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:bf93586a28af1fbaf011ad3492721ea8fc1050b316b7fb495543e4dc36dc386c
+oid sha256:ff476ffa0821524fe14e333ea863933e1ad45c236bb668c02dca26f8e38e9257
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19e5ef0444a996d7ba9cfcf6fd4a64f7430031c080060c4a5ffaf61d1b88ff34
+oid sha256:a627eebb032cb54e9cc98b4837acd719127c52c9bd55ee9357fadc1e95a5f608
 size 250679090

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec7dc567c089b9360385dc88ac6ed83e9342db25848fc49dd9956608ce39fa4a
+oid sha256:8be70d832a1bbff101f33c955af2006518b5495f9530a45087a280e66288a93d
 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": 0.6306657195091248,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.01942690626517727,
+  "best_metric": 0.48243945837020874,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.03885381253035454,
   "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": 5.022,
       "eval_steps_per_second": 2.522,
       "step": 10
+    },
+    {
+      "epoch": 0.021369596891694997,
+      "grad_norm": 1.3569114208221436,
+      "learning_rate": 9.890738003669029e-05,
+      "loss": 3.1272,
+      "step": 11
+    },
+    {
+      "epoch": 0.023312287518212724,
+      "grad_norm": 1.2888952493667603,
+      "learning_rate": 9.567727288213005e-05,
+      "loss": 2.7706,
+      "step": 12
+    },
+    {
+      "epoch": 0.02525497814473045,
+      "grad_norm": 1.3824020624160767,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 2.378,
+      "step": 13
+    },
+    {
+      "epoch": 0.027197668771248178,
+      "grad_norm": 0.6680025458335876,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 1.563,
+      "step": 14
+    },
+    {
+      "epoch": 0.029140359397765905,
+      "grad_norm": 1.1097849607467651,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 1.6712,
+      "step": 15
+    },
+    {
+      "epoch": 0.029140359397765905,
+      "eval_loss": 0.5315653085708618,
+      "eval_runtime": 43.447,
+      "eval_samples_per_second": 4.995,
+      "eval_steps_per_second": 2.509,
+      "step": 15
+    },
+    {
+      "epoch": 0.03108305002428363,
+      "grad_norm": 1.1700183153152466,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 2.3199,
+      "step": 16
+    },
+    {
+      "epoch": 0.03302574065080136,
+      "grad_norm": 1.2776918411254883,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 1.6961,
+      "step": 17
+    },
+    {
+      "epoch": 0.034968431277319086,
+      "grad_norm": 1.0217623710632324,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 2.1827,
+      "step": 18
+    },
+    {
+      "epoch": 0.036911121903836816,
+      "grad_norm": 1.0589659214019775,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 1.3891,
+      "step": 19
+    },
+    {
+      "epoch": 0.03885381253035454,
+      "grad_norm": 2.043240785598755,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.0682,
+      "step": 20
+    },
+    {
+      "epoch": 0.03885381253035454,
+      "eval_loss": 0.48243945837020874,
+      "eval_runtime": 43.5062,
+      "eval_samples_per_second": 4.988,
+      "eval_steps_per_second": 2.505,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3166224305356800.0,
+  "total_flos": 6332448610713600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null