Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:335dc6861df4850c8fba66b3d30ecdcdf772951b06b589f54bc335fcd88ad8e9
+oid sha256:9780cd9fd17d34b215bd36bd9703f810abbb1444351ee0c8888d1123900b1d2d
 size 25271744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e18a6f21200c97f7f669743318dacbcadcf07863af1f258101614f7b351f518
+oid sha256:c17a76ee31c5f7653f58e7216514baafb46d1007dfa727a27d3ceece4a96745a
 size 13685516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea30508b2168921b3e75386a046978772f5cbc66bbd566c5d99dd61ea40c26f1
+oid sha256:4cf355fd48ca7fbf33eb7fc35115a0613a7bff5e1759da5fa0cb1ec53729b7e7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.558466911315918,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.008592910848549946,
+  "best_metric": 1.4640228748321533,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.017185821697099892,
   "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": 10.532,
       "eval_steps_per_second": 5.266,
       "step": 10
+    },
+    {
+      "epoch": 0.00945220193340494,
+      "grad_norm": 0.17917290329933167,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 1.5504,
+      "step": 11
+    },
+    {
+      "epoch": 0.010311493018259935,
+      "grad_norm": 0.1752149611711502,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 1.5564,
+      "step": 12
+    },
+    {
+      "epoch": 0.01117078410311493,
+      "grad_norm": 0.18790920078754425,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 1.578,
+      "step": 13
+    },
+    {
+      "epoch": 0.012030075187969926,
+      "grad_norm": 0.17092998325824738,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 1.3762,
+      "step": 14
+    },
+    {
+      "epoch": 0.01288936627282492,
+      "grad_norm": 0.17537423968315125,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 1.5093,
+      "step": 15
+    },
+    {
+      "epoch": 0.01288936627282492,
+      "eval_loss": 1.4965424537658691,
+      "eval_runtime": 44.9338,
+      "eval_samples_per_second": 10.905,
+      "eval_steps_per_second": 5.452,
+      "step": 15
+    },
+    {
+      "epoch": 0.013748657357679914,
+      "grad_norm": 0.16586551070213318,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.4224,
+      "step": 16
+    },
+    {
+      "epoch": 0.014607948442534909,
+      "grad_norm": 0.18348799645900726,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 1.6179,
+      "step": 17
+    },
+    {
+      "epoch": 0.015467239527389903,
+      "grad_norm": 0.19045992195606232,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 1.459,
+      "step": 18
+    },
+    {
+      "epoch": 0.0163265306122449,
+      "grad_norm": 0.19004923105239868,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 1.4926,
+      "step": 19
+    },
+    {
+      "epoch": 0.017185821697099892,
+      "grad_norm": 0.205982506275177,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 1.4912,
+      "step": 20
+    },
+    {
+      "epoch": 0.017185821697099892,
+      "eval_loss": 1.4640228748321533,
+      "eval_runtime": 44.5134,
+      "eval_samples_per_second": 11.008,
+      "eval_steps_per_second": 5.504,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 511583956500480.0,
+  "total_flos": 1023167913000960.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null