Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cdf14adeceef0fbd05b21f9a0ef2e534ef38247a87d4e45b391749e8c24c669
+oid sha256:c88f25389b1fbd16f93b3287458bd928b4c15de1e4a4f3b7143e593bde59946e
 size 186962

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3b152165a63d4868526b12b251f5243c7e07f14b1bfe3a0b5f8fca8b4297e26
+oid sha256:379a1c120a1e3ed0a6096d4faf83351c944eaa440a72d2a8eb7518458a1ffe77
 size 121430

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cd406dcc1a69f352bf665054745e7b0e58cf1a05b11c53f3d235980b0212ea3
+oid sha256:0ab882bcabe1955d5e2c70b93bcf54988baa043b4bf0556e48727fd08f9d5c0c
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf354fc1278381f18e626930186c06ebc4a0c7f2b402864a5e2123bb5e07df19
+oid sha256:ce74a2a8655842d90e35653184eea205eb930504f5bc3e03521770631ff3446c
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8003ab1179cb0862f43f337f894a13fa4a042517cf9ca22aaca0ef2a34dbf1ea
+oid sha256:3d0f65644b7d543768f977b872ec0511ce9d1fdc459411fae3732f6b5d800166
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82b0cf7205a13aa26934925e69331ac92c27447d93ac004d203c25663f0e058f
+oid sha256:c1956fa9103b2437e516f855867abbfcd74a664d9372e746715c10658080e5ad
 size 15024

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": 6.917991638183594,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.011291779584462511,
+  "best_metric": 6.910342693328857,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.022583559168925023,
   "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": 911.681,
       "eval_steps_per_second": 114.174,
       "step": 25
+    },
+    {
+      "epoch": 0.011743450767841012,
+      "grad_norm": 0.12024138867855072,
+      "learning_rate": 0.0001,
+      "loss": 6.9329,
+      "step": 26
+    },
+    {
+      "epoch": 0.012195121951219513,
+      "grad_norm": 0.12785819172859192,
+      "learning_rate": 9.345968707698569e-05,
+      "loss": 6.9298,
+      "step": 27
+    },
+    {
+      "epoch": 0.012646793134598013,
+      "grad_norm": 0.14583264291286469,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 6.9229,
+      "step": 28
+    },
+    {
+      "epoch": 0.013098464317976514,
+      "grad_norm": 0.17286351323127747,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 6.9189,
+      "step": 29
+    },
+    {
+      "epoch": 0.013550135501355014,
+      "grad_norm": 0.18918299674987793,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 6.9196,
+      "step": 30
+    },
+    {
+      "epoch": 0.014001806684733513,
+      "grad_norm": 0.19743739068508148,
+      "learning_rate": 6.785605346968386e-05,
+      "loss": 6.9115,
+      "step": 31
+    },
+    {
+      "epoch": 0.014453477868112014,
+      "grad_norm": 0.20110255479812622,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 6.9122,
+      "step": 32
+    },
+    {
+      "epoch": 0.014905149051490514,
+      "grad_norm": 0.19309815764427185,
+      "learning_rate": 5.577113097809989e-05,
+      "loss": 6.9141,
+      "step": 33
+    },
+    {
+      "epoch": 0.015356820234869015,
+      "grad_norm": 0.2259165495634079,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 6.9052,
+      "step": 34
+    },
+    {
+      "epoch": 0.015808491418247517,
+      "grad_norm": 0.2182929962873459,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 6.9042,
+      "step": 35
+    },
+    {
+      "epoch": 0.016260162601626018,
+      "grad_norm": 0.23973923921585083,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 6.9081,
+      "step": 36
+    },
+    {
+      "epoch": 0.016711833785004515,
+      "grad_norm": 0.21056023240089417,
+      "learning_rate": 3.406541848999312e-05,
+      "loss": 6.9138,
+      "step": 37
+    },
+    {
+      "epoch": 0.017163504968383016,
+      "grad_norm": 0.14639106392860413,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 6.9281,
+      "step": 38
+    },
+    {
+      "epoch": 0.017615176151761516,
+      "grad_norm": 0.12287917733192444,
+      "learning_rate": 2.4816019252102273e-05,
+      "loss": 6.9262,
+      "step": 39
+    },
+    {
+      "epoch": 0.018066847335140017,
+      "grad_norm": 0.1542358100414276,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 6.9188,
+      "step": 40
+    },
+    {
+      "epoch": 0.018518518518518517,
+      "grad_norm": 0.18276679515838623,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 6.915,
+      "step": 41
+    },
+    {
+      "epoch": 0.018970189701897018,
+      "grad_norm": 0.19573663175106049,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 6.9107,
+      "step": 42
+    },
+    {
+      "epoch": 0.01942186088527552,
+      "grad_norm": 0.1964210867881775,
+      "learning_rate": 1.0312725846731175e-05,
+      "loss": 6.9139,
+      "step": 43
+    },
+    {
+      "epoch": 0.01987353206865402,
+      "grad_norm": 0.21382571756839752,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 6.9072,
+      "step": 44
+    },
+    {
+      "epoch": 0.02032520325203252,
+      "grad_norm": 0.21687394380569458,
+      "learning_rate": 5.306987050489442e-06,
+      "loss": 6.9014,
+      "step": 45
+    },
+    {
+      "epoch": 0.02077687443541102,
+      "grad_norm": 0.2191643863916397,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 6.9125,
+      "step": 46
+    },
+    {
+      "epoch": 0.02122854561878952,
+      "grad_norm": 0.21285398304462433,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 6.9083,
+      "step": 47
+    },
+    {
+      "epoch": 0.02168021680216802,
+      "grad_norm": 0.20628215372562408,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 6.9121,
+      "step": 48
+    },
+    {
+      "epoch": 0.022131887985546522,
+      "grad_norm": 0.21727484464645386,
+      "learning_rate": 2.141076761396521e-07,
+      "loss": 6.9097,
+      "step": 49
+    },
+    {
+      "epoch": 0.022583559168925023,
+      "grad_norm": 0.2488403469324112,
+      "learning_rate": 0.0,
+      "loss": 6.9046,
+      "step": 50
+    },
+    {
+      "epoch": 0.022583559168925023,
+      "eval_loss": 6.910342693328857,
+      "eval_runtime": 4.1189,
+      "eval_samples_per_second": 905.333,
+      "eval_steps_per_second": 113.379,
+      "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": 1181552492544.0,
+  "total_flos": 2360158470144.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null