Training in progress, step 1500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28ee51930983bd5783773a2667d05243c7bf04209d2af78ec03cb00c4518ab18
+oid sha256:8375b215361fcd084be6cb51f159ff41f69e660f7482fadac03c670e43bd6a62
 size 17425352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:339a2885a27a78c8922945c6793e30d8c73a3d30920de4771d5d81652f078020
+oid sha256:c014e6efa0fddde31c3d035dc3ae148865deaf617d38ec91a6f7c15099b32fe3
 size 10252116

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e4c69cf57d25409b07a793754179ed99c623c866f3c475e6cf4023b90af9758
+oid sha256:0b87e05ea1a538a9d6373d03def254fde5a1793a5117b3a1e8f187407516a5b5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df814464c49d6114ced0cb2649f86ff3e3c60dbf90905c8abb1f6369d1225fb1
+oid sha256:e7592e941fa77449d9f7015724b6a3901e596c11e155596880b96def1f284283
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.7133162021636963,
-  "best_model_checkpoint": "miner_id_24/checkpoint-1200",
-  "epoch": 0.4083368779242875,
+  "best_metric": 1.7095513343811035,
+  "best_model_checkpoint": "miner_id_24/checkpoint-1500",
+  "epoch": 0.5104210974053595,
   "eval_steps": 300,
-  "global_step": 1200,
+  "global_step": 1500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -887,6 +887,224 @@
       "eval_samples_per_second": 37.197,
       "eval_steps_per_second": 18.599,
       "step": 1200
+    },
+    {
+      "epoch": 0.4117396852403233,
+      "grad_norm": 0.2934724688529968,
+      "learning_rate": 4.7745751406263165e-06,
+      "loss": 1.6398,
+      "step": 1210
+    },
+    {
+      "epoch": 0.415142492556359,
+      "grad_norm": 0.28240928053855896,
+      "learning_rate": 4.460970818476718e-06,
+      "loss": 1.3729,
+      "step": 1220
+    },
+    {
+      "epoch": 0.41854529987239475,
+      "grad_norm": 0.3319728374481201,
+      "learning_rate": 4.15700759802175e-06,
+      "loss": 1.3721,
+      "step": 1230
+    },
+    {
+      "epoch": 0.42194810718843045,
+      "grad_norm": 0.33748745918273926,
+      "learning_rate": 3.862828160801707e-06,
+      "loss": 2.11,
+      "step": 1240
+    },
+    {
+      "epoch": 0.42535091450446616,
+      "grad_norm": 0.6705477833747864,
+      "learning_rate": 3.578570595810274e-06,
+      "loss": 2.0526,
+      "step": 1250
+    },
+    {
+      "epoch": 0.4287537218205019,
+      "grad_norm": 0.2961376905441284,
+      "learning_rate": 3.3043683346749647e-06,
+      "loss": 1.6024,
+      "step": 1260
+    },
+    {
+      "epoch": 0.4321565291365376,
+      "grad_norm": 0.31039202213287354,
+      "learning_rate": 3.040350089023844e-06,
+      "loss": 1.395,
+      "step": 1270
+    },
+    {
+      "epoch": 0.4355593364525734,
+      "grad_norm": 0.35287657380104065,
+      "learning_rate": 2.786639790067719e-06,
+      "loss": 1.4204,
+      "step": 1280
+    },
+    {
+      "epoch": 0.4389621437686091,
+      "grad_norm": 0.3106899857521057,
+      "learning_rate": 2.543356530426394e-06,
+      "loss": 2.0329,
+      "step": 1290
+    },
+    {
+      "epoch": 0.44236495108464485,
+      "grad_norm": 0.7246268391609192,
+      "learning_rate": 2.310614508226078e-06,
+      "loss": 2.1024,
+      "step": 1300
+    },
+    {
+      "epoch": 0.44576775840068056,
+      "grad_norm": 0.2955819070339203,
+      "learning_rate": 2.0885229734943502e-06,
+      "loss": 1.6619,
+      "step": 1310
+    },
+    {
+      "epoch": 0.44917056571671626,
+      "grad_norm": 0.29394975304603577,
+      "learning_rate": 1.8771861768777792e-06,
+      "loss": 1.4059,
+      "step": 1320
+    },
+    {
+      "epoch": 0.452573373032752,
+      "grad_norm": 0.3255048394203186,
+      "learning_rate": 1.67670332070623e-06,
+      "loss": 1.4292,
+      "step": 1330
+    },
+    {
+      "epoch": 0.45597618034878773,
+      "grad_norm": 0.3254324197769165,
+      "learning_rate": 1.4871685124269008e-06,
+      "loss": 2.1335,
+      "step": 1340
+    },
+    {
+      "epoch": 0.4593789876648235,
+      "grad_norm": 0.6185155510902405,
+      "learning_rate": 1.3086707204299414e-06,
+      "loss": 2.1161,
+      "step": 1350
+    },
+    {
+      "epoch": 0.4627817949808592,
+      "grad_norm": 0.29304781556129456,
+      "learning_rate": 1.141293732286297e-06,
+      "loss": 1.6244,
+      "step": 1360
+    },
+    {
+      "epoch": 0.46618460229689496,
+      "grad_norm": 0.28472885489463806,
+      "learning_rate": 9.851161154175337e-07,
+      "loss": 1.3787,
+      "step": 1370
+    },
+    {
+      "epoch": 0.46958740961293066,
+      "grad_norm": 0.33770933747291565,
+      "learning_rate": 8.402111802159412e-07,
+      "loss": 1.4082,
+      "step": 1380
+    },
+    {
+      "epoch": 0.4729902169289664,
+      "grad_norm": 0.3725377023220062,
+      "learning_rate": 7.06646945632361e-07,
+      "loss": 2.076,
+      "step": 1390
+    },
+    {
+      "epoch": 0.47639302424500213,
+      "grad_norm": 0.6141946911811829,
+      "learning_rate": 5.844861072478336e-07,
+      "loss": 2.0871,
+      "step": 1400
+    },
+    {
+      "epoch": 0.47979583156103783,
+      "grad_norm": 0.2772093713283539,
+      "learning_rate": 4.7378600784402093e-07,
+      "loss": 1.6158,
+      "step": 1410
+    },
+    {
+      "epoch": 0.4831986388770736,
+      "grad_norm": 0.2923103868961334,
+      "learning_rate": 3.745986104862903e-07,
+      "loss": 1.4024,
+      "step": 1420
+    },
+    {
+      "epoch": 0.4866014461931093,
+      "grad_norm": 0.33724531531333923,
+      "learning_rate": 2.869704741320478e-07,
+      "loss": 1.417,
+      "step": 1430
+    },
+    {
+      "epoch": 0.49000425350914506,
+      "grad_norm": 0.3163939118385315,
+      "learning_rate": 2.1094273177576507e-07,
+      "loss": 2.1322,
+      "step": 1440
+    },
+    {
+      "epoch": 0.49340706082518077,
+      "grad_norm": 0.6630510091781616,
+      "learning_rate": 1.4655107114101007e-07,
+      "loss": 2.0956,
+      "step": 1450
+    },
+    {
+      "epoch": 0.4968098681412165,
+      "grad_norm": 0.29451075196266174,
+      "learning_rate": 9.382571792846961e-08,
+      "loss": 1.6392,
+      "step": 1460
+    },
+    {
+      "epoch": 0.5002126754572522,
+      "grad_norm": 0.29572850465774536,
+      "learning_rate": 5.279142162789019e-08,
+      "loss": 1.4153,
+      "step": 1470
+    },
+    {
+      "epoch": 0.5036154827732879,
+      "grad_norm": 0.3492263853549957,
+      "learning_rate": 2.3467443900582198e-08,
+      "loss": 1.3996,
+      "step": 1480
+    },
+    {
+      "epoch": 0.5070182900893236,
+      "grad_norm": 0.3328089714050293,
+      "learning_rate": 5.86754953789681e-09,
+      "loss": 2.0623,
+      "step": 1490
+    },
+    {
+      "epoch": 0.5104210974053595,
+      "grad_norm": 0.6787052750587463,
+      "learning_rate": 0.0,
+      "loss": 2.1523,
+      "step": 1500
+    },
+    {
+      "epoch": 0.5104210974053595,
+      "eval_loss": 1.7095513343811035,
+      "eval_runtime": 132.0071,
+      "eval_samples_per_second": 37.498,
+      "eval_steps_per_second": 18.749,
+      "step": 1500
     }
   ],
   "logging_steps": 10,
@@ -910,12 +1128,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 6.594316339249152e+16,
+  "total_flos": 8.239759752953856e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null