Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:144cc8b9ceaed3f35cf8e84ca4e4644c180cd2edfce98ad1d8e5475c193c19a5
+oid sha256:bf861987e9cf010d3be7bfcfd46f8307858dc36872c1bb573a97bd5a32f1f415
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ccbcc6cef96fcd35243d1d37081f6dfcf2138bb025c44f0560f2fc4b105b9c79
+oid sha256:e73f635cf9eda432dd55ebda9db7741298e7a01b91a97a64b0027783fad2c86d
 size 168037178

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9e7b60da0e9120b8b27b8ee1d3907a094318f4f8679b4947c5c539d131c8798
+oid sha256:fc3816115ffca8d86490c789c3fcb51dafd9ddd44dd5e0fd03ea1b926569b8d1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
+oid sha256:b7af249df5fe11a9896f83a1f972a51ac4c516f61ca7fde0473cca60d389d7ec
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.165292739868164,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.00043808251284129364,
+  "best_metric": 0.9942281246185303,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0008761650256825873,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,92 @@
       "eval_samples_per_second": 6.07,
       "eval_steps_per_second": 3.035,
       "step": 10
+    },
+    {
+      "epoch": 0.00048189076412542305,
+      "grad_norm": 0.823034405708313,
+      "learning_rate": 9.890738003669029e-05,
+      "loss": 1.2728,
+      "step": 11
+    },
+    {
+      "epoch": 0.0005256990154095523,
+      "grad_norm": 0.9349016547203064,
+      "learning_rate": 9.567727288213005e-05,
+      "loss": 1.2353,
+      "step": 12
+    },
+    {
+      "epoch": 0.0005695072666936818,
+      "grad_norm": 1.069957971572876,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 1.0641,
+      "step": 13
+    },
+    {
+      "epoch": 0.0006133155179778112,
+      "grad_norm": 1.1222420930862427,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 1.0955,
+      "step": 14
+    },
+    {
+      "epoch": 0.0006571237692619405,
+      "grad_norm": 0.8900039196014404,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.9203,
+      "step": 15
+    },
+    {
+      "epoch": 0.0006571237692619405,
+      "eval_loss": 1.0537456274032593,
+      "eval_runtime": 1581.098,
+      "eval_samples_per_second": 6.079,
+      "eval_steps_per_second": 3.04,
+      "step": 15
+    },
+    {
+      "epoch": 0.0007009320205460699,
+      "grad_norm": 0.8774672150611877,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.8545,
+      "step": 16
+    },
+    {
+      "epoch": 0.0007447402718301992,
+      "grad_norm": 0.741215705871582,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 0.9492,
+      "step": 17
+    },
+    {
+      "epoch": 0.0007885485231143286,
+      "grad_norm": 0.7526450753211975,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 0.8736,
+      "step": 18
+    },
+    {
+      "epoch": 0.0008323567743984579,
+      "grad_norm": 0.6772991418838501,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.9676,
+      "step": 19
+    },
+    {
+      "epoch": 0.0008761650256825873,
+      "grad_norm": 0.6418992877006531,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.8213,
+      "step": 20
+    },
+    {
+      "epoch": 0.0008761650256825873,
+      "eval_loss": 0.9942281246185303,
+      "eval_runtime": 1580.7376,
+      "eval_samples_per_second": 6.081,
+      "eval_steps_per_second": 3.04,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2450672628793344.0,
+  "total_flos": 5225019001012224.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null