Training in progress, step 350, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07919d84004b61f26317d394d4740d45114572032b53634d3d2fc6d8a0a060ad
+oid sha256:e7728a69927cbf5ab1863d13601cd92aff03ea4fa135fd1ec0340caee3d00a72
 size 500770656

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e6f1c172e8a220f2d46e0282b6538c0f90e75a53be28bceaab7089f94d1c868
+oid sha256:96b4ec67b7573d6ce00f29dae97b772c90015f327ebf5899abca86744d555854
 size 254918356

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:600bab2610486e5cca8bbdf2a9039385561e501d1ce2f750f9ab0c297dad933c
+oid sha256:f42e4ed2746f873dd9feb1b455b35ef31397e4f06da2a8f67a66db11d226b07b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef9686b06e8feaa36ed10d72ecd8afef7e62f88744e516a900f077a3e6a083d3
+oid sha256:1a982b0cf4aa3113be3ccf8c7c44abbcbdbc330e78e6392b70eb543df2118de5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.3297315835952759,
-  "best_model_checkpoint": "miner_id_24/checkpoint-300",
-  "epoch": 0.10033025375193345,
+  "best_metric": 0.3258623778820038,
+  "best_model_checkpoint": "miner_id_24/checkpoint-350",
+  "epoch": 0.11705196271058903,
   "eval_steps": 50,
-  "global_step": 300,
+  "global_step": 350,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -112,6 +112,21 @@
       "eval_samples_per_second": 5.73,
       "eval_steps_per_second": 2.866,
       "step": 300
+    },
+    {
+      "epoch": 0.10701893733539568,
+      "grad_norm": 0.9799840450286865,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.6739,
+      "step": 320
+    },
+    {
+      "epoch": 0.11705196271058903,
+      "eval_loss": 0.3258623778820038,
+      "eval_runtime": 439.5044,
+      "eval_samples_per_second": 5.731,
+      "eval_steps_per_second": 2.867,
+      "step": 350
     }
   ],
   "logging_steps": 40,
@@ -140,7 +155,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.82715559936e+17,
+  "total_flos": 4.46501486592e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null