Training in progress, step 300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea9950dffcfbb4d3b1ee8d4253efbb1337c7593f8d59b870ad6983ecacebd0f3
+oid sha256:cfcde852ee9a7df2f5bcf7cc836b939566d77608613a6d4a635687153c582c11
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:755f0ea7ae61c6d5fa9fa23eb9eb1e43dfca03ea61dfe87d97b6e1ee10296f8d
-size 328468404
+oid sha256:9d38562cb7ead31bb4f8455b0dd5948da0880af22bf9664749faf057882408fc
+size 328468852

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02ae481c8002fa1263f712f930a5df4f2c49037e33af7892692f742d795e7bee
+oid sha256:1889983b1ecda80870c997c8619834b2bf57d34e140454ca55a974593ecf251f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a83bfe9ce791ae9422d624a37c23887da722084404f306517a014ce665484f8
+oid sha256:ddc1c3c9081614df1d173d04f01c875f9673209b6198d21cb724fdbf44311722
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.151829481124878,
-  "best_model_checkpoint": "miner_id_24/checkpoint-250",
-  "epoch": 0.17458100558659218,
+  "best_metric": 1.1206214427947998,
+  "best_model_checkpoint": "miner_id_24/checkpoint-300",
+  "epoch": 0.20949720670391062,
   "eval_steps": 50,
-  "global_step": 250,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -230,6 +230,49 @@
       "eval_samples_per_second": 11.633,
       "eval_steps_per_second": 2.913,
       "step": 250
+    },
+    {
+      "epoch": 0.18156424581005587,
+      "grad_norm": 0.49490973353385925,
+      "learning_rate": 0.0001198413382645404,
+      "loss": 0.9051,
+      "step": 260
+    },
+    {
+      "epoch": 0.18854748603351956,
+      "grad_norm": 0.419166624546051,
+      "learning_rate": 0.00011228659539222137,
+      "loss": 0.856,
+      "step": 270
+    },
+    {
+      "epoch": 0.19553072625698323,
+      "grad_norm": 0.44810253381729126,
+      "learning_rate": 0.00010471340460777866,
+      "loss": 0.772,
+      "step": 280
+    },
+    {
+      "epoch": 0.20251396648044692,
+      "grad_norm": 0.5431365370750427,
+      "learning_rate": 9.715866173545961e-05,
+      "loss": 0.8117,
+      "step": 290
+    },
+    {
+      "epoch": 0.20949720670391062,
+      "grad_norm": 1.623485803604126,
+      "learning_rate": 8.965917272313806e-05,
+      "loss": 1.9584,
+      "step": 300
+    },
+    {
+      "epoch": 0.20949720670391062,
+      "eval_loss": 1.1206214427947998,
+      "eval_runtime": 51.6387,
+      "eval_samples_per_second": 11.677,
+      "eval_steps_per_second": 2.924,
+      "step": 300
     }
   ],
   "logging_steps": 10,
@@ -258,7 +301,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.06500940529664e+16,
+  "total_flos": 8.48689809063936e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null