Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ef7aedffa6b970af8076785063cbd56e4dc0d99619bd418d6deae81177b4fbe
+oid sha256:06c648081afaca89099ab6c10a98fe44a25f80bcc397cccc8a646c05190e470e
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3ac01d76eefe5950d73995158162a10ceafb8d7a1956bb9618db36e1a0d3fc2
+oid sha256:12a3e4416722618f2af9f18f3f032e737a82dea14d4933bb52c07eb4018432c6
 size 118090

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90b71bb277c02108176003616795af009f8695adf01aace96027ba87d500d684
+oid sha256:3e00fcd12909c2322718ef9b746a7e3f5c235d33a48d461c2629c6b0fbe2d5f9
 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": 10.374467849731445,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.042105263157894736,
+  "best_metric": 10.373170852661133,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.08421052631578947,
   "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": 99.861,
       "eval_steps_per_second": 49.93,
       "step": 25
+    },
+    {
+      "epoch": 0.043789473684210524,
+      "grad_norm": 0.06261739879846573,
+      "learning_rate": 0.0001,
+      "loss": 10.3714,
+      "step": 26
+    },
+    {
+      "epoch": 0.04547368421052632,
+      "grad_norm": 0.05161561071872711,
+      "learning_rate": 9.345968707698569e-05,
+      "loss": 10.3704,
+      "step": 27
+    },
+    {
+      "epoch": 0.04715789473684211,
+      "grad_norm": 0.0623190775513649,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 10.3713,
+      "step": 28
+    },
+    {
+      "epoch": 0.048842105263157895,
+      "grad_norm": 0.04920860007405281,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 10.3743,
+      "step": 29
+    },
+    {
+      "epoch": 0.05052631578947368,
+      "grad_norm": 0.0820833221077919,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 10.3766,
+      "step": 30
+    },
+    {
+      "epoch": 0.05221052631578947,
+      "grad_norm": 0.0759882777929306,
+      "learning_rate": 6.785605346968386e-05,
+      "loss": 10.3706,
+      "step": 31
+    },
+    {
+      "epoch": 0.053894736842105266,
+      "grad_norm": 0.09138514846563339,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 10.3766,
+      "step": 32
+    },
+    {
+      "epoch": 0.055578947368421054,
+      "grad_norm": 0.06546122580766678,
+      "learning_rate": 5.577113097809989e-05,
+      "loss": 10.3789,
+      "step": 33
+    },
+    {
+      "epoch": 0.05726315789473684,
+      "grad_norm": 0.07500308752059937,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 10.3635,
+      "step": 34
+    },
+    {
+      "epoch": 0.05894736842105263,
+      "grad_norm": 0.07415971904993057,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 10.3744,
+      "step": 35
+    },
+    {
+      "epoch": 0.06063157894736842,
+      "grad_norm": 0.0628037378191948,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 10.3741,
+      "step": 36
+    },
+    {
+      "epoch": 0.06231578947368421,
+      "grad_norm": 0.07070739567279816,
+      "learning_rate": 3.406541848999312e-05,
+      "loss": 10.3683,
+      "step": 37
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 0.07649371773004532,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 10.3733,
+      "step": 38
+    },
+    {
+      "epoch": 0.06568421052631579,
+      "grad_norm": 0.09366203844547272,
+      "learning_rate": 2.4816019252102273e-05,
+      "loss": 10.3807,
+      "step": 39
+    },
+    {
+      "epoch": 0.06736842105263158,
+      "grad_norm": 0.08414056897163391,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 10.3586,
+      "step": 40
+    },
+    {
+      "epoch": 0.06905263157894737,
+      "grad_norm": 0.09400244802236557,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 10.3526,
+      "step": 41
+    },
+    {
+      "epoch": 0.07073684210526315,
+      "grad_norm": 0.07930176705121994,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 10.3771,
+      "step": 42
+    },
+    {
+      "epoch": 0.07242105263157894,
+      "grad_norm": 0.08477415144443512,
+      "learning_rate": 1.0312725846731175e-05,
+      "loss": 10.3674,
+      "step": 43
+    },
+    {
+      "epoch": 0.07410526315789474,
+      "grad_norm": 0.09532937407493591,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 10.364,
+      "step": 44
+    },
+    {
+      "epoch": 0.07578947368421053,
+      "grad_norm": 0.12698949873447418,
+      "learning_rate": 5.306987050489442e-06,
+      "loss": 10.3493,
+      "step": 45
+    },
+    {
+      "epoch": 0.07747368421052632,
+      "grad_norm": 0.09168936312198639,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 10.3725,
+      "step": 46
+    },
+    {
+      "epoch": 0.07915789473684211,
+      "grad_norm": 0.10333892703056335,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 10.3572,
+      "step": 47
+    },
+    {
+      "epoch": 0.0808421052631579,
+      "grad_norm": 0.15725451707839966,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 10.3644,
+      "step": 48
+    },
+    {
+      "epoch": 0.08252631578947368,
+      "grad_norm": 0.158616304397583,
+      "learning_rate": 2.141076761396521e-07,
+      "loss": 10.3458,
+      "step": 49
+    },
+    {
+      "epoch": 0.08421052631578947,
+      "grad_norm": 0.16719745099544525,
+      "learning_rate": 0.0,
+      "loss": 10.3634,
+      "step": 50
+    },
+    {
+      "epoch": 0.08421052631578947,
+      "eval_loss": 10.373170852661133,
+      "eval_runtime": 2.7738,
+      "eval_samples_per_second": 90.128,
+      "eval_steps_per_second": 45.064,
+      "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": 2615122329600.0,
+  "total_flos": 5230244659200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null