Training in progress, step 250, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04d8cea8e9a82e0722ea21850b5baff43a04cd95c2333423701cfc4fbfd168b1
+oid sha256:fc8fa6db0f6368cb7837478f54d88a877260e33cb7231f7d56f75d176ead69e5
 size 78207176

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79c6f3f35563d4b563cd7b3e6be1e3d02a78240d4d6d7ab0c4782784ad4609fa
+oid sha256:c39c76099f9030ee439710f895c12e8a3e2db69aec51a91046254225a7492965
 size 40177764

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aeda9cb70e42fbbb35a1dc0f39125a6383bf6bc683e5b322ad921bdaddae30c0
+oid sha256:98e7257ad47309fc7e2680519ade99aef9be3ec7bb3a4a1d24ea1cd74e5a95ee
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ddd257a0fbff760007b36fbfd6fe1f543f74da89897bf7bfda1b5bee1f0aafc
+oid sha256:5602495352b6664ae4d000d68650c965ce680494b605edac82dbbcad0c94b031
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.0749144554138184,
-  "best_model_checkpoint": "miner_id_24/checkpoint-200",
-  "epoch": 2.191256830601093,
+  "best_metric": 1.0726149082183838,
+  "best_model_checkpoint": "miner_id_24/checkpoint-250",
+  "epoch": 2.737704918032787,
   "eval_steps": 50,
-  "global_step": 200,
+  "global_step": 250,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -75,6 +75,21 @@
       "eval_samples_per_second": 131.601,
       "eval_steps_per_second": 4.28,
       "step": 200
+    },
+    {
+      "epoch": 2.737704918032787,
+      "grad_norm": 0.12534111738204956,
+      "learning_rate": 0.000217,
+      "loss": 1.0443,
+      "step": 250
+    },
+    {
+      "epoch": 2.737704918032787,
+      "eval_loss": 1.0726149082183838,
+      "eval_runtime": 4.5687,
+      "eval_samples_per_second": 134.612,
+      "eval_steps_per_second": 4.378,
+      "step": 250
     }
   ],
   "logging_steps": 50,
@@ -103,7 +118,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.155742301159424e+16,
+  "total_flos": 1.4449868984549376e+16,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null