Training in progress, step 600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ac448701a045ff439e79b5ff67b3c1c9e27e9a40781e5b7a14904ca15551334
+oid sha256:203e08f046df4d334ef6c8caea21c172e5ea1e2c60c119aa2792cf4ad1d6d1c9
 size 4873875032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3776ada79a70f53d0fb04f3a4270da720aa3ae008d4a93ebaab0fd32c3e3199
+oid sha256:6f1175fc470bdfc8f0d336fde4fd9d2096c6bf3f0f2ad6202f7f87dbeb67b065
 size 1408414360

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca0f47184221cac8d75c4921ac2810fa8f2a1d7ee96fb9be1067cc10fdda9dd0
+oid sha256:443c83fb7b844b8ff3708b529392bea53306a8d3cfda3e62525bc544ce49d42e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de723127fb29334c1d5f5d4d0ba1d4e78fc916dfc4e8f6b4bb5846a069a13ba9
+oid sha256:9d89303aa828aaa9e241260e2ca606db088309d8b5a7ba3d79cb10ce1887994d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 6.284088611602783,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.20957038071952497,
+  "best_metric": 6.1272969245910645,
+  "best_model_checkpoint": "miner_id_24/checkpoint-600",
+  "epoch": 0.2794271742927,
   "eval_steps": 50,
-  "global_step": 450,
+  "global_step": 600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -402,6 +402,135 @@
       "eval_samples_per_second": 9.547,
       "eval_steps_per_second": 2.389,
       "step": 450
+    },
+    {
+      "epoch": 0.21422750029106996,
+      "grad_norm": 27.015338897705078,
+      "learning_rate": 2.6522584913693294e-05,
+      "loss": 6.4693,
+      "step": 460
+    },
+    {
+      "epoch": 0.21888461986261498,
+      "grad_norm": 6.367403984069824,
+      "learning_rate": 2.301660165700936e-05,
+      "loss": 6.2205,
+      "step": 470
+    },
+    {
+      "epoch": 0.22354173943415998,
+      "grad_norm": 16.961223602294922,
+      "learning_rate": 1.9728836206903656e-05,
+      "loss": 6.2914,
+      "step": 480
+    },
+    {
+      "epoch": 0.22819885900570497,
+      "grad_norm": 7.398273468017578,
+      "learning_rate": 1.6668608091748495e-05,
+      "loss": 6.1223,
+      "step": 490
+    },
+    {
+      "epoch": 0.23285597857724996,
+      "grad_norm": 18.52619171142578,
+      "learning_rate": 1.3844591860619383e-05,
+      "loss": 6.1299,
+      "step": 500
+    },
+    {
+      "epoch": 0.23285597857724996,
+      "eval_loss": 6.169624328613281,
+      "eval_runtime": 380.4572,
+      "eval_samples_per_second": 9.507,
+      "eval_steps_per_second": 2.379,
+      "step": 500
+    },
+    {
+      "epoch": 0.23751309814879498,
+      "grad_norm": 13.293009757995605,
+      "learning_rate": 1.1264792494342857e-05,
+      "loss": 6.3948,
+      "step": 510
+    },
+    {
+      "epoch": 0.24217021772033998,
+      "grad_norm": 10.967979431152344,
+      "learning_rate": 8.936522714508678e-06,
+      "loss": 6.1936,
+      "step": 520
+    },
+    {
+      "epoch": 0.24682733729188497,
+      "grad_norm": 5.417884826660156,
+      "learning_rate": 6.866382254766157e-06,
+      "loss": 6.2124,
+      "step": 530
+    },
+    {
+      "epoch": 0.25148445686342996,
+      "grad_norm": 6.8799662590026855,
+      "learning_rate": 5.060239153161872e-06,
+      "loss": 6.0413,
+      "step": 540
+    },
+    {
+      "epoch": 0.256141576434975,
+      "grad_norm": 20.289323806762695,
+      "learning_rate": 3.5232131185484076e-06,
+      "loss": 6.0214,
+      "step": 550
+    },
+    {
+      "epoch": 0.256141576434975,
+      "eval_loss": 6.137284755706787,
+      "eval_runtime": 379.99,
+      "eval_samples_per_second": 9.519,
+      "eval_steps_per_second": 2.382,
+      "step": 550
+    },
+    {
+      "epoch": 0.26079869600651995,
+      "grad_norm": 9.264719009399414,
+      "learning_rate": 2.259661018213333e-06,
+      "loss": 6.4324,
+      "step": 560
+    },
+    {
+      "epoch": 0.26545581557806497,
+      "grad_norm": 4.1392717361450195,
+      "learning_rate": 1.2731645278655445e-06,
+      "loss": 6.2256,
+      "step": 570
+    },
+    {
+      "epoch": 0.27011293514961,
+      "grad_norm": 9.640027046203613,
+      "learning_rate": 5.665199789862907e-07,
+      "loss": 6.0853,
+      "step": 580
+    },
+    {
+      "epoch": 0.27477005472115495,
+      "grad_norm": 5.963624477386475,
+      "learning_rate": 1.4173043232380557e-07,
+      "loss": 6.1615,
+      "step": 590
+    },
+    {
+      "epoch": 0.2794271742927,
+      "grad_norm": 13.913993835449219,
+      "learning_rate": 0.0,
+      "loss": 6.0562,
+      "step": 600
+    },
+    {
+      "epoch": 0.2794271742927,
+      "eval_loss": 6.1272969245910645,
+      "eval_runtime": 380.3389,
+      "eval_samples_per_second": 9.51,
+      "eval_steps_per_second": 2.379,
+      "step": 600
     }
   ],
   "logging_steps": 10,
@@ -425,12 +554,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 8.167799352459264e+17,
+  "total_flos": 1.0911889810784256e+18,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null