Training in progress, step 60, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e28a0969e0d12e5c82f2f9386cc5bfa4aadffff4210ed049daa68d9f0f9b6eb9
+oid sha256:7627bee5f59d424331a7a8c8fa59f2519833f6c9a0b76bf47db086e2d057ba3e
 size 70430032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a840335b9b9afe60a3604be7778ac7251bed11b91667e56629bded1cb7947850
+oid sha256:a277a9128921e08f49f245502ecfafe5e811a6fdcec51f4c80f5c64f8c88065c
 size 36135892

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e01dfd723622e9677c7b52a2436bae7b33f9b2cab0de4c18546921773d165195
+oid sha256:f8276354487b9292066c9bf7fb070ef98904061db81bdcaf8141dd5e722f15d1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:504bbfdc996899ae0fed191469707d16864e324e1af3e19030b955ead524b577
+oid sha256:1d842ae89b9008565268495397aa2a41cfc409fd6aefac567cbdd9ac926ecf81
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.213444709777832,
-  "best_model_checkpoint": "miner_id_24/checkpoint-40",
-  "epoch": 0.016925843647519305,
+  "best_metric": 2.1694796085357666,
+  "best_model_checkpoint": "miner_id_24/checkpoint-60",
+  "epoch": 0.025388765471278957,
   "eval_steps": 20,
-  "global_step": 40,
+  "global_step": 60,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -311,6 +311,154 @@
       "eval_samples_per_second": 26.138,
       "eval_steps_per_second": 6.541,
       "step": 40
+    },
+    {
+      "epoch": 0.01734898973870729,
+      "grad_norm": 1.311227798461914,
+      "learning_rate": 0.00011785568947986367,
+      "loss": 2.2835,
+      "step": 41
+    },
+    {
+      "epoch": 0.017772135829895272,
+      "grad_norm": 5.271040916442871,
+      "learning_rate": 0.00011342332658176555,
+      "loss": 2.3215,
+      "step": 42
+    },
+    {
+      "epoch": 0.018195281921083255,
+      "grad_norm": 1.3460105657577515,
+      "learning_rate": 0.00010896393089034336,
+      "loss": 2.1808,
+      "step": 43
+    },
+    {
+      "epoch": 0.018618428012271235,
+      "grad_norm": 1.4446858167648315,
+      "learning_rate": 0.00010448648303505151,
+      "loss": 2.2533,
+      "step": 44
+    },
+    {
+      "epoch": 0.01904157410345922,
+      "grad_norm": 1.5081716775894165,
+      "learning_rate": 0.0001,
+      "loss": 2.1724,
+      "step": 45
+    },
+    {
+      "epoch": 0.019464720194647202,
+      "grad_norm": 1.2462027072906494,
+      "learning_rate": 9.551351696494854e-05,
+      "loss": 2.1896,
+      "step": 46
+    },
+    {
+      "epoch": 0.019887866285835186,
+      "grad_norm": 1.4999518394470215,
+      "learning_rate": 9.103606910965666e-05,
+      "loss": 2.3309,
+      "step": 47
+    },
+    {
+      "epoch": 0.020311012377023166,
+      "grad_norm": 1.250173807144165,
+      "learning_rate": 8.657667341823448e-05,
+      "loss": 2.1242,
+      "step": 48
+    },
+    {
+      "epoch": 0.02073415846821115,
+      "grad_norm": 5.076053142547607,
+      "learning_rate": 8.214431052013634e-05,
+      "loss": 2.3353,
+      "step": 49
+    },
+    {
+      "epoch": 0.021157304559399133,
+      "grad_norm": 1.4977030754089355,
+      "learning_rate": 7.774790660436858e-05,
+      "loss": 2.3957,
+      "step": 50
+    },
+    {
+      "epoch": 0.021580450650587116,
+      "grad_norm": 1.3641694784164429,
+      "learning_rate": 7.339631544333249e-05,
+      "loss": 2.1407,
+      "step": 51
+    },
+    {
+      "epoch": 0.022003596741775096,
+      "grad_norm": 1.596494197845459,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 2.1233,
+      "step": 52
+    },
+    {
+      "epoch": 0.02242674283296308,
+      "grad_norm": 1.3014681339263916,
+      "learning_rate": 6.486251759186572e-05,
+      "loss": 2.0812,
+      "step": 53
+    },
+    {
+      "epoch": 0.022849888924151063,
+      "grad_norm": 1.2006770372390747,
+      "learning_rate": 6.069749683460765e-05,
+      "loss": 2.171,
+      "step": 54
+    },
+    {
+      "epoch": 0.023273035015339047,
+      "grad_norm": 1.1349421739578247,
+      "learning_rate": 5.6611626088244194e-05,
+      "loss": 2.0624,
+      "step": 55
+    },
+    {
+      "epoch": 0.023696181106527027,
+      "grad_norm": 1.238204002380371,
+      "learning_rate": 5.261313375270014e-05,
+      "loss": 2.2335,
+      "step": 56
+    },
+    {
+      "epoch": 0.02411932719771501,
+      "grad_norm": 1.2505645751953125,
+      "learning_rate": 4.87100722594094e-05,
+      "loss": 2.2071,
+      "step": 57
+    },
+    {
+      "epoch": 0.024542473288902994,
+      "grad_norm": 1.2006800174713135,
+      "learning_rate": 4.491030185478976e-05,
+      "loss": 2.0714,
+      "step": 58
+    },
+    {
+      "epoch": 0.024965619380090977,
+      "grad_norm": 1.3659069538116455,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 2.1511,
+      "step": 59
+    },
+    {
+      "epoch": 0.025388765471278957,
+      "grad_norm": 1.116264820098877,
+      "learning_rate": 3.7651019814126654e-05,
+      "loss": 2.1554,
+      "step": 60
+    },
+    {
+      "epoch": 0.025388765471278957,
+      "eval_loss": 2.1694796085357666,
+      "eval_runtime": 71.9131,
+      "eval_samples_per_second": 27.672,
+      "eval_steps_per_second": 6.925,
+      "step": 60
     }
   ],
   "logging_steps": 1,
@@ -339,7 +487,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 738252281610240.0,
+  "total_flos": 1107378422415360.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null