Training in progress, step 600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d32384f86741ea4337d9afc0d7a078fe3aa36fed3c3d9e70edfae22310ee876
+oid sha256:e3f427ba4b1e818d24db7b9b4d4d27306f060b68299e48b15443c18382ae678d
 size 264285472

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8ac9024c1f37492f3113611c2c865be1a76f1e7941939b9cbbfc0e34ff8415f
+oid sha256:b666b3a8b61d7b820782b1d1b55d63f24c1c1bd8678d41e2c48f18f7e2bf3755
 size 134580692

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92a6ee507ed5c3db946f7f697487dc8cd80b4be1732337c640133afa68554a78
+oid sha256:ab20b00e42e594012f95a32f1dc278947bdfd0ca07fcada88f4fc2c8e3945752
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70f0f789b56065211b8c0b1a5e2a97dd0b5b08a816bbbe288fb6f9c677282af9
+oid sha256:5ad54995b081fae25638228c5d9c8f38ca277e5c5ad00bc3e49897b543f84405
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.09971451759338379,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 1.0198075834748161,
+  "best_metric": 0.09790434688329697,
+  "best_model_checkpoint": "miner_id_24/checkpoint-600",
+  "epoch": 1.3593661573288058,
   "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": 11.199,
       "eval_steps_per_second": 2.8,
       "step": 450
+    },
+    {
+      "epoch": 1.0424448217317488,
+      "grad_norm": 0.25138339400291443,
+      "learning_rate": 2.6522584913693294e-05,
+      "loss": 0.2796,
+      "step": 460
+    },
+    {
+      "epoch": 1.0650820599886814,
+      "grad_norm": 0.1467200219631195,
+      "learning_rate": 2.301660165700936e-05,
+      "loss": 0.168,
+      "step": 470
+    },
+    {
+      "epoch": 1.087719298245614,
+      "grad_norm": 0.18437053263187408,
+      "learning_rate": 1.9728836206903656e-05,
+      "loss": 0.1526,
+      "step": 480
+    },
+    {
+      "epoch": 1.1103565365025467,
+      "grad_norm": 0.00036731516593135893,
+      "learning_rate": 1.6668608091748495e-05,
+      "loss": 0.0535,
+      "step": 490
+    },
+    {
+      "epoch": 1.1329937747594794,
+      "grad_norm": 0.2067088931798935,
+      "learning_rate": 1.3844591860619383e-05,
+      "loss": 1.1511,
+      "step": 500
+    },
+    {
+      "epoch": 1.1329937747594794,
+      "eval_loss": 0.09841449558734894,
+      "eval_runtime": 66.7899,
+      "eval_samples_per_second": 11.139,
+      "eval_steps_per_second": 2.785,
+      "step": 500
+    },
+    {
+      "epoch": 1.155631013016412,
+      "grad_norm": 0.13695839047431946,
+      "learning_rate": 1.1264792494342857e-05,
+      "loss": 0.2589,
+      "step": 510
+    },
+    {
+      "epoch": 1.1782682512733447,
+      "grad_norm": 0.1652461439371109,
+      "learning_rate": 8.936522714508678e-06,
+      "loss": 0.1598,
+      "step": 520
+    },
+    {
+      "epoch": 1.2009054895302773,
+      "grad_norm": 0.12390118092298508,
+      "learning_rate": 6.866382254766157e-06,
+      "loss": 0.1742,
+      "step": 530
+    },
+    {
+      "epoch": 1.22354272778721,
+      "grad_norm": 0.00036215633735992014,
+      "learning_rate": 5.060239153161872e-06,
+      "loss": 0.0305,
+      "step": 540
+    },
+    {
+      "epoch": 1.2461799660441426,
+      "grad_norm": 0.20766952633857727,
+      "learning_rate": 3.5232131185484076e-06,
+      "loss": 1.2,
+      "step": 550
+    },
+    {
+      "epoch": 1.2461799660441426,
+      "eval_loss": 0.09686872363090515,
+      "eval_runtime": 67.296,
+      "eval_samples_per_second": 11.056,
+      "eval_steps_per_second": 2.764,
+      "step": 550
+    },
+    {
+      "epoch": 1.2688172043010753,
+      "grad_norm": 0.07413782179355621,
+      "learning_rate": 2.259661018213333e-06,
+      "loss": 0.2373,
+      "step": 560
+    },
+    {
+      "epoch": 1.291454442558008,
+      "grad_norm": 0.20543290674686432,
+      "learning_rate": 1.2731645278655445e-06,
+      "loss": 0.1418,
+      "step": 570
+    },
+    {
+      "epoch": 1.3140916808149405,
+      "grad_norm": 0.13837286829948425,
+      "learning_rate": 5.665199789862907e-07,
+      "loss": 0.1563,
+      "step": 580
+    },
+    {
+      "epoch": 1.3367289190718732,
+      "grad_norm": 0.0003274640184827149,
+      "learning_rate": 1.4173043232380557e-07,
+      "loss": 0.0364,
+      "step": 590
+    },
+    {
+      "epoch": 1.3593661573288058,
+      "grad_norm": 0.17645882070064545,
+      "learning_rate": 0.0,
+      "loss": 1.1926,
+      "step": 600
+    },
+    {
+      "epoch": 1.3593661573288058,
+      "eval_loss": 0.09790434688329697,
+      "eval_runtime": 67.234,
+      "eval_samples_per_second": 11.066,
+      "eval_steps_per_second": 2.766,
+      "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": 5.258291218951373e+17,
+  "total_flos": 7.010086580845117e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null