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:c289e30570510bbc1fe85e9dddf1124d4d9d27faf279d8190146f74366c8b651
+oid sha256:80cf098083e6be16bf73641af06eb2fb48342ed707d928ce21893cc24ec9dfff
 size 138995824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cba8757a8d8e46bfe8b5b599de3592a77eeada7a89782a524299c979ff1f6817
+oid sha256:404883f9b49a9fbf8d42ca08d6de274fd3b30c021dc14e69f766dc8852dddf40
 size 71077780

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc606b024f32950624832b549d8d615f8cbd0bf20ab17b21abbd312c0d57f4ca
+oid sha256:77f60bbff6e8aecbb6064459455b86407666ac7ff107875eaadd58531a093350
 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": 1.8115742206573486,
-  "best_model_checkpoint": "miner_id_24/checkpoint-200",
-  "epoch": 0.005870094802031053,
+  "best_metric": 1.7828339338302612,
+  "best_model_checkpoint": "miner_id_24/checkpoint-250",
+  "epoch": 0.007337618502538816,
   "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": 68.066,
       "eval_steps_per_second": 17.019,
       "step": 200
+    },
+    {
+      "epoch": 0.006163599542132606,
+      "grad_norm": 0.4287732243537903,
+      "learning_rate": 0.00015678245500000943,
+      "loss": 1.8633,
+      "step": 210
+    },
+    {
+      "epoch": 0.006457104282234158,
+      "grad_norm": 0.4952814280986786,
+      "learning_rate": 0.00014983211868233444,
+      "loss": 1.7891,
+      "step": 220
+    },
+    {
+      "epoch": 0.006750609022335711,
+      "grad_norm": 0.6276448965072632,
+      "learning_rate": 0.00014268285238686927,
+      "loss": 1.9548,
+      "step": 230
+    },
+    {
+      "epoch": 0.007044113762437264,
+      "grad_norm": 0.7252087593078613,
+      "learning_rate": 0.00013536948662036378,
+      "loss": 1.8363,
+      "step": 240
+    },
+    {
+      "epoch": 0.007337618502538816,
+      "grad_norm": 0.5657986998558044,
+      "learning_rate": 0.00012792765136569544,
+      "loss": 1.464,
+      "step": 250
+    },
+    {
+      "epoch": 0.007337618502538816,
+      "eval_loss": 1.7828339338302612,
+      "eval_runtime": 211.3794,
+      "eval_samples_per_second": 67.868,
+      "eval_steps_per_second": 16.969,
+      "step": 250
     }
   ],
   "logging_steps": 10,
@@ -215,7 +258,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3219787284480000.0,
+  "total_flos": 4009708431605760.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null