Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03a0f7fa5bee6c507adab31457d68d01022011b726953bdba8927b9e45d83b34
+oid sha256:898bcb5b3e90a282f9f232a504ea32dafefd0832b851fa491351be6ea2c6dd2b
 size 50358592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a40d8940756824c36d5a920c20f3b0ce7835ad03b566aff026fe39c4a46ff079
+oid sha256:9cc376ff41eb85aaf1e12f3abb65baf73084d2db2c95c5d13f0e143ecad9db95
 size 100824826

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0333107f768ee5103645ae6555359c211d8dd5cf129f9e7dc55c9ed6e13022c2
+oid sha256:e74c3b12acf1da998c5b4462ee9a4c08c136d290674801eabfefd664e73009fc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ea7ff16b0c30a914eb0d145e3fb06ff9027c6cd2408e766ce8a09accab89a4d
+oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.4314424991607666,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.07598784194528875,
+  "best_metric": 1.5591756105422974,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.1519756838905775,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 2.082,
       "eval_steps_per_second": 1.048,
       "step": 25
+    },
+    {
+      "epoch": 0.0790273556231003,
+      "grad_norm": 31.762439727783203,
+      "learning_rate": 0.0001,
+      "loss": 7.3931,
+      "step": 26
+    },
+    {
+      "epoch": 0.08206686930091185,
+      "grad_norm": 46.987701416015625,
+      "learning_rate": 9.345968707698569e-05,
+      "loss": 11.0254,
+      "step": 27
+    },
+    {
+      "epoch": 0.0851063829787234,
+      "grad_norm": 39.347415924072266,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 9.7276,
+      "step": 28
+    },
+    {
+      "epoch": 0.08814589665653495,
+      "grad_norm": 27.018573760986328,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 6.8205,
+      "step": 29
+    },
+    {
+      "epoch": 0.0911854103343465,
+      "grad_norm": 38.160160064697266,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 8.0631,
+      "step": 30
+    },
+    {
+      "epoch": 0.09422492401215805,
+      "grad_norm": 20.63794708251953,
+      "learning_rate": 6.785605346968386e-05,
+      "loss": 5.7677,
+      "step": 31
+    },
+    {
+      "epoch": 0.0972644376899696,
+      "grad_norm": 26.39188003540039,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 7.9546,
+      "step": 32
+    },
+    {
+      "epoch": 0.10030395136778116,
+      "grad_norm": 32.68507385253906,
+      "learning_rate": 5.577113097809989e-05,
+      "loss": 5.3357,
+      "step": 33
+    },
+    {
+      "epoch": 0.1033434650455927,
+      "grad_norm": 23.021486282348633,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 4.2771,
+      "step": 34
+    },
+    {
+      "epoch": 0.10638297872340426,
+      "grad_norm": 38.087120056152344,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 7.5119,
+      "step": 35
+    },
+    {
+      "epoch": 0.1094224924012158,
+      "grad_norm": 35.39018249511719,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 8.1111,
+      "step": 36
+    },
+    {
+      "epoch": 0.11246200607902736,
+      "grad_norm": 68.58114624023438,
+      "learning_rate": 3.406541848999312e-05,
+      "loss": 10.3492,
+      "step": 37
+    },
+    {
+      "epoch": 0.11550151975683891,
+      "grad_norm": 35.49908447265625,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 5.9193,
+      "step": 38
+    },
+    {
+      "epoch": 0.11854103343465046,
+      "grad_norm": 49.49984359741211,
+      "learning_rate": 2.4816019252102273e-05,
+      "loss": 6.7471,
+      "step": 39
+    },
+    {
+      "epoch": 0.12158054711246201,
+      "grad_norm": 25.06878089904785,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 3.6904,
+      "step": 40
+    },
+    {
+      "epoch": 0.12462006079027356,
+      "grad_norm": 52.52233123779297,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 6.2508,
+      "step": 41
+    },
+    {
+      "epoch": 0.1276595744680851,
+      "grad_norm": 40.56067657470703,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 5.418,
+      "step": 42
+    },
+    {
+      "epoch": 0.13069908814589665,
+      "grad_norm": 48.30466079711914,
+      "learning_rate": 1.0312725846731175e-05,
+      "loss": 6.1278,
+      "step": 43
+    },
+    {
+      "epoch": 0.1337386018237082,
+      "grad_norm": 100.85240936279297,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 8.8476,
+      "step": 44
+    },
+    {
+      "epoch": 0.13677811550151975,
+      "grad_norm": 44.3907585144043,
+      "learning_rate": 5.306987050489442e-06,
+      "loss": 6.1738,
+      "step": 45
+    },
+    {
+      "epoch": 0.1398176291793313,
+      "grad_norm": 58.735931396484375,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 10.7501,
+      "step": 46
+    },
+    {
+      "epoch": 0.14285714285714285,
+      "grad_norm": 71.46258544921875,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 10.3434,
+      "step": 47
+    },
+    {
+      "epoch": 0.1458966565349544,
+      "grad_norm": 102.83684539794922,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 10.9469,
+      "step": 48
+    },
+    {
+      "epoch": 0.14893617021276595,
+      "grad_norm": 55.492740631103516,
+      "learning_rate": 2.141076761396521e-07,
+      "loss": 10.7603,
+      "step": 49
+    },
+    {
+      "epoch": 0.1519756838905775,
+      "grad_norm": 73.8077163696289,
+      "learning_rate": 0.0,
+      "loss": 12.376,
+      "step": 50
+    },
+    {
+      "epoch": 0.1519756838905775,
+      "eval_loss": 1.5591756105422974,
+      "eval_runtime": 66.7749,
+      "eval_samples_per_second": 2.082,
+      "eval_steps_per_second": 1.048,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 6002371146547200.0,
+  "total_flos": 1.20047422930944e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null