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:fe441fe094288b9a7c97256e8ba61b248abaa56d7c0b3dec02c2665e28ddfade
+oid sha256:a44190b135bc3c8f9300efca67ce550817adaf98bb1ac3c2cd21bf00d403999c
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f8a6c49e250e91a3fbbb26e89d42c5021057a01115631a8524fc532fadcc169
+oid sha256:8c10d11bb33e043b91b8ad3d93a335572dc7cfd2ea12cc79c6b0dbf514c9d000
 size 168149074

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c79ce16733b6db80aea90add053d7250afe407dd6159d54ee4a13e9dc59595aa
+oid sha256:80c1d09c2a12ae6aabde409ba2f85375363a1967e5a6f52e8e3b31784463fd73
 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": 2.1534292697906494,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.003328340822100183,
+  "best_metric": 2.099368095397949,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.006656681644200366,
   "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": 7.489,
       "eval_steps_per_second": 3.747,
       "step": 10
+    },
+    {
+      "epoch": 0.0036611749043102015,
+      "grad_norm": 8.140580177307129,
+      "learning_rate": 1.9781476007338058e-05,
+      "loss": 8.3768,
+      "step": 11
+    },
+    {
+      "epoch": 0.00399400898652022,
+      "grad_norm": 6.66556453704834,
+      "learning_rate": 1.913545457642601e-05,
+      "loss": 7.6198,
+      "step": 12
+    },
+    {
+      "epoch": 0.004326843068730238,
+      "grad_norm": 8.427690505981445,
+      "learning_rate": 1.8090169943749477e-05,
+      "loss": 9.0,
+      "step": 13
+    },
+    {
+      "epoch": 0.004659677150940256,
+      "grad_norm": 11.37745189666748,
+      "learning_rate": 1.6691306063588583e-05,
+      "loss": 9.6437,
+      "step": 14
+    },
+    {
+      "epoch": 0.004992511233150275,
+      "grad_norm": 8.17237377166748,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 8.5021,
+      "step": 15
+    },
+    {
+      "epoch": 0.004992511233150275,
+      "eval_loss": 2.121389389038086,
+      "eval_runtime": 167.9606,
+      "eval_samples_per_second": 7.532,
+      "eval_steps_per_second": 3.769,
+      "step": 15
+    },
+    {
+      "epoch": 0.005325345315360293,
+      "grad_norm": 10.338920593261719,
+      "learning_rate": 1.3090169943749475e-05,
+      "loss": 9.3378,
+      "step": 16
+    },
+    {
+      "epoch": 0.005658179397570311,
+      "grad_norm": 12.773215293884277,
+      "learning_rate": 1.1045284632676535e-05,
+      "loss": 8.3154,
+      "step": 17
+    },
+    {
+      "epoch": 0.005991013479780329,
+      "grad_norm": 10.358263969421387,
+      "learning_rate": 8.954715367323468e-06,
+      "loss": 8.038,
+      "step": 18
+    },
+    {
+      "epoch": 0.006323847561990348,
+      "grad_norm": 9.670676231384277,
+      "learning_rate": 6.909830056250527e-06,
+      "loss": 8.7551,
+      "step": 19
+    },
+    {
+      "epoch": 0.006656681644200366,
+      "grad_norm": 10.703207015991211,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 8.5689,
+      "step": 20
+    },
+    {
+      "epoch": 0.006656681644200366,
+      "eval_loss": 2.099368095397949,
+      "eval_runtime": 167.8502,
+      "eval_samples_per_second": 7.536,
+      "eval_steps_per_second": 3.771,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1752669785948160.0,
+  "total_flos": 3549156316545024.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null