Training in progress, step 300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c33d14a1446a853ffae6472e0d722e77d45aa291020d64234d30aeaf8f230620
+oid sha256:a51579b106688c68b29a853dff4455ec147ba32914864ff41f585b3e0418ca95
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a5fb8dc5333e29e18f407ddccab9f2284913fb4dd7971c4bc59cd5bcc8f264e
-size 328468404
+oid sha256:988e0150d49a2651e1005b097bc92b3dfcd4401ecd2b6d301c45e45cfdbed147
+size 328468852

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02ae481c8002fa1263f712f930a5df4f2c49037e33af7892692f742d795e7bee
+oid sha256:1889983b1ecda80870c997c8619834b2bf57d34e140454ca55a974593ecf251f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c025e03e0d8ded968e4f23b186aaafce8f23c2a50b134c4f77cea95627049ac8
+oid sha256:09bf653dc25e0c029a8db4ba507ae3589e41445bb2b0fcc38f99c09150129f49
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.148054599761963,
-  "best_model_checkpoint": "miner_id_24/checkpoint-250",
-  "epoch": 0.17458100558659218,
+  "best_metric": 1.1187446117401123,
+  "best_model_checkpoint": "miner_id_24/checkpoint-300",
+  "epoch": 0.20949720670391062,
   "eval_steps": 50,
-  "global_step": 250,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -230,6 +230,49 @@
       "eval_samples_per_second": 11.575,
       "eval_steps_per_second": 2.898,
       "step": 250
+    },
+    {
+      "epoch": 0.18156424581005587,
+      "grad_norm": 0.48482319712638855,
+      "learning_rate": 0.00011597548864310363,
+      "loss": 0.9017,
+      "step": 260
+    },
+    {
+      "epoch": 0.18854748603351956,
+      "grad_norm": 0.42090746760368347,
+      "learning_rate": 0.00010866444715376263,
+      "loss": 0.8558,
+      "step": 270
+    },
+    {
+      "epoch": 0.19553072625698323,
+      "grad_norm": 0.44340935349464417,
+      "learning_rate": 0.00010133555284623744,
+      "loss": 0.7718,
+      "step": 280
+    },
+    {
+      "epoch": 0.20251396648044692,
+      "grad_norm": 0.5416050553321838,
+      "learning_rate": 9.402451135689641e-05,
+      "loss": 0.8102,
+      "step": 290
+    },
+    {
+      "epoch": 0.20949720670391062,
+      "grad_norm": 1.8410241603851318,
+      "learning_rate": 8.676694134497232e-05,
+      "loss": 1.9591,
+      "step": 300
+    },
+    {
+      "epoch": 0.20949720670391062,
+      "eval_loss": 1.1187446117401123,
+      "eval_runtime": 51.9082,
+      "eval_samples_per_second": 11.617,
+      "eval_steps_per_second": 2.909,
+      "step": 300
     }
   ],
   "logging_steps": 10,
@@ -258,7 +301,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.06500940529664e+16,
+  "total_flos": 8.48689809063936e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null