Training in progress, step 250, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c8f50fe2b965692fba8740a59d3a2eddd958e7a3d88ea53809b797387d80737
+oid sha256:5caf7dfcf8ed893ff77a660f14d9d600e2fb93aa38c91403c9e2b1fe492e7e81
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b0fc074cab8930b3f92a6ca2e41c4d035e22d1ca202f609559f7db9fd016b2a
+oid sha256:a41275b1205e8fa27e5c01f2ad55cb4c073ce412ea7b704ba9b5118aef07daee
 size 325339796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8f67d3ffa63a9325a4e54e3858fd9c5305f595b9016fa36f8838ba1575de998
+oid sha256:ee6c65374969079a97d587c57ff4dfef3f5f9263484451a1467b8321bafb06c3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c41568ec8d15c28a2145796b65c5977bed142a18699c02f8db4b41d7a5440c4c
+oid sha256:5245962b37abe5debb29d3c0771306ab720257c32ca897672f6c78751ec6642f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.0043987035751343,
-  "best_model_checkpoint": "miner_id_24/checkpoint-200",
-  "epoch": 0.018889308651303362,
+  "best_metric": 0.9553887248039246,
+  "best_model_checkpoint": "miner_id_24/checkpoint-250",
+  "epoch": 0.023611635814129204,
   "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": 17.351,
       "eval_steps_per_second": 4.34,
       "step": 200
+    },
+    {
+      "epoch": 0.019833774083868532,
+      "grad_norm": 0.7500446438789368,
+      "learning_rate": 0.00015678245500000943,
+      "loss": 1.0322,
+      "step": 210
+    },
+    {
+      "epoch": 0.0207782395164337,
+      "grad_norm": 0.8743635416030884,
+      "learning_rate": 0.00014983211868233444,
+      "loss": 0.9676,
+      "step": 220
+    },
+    {
+      "epoch": 0.021722704948998868,
+      "grad_norm": 0.9597961902618408,
+      "learning_rate": 0.00014268285238686927,
+      "loss": 1.0018,
+      "step": 230
+    },
+    {
+      "epoch": 0.022667170381564034,
+      "grad_norm": 1.6248764991760254,
+      "learning_rate": 0.00013536948662036378,
+      "loss": 0.8842,
+      "step": 240
+    },
+    {
+      "epoch": 0.023611635814129204,
+      "grad_norm": 2.130323886871338,
+      "learning_rate": 0.00012792765136569544,
+      "loss": 0.8014,
+      "step": 250
+    },
+    {
+      "epoch": 0.023611635814129204,
+      "eval_loss": 0.9553887248039246,
+      "eval_runtime": 256.8747,
+      "eval_samples_per_second": 17.355,
+      "eval_steps_per_second": 4.341,
+      "step": 250
     }
   ],
   "logging_steps": 10,
@@ -215,7 +258,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.3728300580864e+16,
+  "total_flos": 4.2139348107264e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null