Training in progress, step 82, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9f7f3788ba7a72a625d9d91de7a69ba4219e4b5f6024ebe430551b76b03d251
+oid sha256:5da06306de955cddc9618c758dfb98212eabbbed03232965629ae48b98e5609f
 size 140815952

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87518e8ccc688f7a53f80028f2c633bc95d40d8d744e454e071a40e0cb370453
+oid sha256:f9086a21a3230630da4e5ca2107e22cf9fd3f258cd0f9925fd8e5c0b2a5666e6
 size 71878612

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f115dd00401ad09a019a79057eef9805cd37d1dee586fb50518d785474dca9ed
+oid sha256:07c34260a314a1151e761369646bee8d7c1d2f43246d6d1db828d43799d50770
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c22c4128b93322f91dfe46e838107695ac428a6ebd522442cb1b93f0b3af5c23
+oid sha256:2913c743d432c63154cc874349ee4f205805b2a7c45ea65b19238384071e5c70
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 2.797705888748169,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 1.834862385321101,
+  "epoch": 3.0091743119266057,
   "eval_steps": 50,
-  "global_step": 50,
+  "global_step": 82,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -373,6 +373,230 @@
       "eval_samples_per_second": 55.156,
       "eval_steps_per_second": 14.388,
       "step": 50
+    },
+    {
+      "epoch": 1.8715596330275228,
+      "grad_norm": 2.460315465927124,
+      "learning_rate": 3.917801930309486e-05,
+      "loss": 3.1729,
+      "step": 51
+    },
+    {
+      "epoch": 1.908256880733945,
+      "grad_norm": 1.8984283208847046,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.8745,
+      "step": 52
+    },
+    {
+      "epoch": 1.9449541284403669,
+      "grad_norm": 1.9956234693527222,
+      "learning_rate": 3.4964710024786354e-05,
+      "loss": 2.3038,
+      "step": 53
+    },
+    {
+      "epoch": 1.981651376146789,
+      "grad_norm": 2.3581149578094482,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 2.8755,
+      "step": 54
+    },
+    {
+      "epoch": 2.018348623853211,
+      "grad_norm": 18.337871551513672,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 3.4319,
+      "step": 55
+    },
+    {
+      "epoch": 2.055045871559633,
+      "grad_norm": 1.552891731262207,
+      "learning_rate": 2.886908691296504e-05,
+      "loss": 1.714,
+      "step": 56
+    },
+    {
+      "epoch": 2.091743119266055,
+      "grad_norm": 2.069896936416626,
+      "learning_rate": 2.6912569338248315e-05,
+      "loss": 2.0409,
+      "step": 57
+    },
+    {
+      "epoch": 2.128440366972477,
+      "grad_norm": 1.9617815017700195,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.1593,
+      "step": 58
+    },
+    {
+      "epoch": 2.165137614678899,
+      "grad_norm": 2.324594020843506,
+      "learning_rate": 2.3135019582658802e-05,
+      "loss": 2.6379,
+      "step": 59
+    },
+    {
+      "epoch": 2.2018348623853212,
+      "grad_norm": 2.1645970344543457,
+      "learning_rate": 2.132117818244771e-05,
+      "loss": 2.4046,
+      "step": 60
+    },
+    {
+      "epoch": 2.238532110091743,
+      "grad_norm": 1.891936182975769,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.5791,
+      "step": 61
+    },
+    {
+      "epoch": 2.2752293577981653,
+      "grad_norm": 1.838078498840332,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 1.8864,
+      "step": 62
+    },
+    {
+      "epoch": 2.311926605504587,
+      "grad_norm": 1.869794487953186,
+      "learning_rate": 1.622048961921699e-05,
+      "loss": 1.8824,
+      "step": 63
+    },
+    {
+      "epoch": 2.3486238532110093,
+      "grad_norm": 1.999611496925354,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.0747,
+      "step": 64
+    },
+    {
+      "epoch": 2.385321100917431,
+      "grad_norm": 2.4880917072296143,
+      "learning_rate": 1.3136133159493802e-05,
+      "loss": 2.5882,
+      "step": 65
+    },
+    {
+      "epoch": 2.4220183486238533,
+      "grad_norm": 2.3010945320129395,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 2.2849,
+      "step": 66
+    },
+    {
+      "epoch": 2.458715596330275,
+      "grad_norm": 2.2293477058410645,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 2.5007,
+      "step": 67
+    },
+    {
+      "epoch": 2.4954128440366974,
+      "grad_norm": 1.701717495918274,
+      "learning_rate": 9.042397785550405e-06,
+      "loss": 1.7229,
+      "step": 68
+    },
+    {
+      "epoch": 2.532110091743119,
+      "grad_norm": 1.9193297624588013,
+      "learning_rate": 7.830427709355725e-06,
+      "loss": 1.8555,
+      "step": 69
+    },
+    {
+      "epoch": 2.5688073394495414,
+      "grad_norm": 2.2191734313964844,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.2206,
+      "step": 70
+    },
+    {
+      "epoch": 2.6055045871559632,
+      "grad_norm": 2.41422176361084,
+      "learning_rate": 5.649458341088915e-06,
+      "loss": 2.4332,
+      "step": 71
+    },
+    {
+      "epoch": 2.6422018348623855,
+      "grad_norm": 2.3952369689941406,
+      "learning_rate": 4.684610648167503e-06,
+      "loss": 2.6096,
+      "step": 72
+    },
+    {
+      "epoch": 2.6788990825688073,
+      "grad_norm": 2.0205039978027344,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.0678,
+      "step": 73
+    },
+    {
+      "epoch": 2.7155963302752295,
+      "grad_norm": 1.8305858373641968,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 1.6213,
+      "step": 74
+    },
+    {
+      "epoch": 2.7522935779816513,
+      "grad_norm": 2.063669443130493,
+      "learning_rate": 2.314152462588659e-06,
+      "loss": 1.985,
+      "step": 75
+    },
+    {
+      "epoch": 2.7889908256880735,
+      "grad_norm": 2.322510004043579,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 2.3461,
+      "step": 76
+    },
+    {
+      "epoch": 2.8256880733944953,
+      "grad_norm": 2.1044540405273438,
+      "learning_rate": 1.1851996440033319e-06,
+      "loss": 2.1274,
+      "step": 77
+    },
+    {
+      "epoch": 2.8623853211009176,
+      "grad_norm": 2.5979394912719727,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 2.5614,
+      "step": 78
+    },
+    {
+      "epoch": 2.8990825688073394,
+      "grad_norm": 2.0980842113494873,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.837,
+      "step": 79
+    },
+    {
+      "epoch": 2.9357798165137616,
+      "grad_norm": 1.867730736732483,
+      "learning_rate": 1.9026509541272275e-07,
+      "loss": 1.7832,
+      "step": 80
+    },
+    {
+      "epoch": 2.9724770642201834,
+      "grad_norm": 2.4892702102661133,
+      "learning_rate": 4.7588920907110094e-08,
+      "loss": 2.4829,
+      "step": 81
+    },
+    {
+      "epoch": 3.0091743119266057,
+      "grad_norm": 23.18197250366211,
+      "learning_rate": 0.0,
+      "loss": 2.3259,
+      "step": 82
     }
   ],
   "logging_steps": 1,
@@ -396,12 +620,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3847335160578048.0,
+  "total_flos": 6286637428113408.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null