Training in progress, step 720, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcd16a4c3efa89917df326405ecfe0efcf8f6c874917919a42fb2cba5ea9e5d7
+oid sha256:e030ed8e4bab74ae0756f9785c1052e4d7f2dca2d17c8f70ae32ca64cc95e3f6
 size 109009752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f028ce1134de3dfa617e8de596ee2c14769c4de538242abe1720bca892dedd83
+oid sha256:9d54f0be12773f49f1ed5bad80963b7faa9c5309fc7694acdb28050711891693
 size 56088788

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b250a2d04e3b7e4ef325f1e6fbf465a54671732991d72fcdb0e05b3d7235a51
+oid sha256:18c6f9ff482fa2a35bf4d9816a8121899fc9a74219c376abafabd02392dad42b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:280ee2cc37f59aee556afc8e2e917a0f6ae2ddebaa406909481cc701e5697e8a
+oid sha256:fa211036836c6e38255f6b77eef8f38a88688a8d10961949bdf9bdd5ecea416f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.556154470312322e-07,
-  "best_model_checkpoint": "miner_id_24/checkpoint-680",
-  "epoch": 4.57912457912458,
+  "best_metric": 2.54923321563183e-07,
+  "best_model_checkpoint": "miner_id_24/checkpoint-720",
+  "epoch": 4.848484848484849,
   "eval_steps": 20,
-  "global_step": 680,
+  "global_step": 720,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -329,6 +329,29 @@
       "eval_samples_per_second": 28.617,
       "eval_steps_per_second": 0.916,
       "step": 680
+    },
+    {
+      "epoch": 4.713804713804714,
+      "grad_norm": 5.829084329889156e-06,
+      "learning_rate": 2.2109374505137555e-06,
+      "loss": 0.0,
+      "step": 700
+    },
+    {
+      "epoch": 4.713804713804714,
+      "eval_loss": 2.5736900965966925e-07,
+      "eval_runtime": 4.3762,
+      "eval_samples_per_second": 28.563,
+      "eval_steps_per_second": 0.914,
+      "step": 700
+    },
+    {
+      "epoch": 4.848484848484849,
+      "eval_loss": 2.54923321563183e-07,
+      "eval_runtime": 4.3625,
+      "eval_samples_per_second": 28.653,
+      "eval_steps_per_second": 0.917,
+      "step": 720
     }
   ],
   "logging_steps": 100,
@@ -357,7 +380,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.8715123912736768e+17,
+  "total_flos": 3.040487007898829e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null