Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0de498619c03f5bd43d744ca428302b36dd68ef25f5de3b52e9eb8e3c4f457aa
+oid sha256:634856382964ad884b5cb0e39c8a78aa46afe605ba6c9c16679ae3019fa5cced
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfa7b7fe5184f556d1613339f28e52ae99d69738946b0c00fc6fb35dbbeceb7b
+oid sha256:67bbfee61ec6b58ae140b18174bf67af33194ebac6bcd77a6543737b23697c05
 size 168149074

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c79ce16733b6db80aea90add053d7250afe407dd6159d54ee4a13e9dc59595aa
+oid sha256:eff7fd73f973e46014ca0cba260ef1bf771431578dfc80d8fcdb5d9fe1ecc859
 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": 4.402764797210693,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.022185246810870772,
+  "best_metric": 4.217616558074951,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.044370493621741544,
   "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": 5.625,
       "eval_steps_per_second": 2.812,
       "step": 10
+    },
+    {
+      "epoch": 0.024403771491957847,
+      "grad_norm": 2.1179568767547607,
+      "learning_rate": 1.9781476007338058e-05,
+      "loss": 3.8605,
+      "step": 11
+    },
+    {
+      "epoch": 0.026622296173044926,
+      "grad_norm": 3.036003351211548,
+      "learning_rate": 1.913545457642601e-05,
+      "loss": 3.9802,
+      "step": 12
+    },
+    {
+      "epoch": 0.028840820854132,
+      "grad_norm": 4.221029281616211,
+      "learning_rate": 1.8090169943749477e-05,
+      "loss": 3.9111,
+      "step": 13
+    },
+    {
+      "epoch": 0.03105934553521908,
+      "grad_norm": 2.8276443481445312,
+      "learning_rate": 1.6691306063588583e-05,
+      "loss": 4.0468,
+      "step": 14
+    },
+    {
+      "epoch": 0.033277870216306155,
+      "grad_norm": 2.372344732284546,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 3.8586,
+      "step": 15
+    },
+    {
+      "epoch": 0.033277870216306155,
+      "eval_loss": 4.304647445678711,
+      "eval_runtime": 33.8965,
+      "eval_samples_per_second": 5.605,
+      "eval_steps_per_second": 2.803,
+      "step": 15
+    },
+    {
+      "epoch": 0.03549639489739324,
+      "grad_norm": 3.554687261581421,
+      "learning_rate": 1.3090169943749475e-05,
+      "loss": 3.7669,
+      "step": 16
+    },
+    {
+      "epoch": 0.03771491957848031,
+      "grad_norm": 3.1627137660980225,
+      "learning_rate": 1.1045284632676535e-05,
+      "loss": 4.1453,
+      "step": 17
+    },
+    {
+      "epoch": 0.03993344425956739,
+      "grad_norm": 3.4077558517456055,
+      "learning_rate": 8.954715367323468e-06,
+      "loss": 3.5914,
+      "step": 18
+    },
+    {
+      "epoch": 0.04215196894065446,
+      "grad_norm": 2.9431214332580566,
+      "learning_rate": 6.909830056250527e-06,
+      "loss": 3.8104,
+      "step": 19
+    },
+    {
+      "epoch": 0.044370493621741544,
+      "grad_norm": 2.9738147258758545,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 3.5344,
+      "step": 20
+    },
+    {
+      "epoch": 0.044370493621741544,
+      "eval_loss": 4.217616558074951,
+      "eval_runtime": 33.6384,
+      "eval_samples_per_second": 5.648,
+      "eval_steps_per_second": 2.824,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1849564248145920.0,
+  "total_flos": 3699128496291840.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null