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:a9673b75ff65472cf57920ac8a5f565af82b0d021c9df5c932559e7fd1b14466
+oid sha256:67b9a4a320616636e7866c76549f2a8c0434284e05d58d53698f393f2fc7b1a8
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e281237073b69b36f28fea5d91b0d182297d679b915d4c1aaeda68875c0d1637
+oid sha256:6fdaf64de66dad028f43e60ec55e0589f71a11cc71e7905cdd6d516dbff20288
 size 170920532

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a4c01728ceb4d2b09187d13e5e5264c8535951394a0a7a1619f2855925e0d60
+oid sha256:a49cddaaa216a751d27007e436849ce112f09937a88b6fc75f253a22548d3653
 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": 1.4548931121826172,
-  "best_model_checkpoint": "miner_id_24/checkpoint-300",
-  "epoch": 0.3180492976411344,
+  "best_metric": 1.3930524587631226,
+  "best_model_checkpoint": "miner_id_24/checkpoint-350",
+  "epoch": 0.37105751391465674,
   "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": 14.504,
       "eval_steps_per_second": 7.261,
       "step": 300
+    },
+    {
+      "epoch": 0.3392525841505433,
+      "grad_norm": 14.403338432312012,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 11.2139,
+      "step": 320
+    },
+    {
+      "epoch": 0.37105751391465674,
+      "eval_loss": 1.3930524587631226,
+      "eval_runtime": 56.2238,
+      "eval_samples_per_second": 14.14,
+      "eval_steps_per_second": 7.079,
+      "step": 350
     }
   ],
   "logging_steps": 40,
@@ -140,7 +155,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0728138896886989e+17,
+  "total_flos": 1.2509531552612352e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null