Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:938309e8862c13409ec9b4a2050f987eeae531fd60baf9fcffce49f6b0dd19e6
+oid sha256:291043bd750e74876ec805c688a970cd4891d5e54c5d802601b5336d44188976
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09be9d7524e83ab6217a35a03c8c1b667a52874bf59f9004db7aa41e6fbcaa2c
+oid sha256:c6ecbb222469e768c81b8ef94a8b75c6051f82780d7c81e9c4fe3648b87c64be
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdb121aa3d29c4e174a6cf4b706999dc4c97a042e37296604b36b0e8eec663c7
+oid sha256:fbb92ceee37a3625aebc2d35b6d4627b5a6df79ff497d84d5a62fe17d38cea8d
 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": 1.4492992162704468,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.005689900426742532,
+  "best_metric": 1.3764064311981201,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.011379800853485065,
   "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": 5.855,
       "eval_steps_per_second": 2.928,
       "step": 10
+    },
+    {
+      "epoch": 0.006258890469416785,
+      "grad_norm": 2.8724112510681152,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 5.1733,
+      "step": 11
+    },
+    {
+      "epoch": 0.0068278805120910386,
+      "grad_norm": 2.897056818008423,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 4.9277,
+      "step": 12
+    },
+    {
+      "epoch": 0.007396870554765292,
+      "grad_norm": 1.9220606088638306,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 3.0438,
+      "step": 13
+    },
+    {
+      "epoch": 0.007965860597439544,
+      "grad_norm": 4.364326000213623,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 5.4731,
+      "step": 14
+    },
+    {
+      "epoch": 0.008534850640113799,
+      "grad_norm": 3.4079654216766357,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 6.2501,
+      "step": 15
+    },
+    {
+      "epoch": 0.008534850640113799,
+      "eval_loss": 1.4071946144104004,
+      "eval_runtime": 113.6558,
+      "eval_samples_per_second": 6.511,
+      "eval_steps_per_second": 3.255,
+      "step": 15
+    },
+    {
+      "epoch": 0.009103840682788052,
+      "grad_norm": 3.1693203449249268,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 5.6554,
+      "step": 16
+    },
+    {
+      "epoch": 0.009672830725462305,
+      "grad_norm": 3.4745993614196777,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 6.187,
+      "step": 17
+    },
+    {
+      "epoch": 0.010241820768136558,
+      "grad_norm": 4.106719017028809,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 7.185,
+      "step": 18
+    },
+    {
+      "epoch": 0.010810810810810811,
+      "grad_norm": 4.38962459564209,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 7.0849,
+      "step": 19
+    },
+    {
+      "epoch": 0.011379800853485065,
+      "grad_norm": 3.2297611236572266,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 7.1814,
+      "step": 20
+    },
+    {
+      "epoch": 0.011379800853485065,
+      "eval_loss": 1.3764064311981201,
+      "eval_runtime": 116.0269,
+      "eval_samples_per_second": 6.378,
+      "eval_steps_per_second": 3.189,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2076634748289024.0,
+  "total_flos": 4193987824975872.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null