Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed7b4e07cdeea136fbeb45894eea2f49845e9fb24f8dd500a9bd99d0e5483f98
+oid sha256:059db1a3c6684471f3645f6bb9b4b365abc003b7743d519625b9915c9f983356
 size 226530600

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f95bcea3f6401c1406348f68b92f93d12e149e8da2e525444ab479323cfdf335
+oid sha256:de9b3c85852cadf47ea03634c9743bdc5c2faae5ec1741ef69ba8550c4e64a0a
 size 115354708

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53d4fcd3851960c2dc3a6716ff16df631b6145dc916eadf88e970208e3fc415f
+oid sha256:57772fceaad7481ccbae002dfc8f1b78538485cd6d393a74683489520cf2d66f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83c409614fe7c4294c30c517ac4a1097721f51ec5d3456b5de1ee4e4e2aed9ba
+oid sha256:212837ccb433e5430b061dc107b19dc09e932e6cfb62a751187d0903b7b0d94e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.3463674783706665,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.3140950137416568,
+  "epoch": 0.4711425206124853,
   "eval_steps": 50,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -373,6 +373,181 @@
       "eval_samples_per_second": 16.452,
       "eval_steps_per_second": 4.136,
       "step": 50
+    },
+    {
+      "epoch": 0.32037691401649,
+      "grad_norm": 0.5381672382354736,
+      "learning_rate": 4.007047666771274e-05,
+      "loss": 1.3637,
+      "step": 51
+    },
+    {
+      "epoch": 0.32665881429132315,
+      "grad_norm": 0.5182757377624512,
+      "learning_rate": 3.728908329032567e-05,
+      "loss": 1.2958,
+      "step": 52
+    },
+    {
+      "epoch": 0.33294071456615626,
+      "grad_norm": 0.5560421347618103,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 1.362,
+      "step": 53
+    },
+    {
+      "epoch": 0.3392226148409894,
+      "grad_norm": 0.5303387641906738,
+      "learning_rate": 3.1859614732467954e-05,
+      "loss": 1.3819,
+      "step": 54
+    },
+    {
+      "epoch": 0.34550451511582253,
+      "grad_norm": 0.5558652877807617,
+      "learning_rate": 2.9229249349905684e-05,
+      "loss": 1.4103,
+      "step": 55
+    },
+    {
+      "epoch": 0.3517864153906557,
+      "grad_norm": 0.5830622315406799,
+      "learning_rate": 2.6666633838716314e-05,
+      "loss": 1.3872,
+      "step": 56
+    },
+    {
+      "epoch": 0.3580683156654888,
+      "grad_norm": 0.534251868724823,
+      "learning_rate": 2.418012691805191e-05,
+      "loss": 1.2987,
+      "step": 57
+    },
+    {
+      "epoch": 0.36435021594032196,
+      "grad_norm": 0.5476053357124329,
+      "learning_rate": 2.1777839056661554e-05,
+      "loss": 1.5308,
+      "step": 58
+    },
+    {
+      "epoch": 0.37063211621515507,
+      "grad_norm": 0.5888764262199402,
+      "learning_rate": 1.946760601822809e-05,
+      "loss": 1.3414,
+      "step": 59
+    },
+    {
+      "epoch": 0.37691401648998824,
+      "grad_norm": 0.5604611039161682,
+      "learning_rate": 1.725696330273575e-05,
+      "loss": 1.3186,
+      "step": 60
+    },
+    {
+      "epoch": 0.38319591676482134,
+      "grad_norm": 0.569729208946228,
+      "learning_rate": 1.5153121567235335e-05,
+      "loss": 1.2864,
+      "step": 61
+    },
+    {
+      "epoch": 0.3894778170396545,
+      "grad_norm": 0.5799680948257446,
+      "learning_rate": 1.3162943106179749e-05,
+      "loss": 1.3188,
+      "step": 62
+    },
+    {
+      "epoch": 0.3957597173144876,
+      "grad_norm": 0.5320284962654114,
+      "learning_rate": 1.1292919468045877e-05,
+      "loss": 1.3297,
+      "step": 63
+    },
+    {
+      "epoch": 0.4020416175893208,
+      "grad_norm": 0.6015669703483582,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.3177,
+      "step": 64
+    },
+    {
+      "epoch": 0.4083235178641539,
+      "grad_norm": 0.5521041750907898,
+      "learning_rate": 7.937323358440935e-06,
+      "loss": 1.3842,
+      "step": 65
+    },
+    {
+      "epoch": 0.41460541813898705,
+      "grad_norm": 0.5729659199714661,
+      "learning_rate": 6.462696144011149e-06,
+      "loss": 1.4533,
+      "step": 66
+    },
+    {
+      "epoch": 0.42088731841382016,
+      "grad_norm": 0.5563532710075378,
+      "learning_rate": 5.13007856543209e-06,
+      "loss": 1.3325,
+      "step": 67
+    },
+    {
+      "epoch": 0.4271692186886533,
+      "grad_norm": 0.5714989304542542,
+      "learning_rate": 3.9438173442575e-06,
+      "loss": 1.2834,
+      "step": 68
+    },
+    {
+      "epoch": 0.4334511189634865,
+      "grad_norm": 0.5417236685752869,
+      "learning_rate": 2.9077818180237693e-06,
+      "loss": 1.2234,
+      "step": 69
+    },
+    {
+      "epoch": 0.4397330192383196,
+      "grad_norm": 0.5344116687774658,
+      "learning_rate": 2.0253513192751373e-06,
+      "loss": 1.3796,
+      "step": 70
+    },
+    {
+      "epoch": 0.44601491951315275,
+      "grad_norm": 0.5636404156684875,
+      "learning_rate": 1.2994041528833266e-06,
+      "loss": 1.2578,
+      "step": 71
+    },
+    {
+      "epoch": 0.45229681978798586,
+      "grad_norm": 0.5255051255226135,
+      "learning_rate": 7.323082076153509e-07,
+      "loss": 1.2997,
+      "step": 72
+    },
+    {
+      "epoch": 0.458578720062819,
+      "grad_norm": 0.5886712074279785,
+      "learning_rate": 3.2591323257248893e-07,
+      "loss": 1.2594,
+      "step": 73
+    },
+    {
+      "epoch": 0.46486062033765213,
+      "grad_norm": 0.5472262501716614,
+      "learning_rate": 8.15448036932176e-08,
+      "loss": 1.3018,
+      "step": 74
+    },
+    {
+      "epoch": 0.4711425206124853,
+      "grad_norm": 0.5682985782623291,
+      "learning_rate": 0.0,
+      "loss": 1.3637,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -396,12 +571,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5.40066964266025e+16,
+  "total_flos": 8.09427046194217e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null