Training in progress, step 250, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7274c55c927d3afc48714d91a3ae6ce57a85c2ca6d976c49994ec951c5ec7f99
+oid sha256:ddc0d080daf9f36b20d9af7f32de001f50cda12c7d0babdbb79d46ee9643dcf5
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50ef1ac3cc0763621815f41da8edf01f21779347746dc1aa99d8385ee3aa9e56
+oid sha256:3dc805f052e23ef1d50bb2f989067dd601be6bc613556b646acd36f8d3b2e714
 size 328468404

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9a91b7b1000237604b7d2bb13fa6d3278f6427f80e66de5f4a8a7558e4d7f3b
+oid sha256:0a8bf54e605c69e3ca1544f43f033c47c7e11641af7e205ed25a5aa2e16f1dcd
 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": 1.6833069324493408,
-  "best_model_checkpoint": "miner_id_24/checkpoint-200",
-  "epoch": 0.1718213058419244,
+  "best_metric": 1.633361577987671,
+  "best_model_checkpoint": "miner_id_24/checkpoint-250",
+  "epoch": 0.21477663230240548,
   "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": 17.749,
       "eval_steps_per_second": 4.455,
       "step": 200
+    },
+    {
+      "epoch": 0.18041237113402062,
+      "grad_norm": 0.8244263529777527,
+      "learning_rate": 0.00015678245500000943,
+      "loss": 1.78,
+      "step": 210
+    },
+    {
+      "epoch": 0.18900343642611683,
+      "grad_norm": 0.9824907779693604,
+      "learning_rate": 0.00014983211868233444,
+      "loss": 1.6569,
+      "step": 220
+    },
+    {
+      "epoch": 0.19759450171821305,
+      "grad_norm": 1.210037350654602,
+      "learning_rate": 0.00014268285238686927,
+      "loss": 1.6465,
+      "step": 230
+    },
+    {
+      "epoch": 0.20618556701030927,
+      "grad_norm": 1.3609579801559448,
+      "learning_rate": 0.00013536948662036378,
+      "loss": 1.4355,
+      "step": 240
+    },
+    {
+      "epoch": 0.21477663230240548,
+      "grad_norm": 2.412757396697998,
+      "learning_rate": 0.00012792765136569544,
+      "loss": 1.4067,
+      "step": 250
+    },
+    {
+      "epoch": 0.21477663230240548,
+      "eval_loss": 1.633361577987671,
+      "eval_runtime": 27.6613,
+      "eval_samples_per_second": 17.714,
+      "eval_steps_per_second": 4.447,
+      "step": 250
     }
   ],
   "logging_steps": 10,
@@ -215,7 +258,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.5547217133568e+16,
+  "total_flos": 4.443402141696e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null