Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69c0d0f0165f2e320264b0cbf7a406d8ade6350ee3ddad75d08ab7a097c3d1b7
+oid sha256:b7931c8629b10bcb3c46f312d6c443a54a2a48235580af5d7456c2ae18bf0ca2
 size 72396376

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c3419855da5d9fa1454decf9c5559af4499b354f8e3df8d2778fcf7856fbb86
+oid sha256:98c509aa7ad8a62165ac20ffbdd603d04e7f0f343031939c9db41d61e938203d
 size 37134740

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44a493c7fd0594ffa7fd7ceee4d682a949a06d6dbea4370ae50c901b5384a7d8
+oid sha256:155b07930e359433d6f58b15ccf7fec7f70457bb2abf5bdbdb44970b5f4ce523
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70f0f789b56065211b8c0b1a5e2a97dd0b5b08a816bbbe288fb6f9c677282af9
+oid sha256:5b782a524e5b57eb023365370accae538ac5e68454bafa53a6dd8b2c51cead56
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2068712711334229,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.2938295788442703,
+  "best_metric": 1.2039023637771606,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.32647730982696704,
   "eval_steps": 50,
-  "global_step": 450,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -402,6 +402,49 @@
       "eval_samples_per_second": 60.372,
       "eval_steps_per_second": 15.099,
       "step": 450
+    },
+    {
+      "epoch": 0.30035912504080964,
+      "grad_norm": 0.054399143904447556,
+      "learning_rate": 2.6522584913693294e-05,
+      "loss": 1.1521,
+      "step": 460
+    },
+    {
+      "epoch": 0.30688867123734903,
+      "grad_norm": 0.08509223908185959,
+      "learning_rate": 2.301660165700936e-05,
+      "loss": 1.2187,
+      "step": 470
+    },
+    {
+      "epoch": 0.31341821743388837,
+      "grad_norm": 0.1509586125612259,
+      "learning_rate": 1.9728836206903656e-05,
+      "loss": 1.3379,
+      "step": 480
+    },
+    {
+      "epoch": 0.3199477636304277,
+      "grad_norm": 0.3751097619533539,
+      "learning_rate": 1.6668608091748495e-05,
+      "loss": 1.3362,
+      "step": 490
+    },
+    {
+      "epoch": 0.32647730982696704,
+      "grad_norm": 0.8351140022277832,
+      "learning_rate": 1.3844591860619383e-05,
+      "loss": 1.1598,
+      "step": 500
+    },
+    {
+      "epoch": 0.32647730982696704,
+      "eval_loss": 1.2039023637771606,
+      "eval_runtime": 42.6078,
+      "eval_samples_per_second": 60.529,
+      "eval_steps_per_second": 15.138,
+      "step": 500
     }
   ],
   "logging_steps": 10,
@@ -430,7 +473,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.317376872952627e+16,
+  "total_flos": 8.133976917855437e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null