Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46395f6f4c73e9a23dfaaabbe69b89067a54226fcbc7c174637c0fa0bb600e50
+oid sha256:945fc7eece7cc22e8ef95aed85d8dbf3a10057831eb21355b1f223d8c267c3fb
 size 50899792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd8a82ee41f30e6d4bc68d2fd9e68b697887cc954ebb1e939b210b9cdc0c2e6d
+oid sha256:931f2ae219ced8c9a837e938eabdcdc2e3325b89bac538566f7944c38980d852
 size 102009558

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bace1f47a0df86443734a99f5e182c48571d7de135a2c5f4b6522e11d755e0a5
+oid sha256:f9d1ebf09b505f76dee426288bfee7734b789b5ffb4a889d3987eebbc6d9d6ae
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b8bc8abd4c9f82dfc46828b9bd127304694d7b33110834b4b23e29a7f6b47fd
+oid sha256:c2d5f342d4229a407b143249c0b0919abc73174c3fbf690cf4dd4451580b8e09
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.515305995941162,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0007669446841146582,
+  "best_metric": 2.433856248855591,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0015338893682293165,
   "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": 13.154,
       "eval_steps_per_second": 6.577,
       "step": 10
+    },
+    {
+      "epoch": 0.0008436391525261241,
+      "grad_norm": 0.5526045560836792,
+      "learning_rate": 1.9781476007338058e-05,
+      "loss": 2.4659,
+      "step": 11
+    },
+    {
+      "epoch": 0.0009203336209375898,
+      "grad_norm": 0.7641571164131165,
+      "learning_rate": 1.913545457642601e-05,
+      "loss": 2.4907,
+      "step": 12
+    },
+    {
+      "epoch": 0.0009970280893490558,
+      "grad_norm": 0.6876296401023865,
+      "learning_rate": 1.8090169943749477e-05,
+      "loss": 2.4951,
+      "step": 13
+    },
+    {
+      "epoch": 0.0010737225577605216,
+      "grad_norm": 0.893703818321228,
+      "learning_rate": 1.6691306063588583e-05,
+      "loss": 2.6525,
+      "step": 14
+    },
+    {
+      "epoch": 0.0011504170261719873,
+      "grad_norm": 0.6102678179740906,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 2.2531,
+      "step": 15
+    },
+    {
+      "epoch": 0.0011504170261719873,
+      "eval_loss": 2.4703986644744873,
+      "eval_runtime": 417.428,
+      "eval_samples_per_second": 13.152,
+      "eval_steps_per_second": 6.576,
+      "step": 15
+    },
+    {
+      "epoch": 0.001227111494583453,
+      "grad_norm": 0.6123389601707458,
+      "learning_rate": 1.3090169943749475e-05,
+      "loss": 2.4546,
+      "step": 16
+    },
+    {
+      "epoch": 0.001303805962994919,
+      "grad_norm": 0.7166579961776733,
+      "learning_rate": 1.1045284632676535e-05,
+      "loss": 2.4489,
+      "step": 17
+    },
+    {
+      "epoch": 0.0013805004314063848,
+      "grad_norm": 0.6961430907249451,
+      "learning_rate": 8.954715367323468e-06,
+      "loss": 2.4205,
+      "step": 18
+    },
+    {
+      "epoch": 0.0014571948998178506,
+      "grad_norm": 0.625072181224823,
+      "learning_rate": 6.909830056250527e-06,
+      "loss": 2.3686,
+      "step": 19
+    },
+    {
+      "epoch": 0.0015338893682293165,
+      "grad_norm": 0.6170470118522644,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 2.3949,
+      "step": 20
+    },
+    {
+      "epoch": 0.0015338893682293165,
+      "eval_loss": 2.433856248855591,
+      "eval_runtime": 417.1619,
+      "eval_samples_per_second": 13.16,
+      "eval_steps_per_second": 6.58,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1250574214103040.0,
+  "total_flos": 2562652078080000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null