Training in progress, step 550, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7931c8629b10bcb3c46f312d6c443a54a2a48235580af5d7456c2ae18bf0ca2
+oid sha256:ddc849f67df44c0f94d94e50d3138d44e678691377fbca6c6a6eb5a5ada8845e
 size 72396376

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98c509aa7ad8a62165ac20ffbdd603d04e7f0f343031939c9db41d61e938203d
+oid sha256:58ea048ccc35d066e768949acd5b2b5723823827ea6db1d1ee2200d23cdf55d5
 size 37134740

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:155b07930e359433d6f58b15ccf7fec7f70457bb2abf5bdbdb44970b5f4ce523
+oid sha256:1b61b7f19e5d89fcee16059d0b521fd7346a03cdf1b23e4aaf0a3720db2476c1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b782a524e5b57eb023365370accae538ac5e68454bafa53a6dd8b2c51cead56
+oid sha256:6bb9c0d62d6b3cf0976c16f73e9bd814b298ebffa1786831bc2a68d8e48809b9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2039023637771606,
-  "best_model_checkpoint": "miner_id_24/checkpoint-500",
-  "epoch": 0.32647730982696704,
+  "best_metric": 1.2006784677505493,
+  "best_model_checkpoint": "miner_id_24/checkpoint-550",
+  "epoch": 0.35912504080966373,
   "eval_steps": 50,
-  "global_step": 500,
+  "global_step": 550,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -445,6 +445,49 @@
       "eval_samples_per_second": 60.529,
       "eval_steps_per_second": 15.138,
       "step": 500
+    },
+    {
+      "epoch": 0.3330068560235064,
+      "grad_norm": 0.05650899186730385,
+      "learning_rate": 1.1264792494342857e-05,
+      "loss": 1.1749,
+      "step": 510
+    },
+    {
+      "epoch": 0.3395364022200457,
+      "grad_norm": 0.0797816812992096,
+      "learning_rate": 8.936522714508678e-06,
+      "loss": 1.2085,
+      "step": 520
+    },
+    {
+      "epoch": 0.34606594841658506,
+      "grad_norm": 0.14462202787399292,
+      "learning_rate": 6.866382254766157e-06,
+      "loss": 1.2441,
+      "step": 530
+    },
+    {
+      "epoch": 0.3525954946131244,
+      "grad_norm": 0.30583634972572327,
+      "learning_rate": 5.060239153161872e-06,
+      "loss": 1.2586,
+      "step": 540
+    },
+    {
+      "epoch": 0.35912504080966373,
+      "grad_norm": 0.7339666485786438,
+      "learning_rate": 3.5232131185484076e-06,
+      "loss": 1.1969,
+      "step": 550
+    },
+    {
+      "epoch": 0.35912504080966373,
+      "eval_loss": 1.2006784677505493,
+      "eval_runtime": 41.9627,
+      "eval_samples_per_second": 61.459,
+      "eval_steps_per_second": 15.371,
+      "step": 550
     }
   ],
   "logging_steps": 10,
@@ -473,7 +516,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.133976917855437e+16,
+  "total_flos": 8.942571079965082e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null