,
+      "eval_steps_per_second": 4.865,
+      "step": 450
     }
   ],
   "logging_steps": 10,
@@ -387,7 +430,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.89128669446144e+16,
+  "total_flos": 7.754773220032512e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null