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:fc80756108bc93eb4ee95671dce547cda2fa9908f545a9e2f99cf8e9c93d089c
+oid sha256:d2ba6709880916f77a34eed6d1c2c2a558cd4bb13317b0ec2bb7d324d02ae4cc
 size 12609416

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1418345a19b32d3331a1fa304d0f42b846a0d18803e065c7010a099d17d73d6
+oid sha256:a3d3a238cf1a07566a6378e9e6ffd3244d8ab8824f039c2f0fd952c1f6c92a49
 size 6615034

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c9a75f108334a418a7a60fec99e44fa186e26e0cb2561fc9cb4a7566e3c595c
+oid sha256:c8195f5f8ab0a2152863fee8331a14f0c6fd922ebfbe0783423b8278beeaadd3
 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": 3.248414993286133,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.00019502586530538614,
+  "best_metric": 2.7909083366394043,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0003900517306107723,
   "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": 11.916,
       "eval_steps_per_second": 5.958,
       "step": 10
+    },
+    {
+      "epoch": 0.00021452845183592473,
+      "grad_norm": 11.077315330505371,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 14.4034,
+      "step": 11
+    },
+    {
+      "epoch": 0.00023403103836646335,
+      "grad_norm": 12.010499954223633,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 12.714,
+      "step": 12
+    },
+    {
+      "epoch": 0.00025353362489700194,
+      "grad_norm": 9.952736854553223,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 13.5068,
+      "step": 13
+    },
+    {
+      "epoch": 0.00027303621142754056,
+      "grad_norm": 10.11349105834961,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 12.3709,
+      "step": 14
+    },
+    {
+      "epoch": 0.0002925387979580792,
+      "grad_norm": 10.342610359191895,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 9.9486,
+      "step": 15
+    },
+    {
+      "epoch": 0.0002925387979580792,
+      "eval_loss": 2.8909246921539307,
+      "eval_runtime": 1803.0764,
+      "eval_samples_per_second": 11.974,
+      "eval_steps_per_second": 5.987,
+      "step": 15
+    },
+    {
+      "epoch": 0.0003120413844886178,
+      "grad_norm": 11.209519386291504,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 11.7412,
+      "step": 16
+    },
+    {
+      "epoch": 0.0003315439710191564,
+      "grad_norm": 10.916708946228027,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 11.9705,
+      "step": 17
+    },
+    {
+      "epoch": 0.00035104655754969504,
+      "grad_norm": 12.23410415649414,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 10.1354,
+      "step": 18
+    },
+    {
+      "epoch": 0.00037054914408023366,
+      "grad_norm": 14.120523452758789,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 11.6195,
+      "step": 19
+    },
+    {
+      "epoch": 0.0003900517306107723,
+      "grad_norm": 11.8251371383667,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 11.1802,
+      "step": 20
+    },
+    {
+      "epoch": 0.0003900517306107723,
+      "eval_loss": 2.7909083366394043,
+      "eval_runtime": 1794.027,
+      "eval_samples_per_second": 12.034,
+      "eval_steps_per_second": 6.017,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 75069652992000.0,
+  "total_flos": 150139305984000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null