Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:348d60ac1b34800ec2849b66fc67ac7040d994112415e129af1a3fa0b5a490d2
+oid sha256:7a09b06d5672cc3af0487a720566bb2e0f21c920af30411cfccb781ec93f1208
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e655ab9dab28e35b8d6bf123f1c9daaa7b9d3da7074e12b3cad5ae5aeaa8faa7
+oid sha256:7a58f5aa8cdcb10c427ab588dab2fcea300b67fe3d26d8716226247cd98115c6
 size 250819170

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:565c117b0554bcadbb2962d5778f478da838b047d26cc08e6b3663c916f71fed
+oid sha256:e4b82d94a3f3ba4658ccb6aa5c8b6ba7ae6394ee1ce2647f24e42e072d6200c3
 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": 2.4917423725128174,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.021586616297895305,
+  "best_metric": 2.474599599838257,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.04317323259579061,
   "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": 5.902,
       "eval_steps_per_second": 2.966,
       "step": 10
+    },
+    {
+      "epoch": 0.023745277927684834,
+      "grad_norm": 0.4039216935634613,
+      "learning_rate": 1.9781476007338058e-05,
+      "loss": 2.3033,
+      "step": 11
+    },
+    {
+      "epoch": 0.025903939557474366,
+      "grad_norm": 0.4976852536201477,
+      "learning_rate": 1.913545457642601e-05,
+      "loss": 2.5265,
+      "step": 12
+    },
+    {
+      "epoch": 0.028062601187263895,
+      "grad_norm": 0.40776801109313965,
+      "learning_rate": 1.8090169943749477e-05,
+      "loss": 2.4908,
+      "step": 13
+    },
+    {
+      "epoch": 0.030221262817053427,
+      "grad_norm": 0.49444299936294556,
+      "learning_rate": 1.6691306063588583e-05,
+      "loss": 2.476,
+      "step": 14
+    },
+    {
+      "epoch": 0.032379924446842956,
+      "grad_norm": 0.6038114428520203,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 2.3912,
+      "step": 15
+    },
+    {
+      "epoch": 0.032379924446842956,
+      "eval_loss": 2.4828007221221924,
+      "eval_runtime": 34.2086,
+      "eval_samples_per_second": 5.7,
+      "eval_steps_per_second": 2.865,
+      "step": 15
+    },
+    {
+      "epoch": 0.03453858607663249,
+      "grad_norm": 0.5087575912475586,
+      "learning_rate": 1.3090169943749475e-05,
+      "loss": 2.6166,
+      "step": 16
+    },
+    {
+      "epoch": 0.03669724770642202,
+      "grad_norm": 0.6161304712295532,
+      "learning_rate": 1.1045284632676535e-05,
+      "loss": 2.3413,
+      "step": 17
+    },
+    {
+      "epoch": 0.038855909336211546,
+      "grad_norm": 0.8429335951805115,
+      "learning_rate": 8.954715367323468e-06,
+      "loss": 2.8171,
+      "step": 18
+    },
+    {
+      "epoch": 0.04101457096600108,
+      "grad_norm": 0.46091142296791077,
+      "learning_rate": 6.909830056250527e-06,
+      "loss": 2.2982,
+      "step": 19
+    },
+    {
+      "epoch": 0.04317323259579061,
+      "grad_norm": 0.5474252700805664,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 2.563,
+      "step": 20
+    },
+    {
+      "epoch": 0.04317323259579061,
+      "eval_loss": 2.474599599838257,
+      "eval_runtime": 34.2783,
+      "eval_samples_per_second": 5.689,
+      "eval_steps_per_second": 2.859,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3166204172697600.0,
+  "total_flos": 6332408345395200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null