Training in progress, step 250, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:392586bbd1d2e0bfd03a12554658d1e295050b4c5ddf2a9b1f635b349bbf03df
+oid sha256:b7e855a35f141b5253607d53f94522c7f284d2be9cc5e3dabbea324b5352af47
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cffc1441a3bb67007c6dc9aadc468cd33a3680bdb5d757caafe5fc9ae7d64cd
+oid sha256:5a4a41ac6a3b5f191aab5d435dfc2db58bb3d9f5b72d19929c40bcb83c6a7c4e
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b05e3ff61da4b09e0b44b4180d36a0787a179101f6710bc48bb92a55540b2bff
+oid sha256:b37d25a32f33a65385df3a85085a9aa67a364c56de5b730154339b363ed6b6ad
 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": 2.2128450870513916,
-  "best_model_checkpoint": "miner_id_24/checkpoint-200",
-  "epoch": 0.07216308858019123,
+  "best_metric": 2.196916341781616,
+  "best_model_checkpoint": "miner_id_24/checkpoint-250",
+  "epoch": 0.09020386072523905,
   "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": 15.904,
       "eval_steps_per_second": 3.979,
       "step": 200
+    },
+    {
+      "epoch": 0.0757712430092008,
+      "grad_norm": 1.2760608196258545,
+      "learning_rate": 0.00015678245500000943,
+      "loss": 2.2211,
+      "step": 210
+    },
+    {
+      "epoch": 0.07937939743821036,
+      "grad_norm": 1.7979975938796997,
+      "learning_rate": 0.00014983211868233444,
+      "loss": 2.3215,
+      "step": 220
+    },
+    {
+      "epoch": 0.08298755186721991,
+      "grad_norm": 2.1475672721862793,
+      "learning_rate": 0.00014268285238686927,
+      "loss": 2.1729,
+      "step": 230
+    },
+    {
+      "epoch": 0.08659570629622948,
+      "grad_norm": 2.0573699474334717,
+      "learning_rate": 0.00013536948662036378,
+      "loss": 2.0533,
+      "step": 240
+    },
+    {
+      "epoch": 0.09020386072523905,
+      "grad_norm": 5.545847415924072,
+      "learning_rate": 0.00012792765136569544,
+      "loss": 2.0229,
+      "step": 250
+    },
+    {
+      "epoch": 0.09020386072523905,
+      "eval_loss": 2.196916341781616,
+      "eval_runtime": 73.0911,
+      "eval_samples_per_second": 15.966,
+      "eval_steps_per_second": 3.995,
+      "step": 250
     }
   ],
   "logging_steps": 10,
@@ -215,7 +258,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.893850675137741e+16,
+  "total_flos": 4.864956291455386e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null