Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a01779fe543b5bef758cc4d92cde245c925f823c81fbba268576aaad71936c5
+oid sha256:aad2648564fc09bb7b9a8c1b41de047bc1d4efdbe9b6b39b7e4a11546a9b2f6e
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bac5e49a8a0f77f5db565db705b3752005f59b49f3fb17ded5b631c6f761fc92
+oid sha256:1d1f91fc307a0fff3c6543d72483253616d6baac9316facfca98c9d7977e9094
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:762db5ed258fbe7e96417821bcac11016bd2e16c747d8ee78a53f244b52a2b50
+oid sha256:b7395db3a1c36867fcc6984c64b2a864ad2a00e2b97d1e6eef15ac08aec4ffac
 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": 0.6736397743225098,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.2737850787132101,
+  "epoch": 0.4106776180698152,
   "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": 6.067,
       "eval_steps_per_second": 1.519,
       "step": 50
+    },
+    {
+      "epoch": 0.2792607802874743,
+      "grad_norm": 0.2991454601287842,
+      "learning_rate": 4.007047666771274e-05,
+      "loss": 0.6708,
+      "step": 51
+    },
+    {
+      "epoch": 0.28473648186173856,
+      "grad_norm": 0.4416026771068573,
+      "learning_rate": 3.728908329032567e-05,
+      "loss": 0.5792,
+      "step": 52
+    },
+    {
+      "epoch": 0.29021218343600275,
+      "grad_norm": 0.4120028614997864,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.6597,
+      "step": 53
+    },
+    {
+      "epoch": 0.29568788501026694,
+      "grad_norm": 0.32571035623550415,
+      "learning_rate": 3.1859614732467954e-05,
+      "loss": 0.6663,
+      "step": 54
+    },
+    {
+      "epoch": 0.30116358658453113,
+      "grad_norm": 0.3586292266845703,
+      "learning_rate": 2.9229249349905684e-05,
+      "loss": 0.7519,
+      "step": 55
+    },
+    {
+      "epoch": 0.3066392881587953,
+      "grad_norm": 0.41633692383766174,
+      "learning_rate": 2.6666633838716314e-05,
+      "loss": 0.5602,
+      "step": 56
+    },
+    {
+      "epoch": 0.31211498973305957,
+      "grad_norm": 0.31863197684288025,
+      "learning_rate": 2.418012691805191e-05,
+      "loss": 0.5738,
+      "step": 57
+    },
+    {
+      "epoch": 0.31759069130732376,
+      "grad_norm": 0.3499593436717987,
+      "learning_rate": 2.1777839056661554e-05,
+      "loss": 0.6865,
+      "step": 58
+    },
+    {
+      "epoch": 0.32306639288158795,
+      "grad_norm": 0.3165656626224518,
+      "learning_rate": 1.946760601822809e-05,
+      "loss": 0.6762,
+      "step": 59
+    },
+    {
+      "epoch": 0.32854209445585214,
+      "grad_norm": 0.2701724171638489,
+      "learning_rate": 1.725696330273575e-05,
+      "loss": 0.6685,
+      "step": 60
+    },
+    {
+      "epoch": 0.33401779603011633,
+      "grad_norm": 0.315905898809433,
+      "learning_rate": 1.5153121567235335e-05,
+      "loss": 0.639,
+      "step": 61
+    },
+    {
+      "epoch": 0.3394934976043806,
+      "grad_norm": 0.31216394901275635,
+      "learning_rate": 1.3162943106179749e-05,
+      "loss": 0.6063,
+      "step": 62
+    },
+    {
+      "epoch": 0.34496919917864477,
+      "grad_norm": 0.34306395053863525,
+      "learning_rate": 1.1292919468045877e-05,
+      "loss": 0.7331,
+      "step": 63
+    },
+    {
+      "epoch": 0.35044490075290896,
+      "grad_norm": 0.30784016847610474,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.7028,
+      "step": 64
+    },
+    {
+      "epoch": 0.35592060232717315,
+      "grad_norm": 0.26059669256210327,
+      "learning_rate": 7.937323358440935e-06,
+      "loss": 0.5754,
+      "step": 65
+    },
+    {
+      "epoch": 0.3613963039014374,
+      "grad_norm": 0.3006216287612915,
+      "learning_rate": 6.462696144011149e-06,
+      "loss": 0.6352,
+      "step": 66
+    },
+    {
+      "epoch": 0.3668720054757016,
+      "grad_norm": 0.32661935687065125,
+      "learning_rate": 5.13007856543209e-06,
+      "loss": 0.7031,
+      "step": 67
+    },
+    {
+      "epoch": 0.3723477070499658,
+      "grad_norm": 0.3083003759384155,
+      "learning_rate": 3.9438173442575e-06,
+      "loss": 0.5866,
+      "step": 68
+    },
+    {
+      "epoch": 0.37782340862423,
+      "grad_norm": 0.30131563544273376,
+      "learning_rate": 2.9077818180237693e-06,
+      "loss": 0.6072,
+      "step": 69
+    },
+    {
+      "epoch": 0.38329911019849416,
+      "grad_norm": 1.1107707023620605,
+      "learning_rate": 2.0253513192751373e-06,
+      "loss": 0.6356,
+      "step": 70
+    },
+    {
+      "epoch": 0.3887748117727584,
+      "grad_norm": 0.35799431800842285,
+      "learning_rate": 1.2994041528833266e-06,
+      "loss": 0.6736,
+      "step": 71
+    },
+    {
+      "epoch": 0.3942505133470226,
+      "grad_norm": 0.31380966305732727,
+      "learning_rate": 7.323082076153509e-07,
+      "loss": 0.6704,
+      "step": 72
+    },
+    {
+      "epoch": 0.3997262149212868,
+      "grad_norm": 0.2964222729206085,
+      "learning_rate": 3.2591323257248893e-07,
+      "loss": 0.6053,
+      "step": 73
+    },
+    {
+      "epoch": 0.405201916495551,
+      "grad_norm": 0.2598344385623932,
+      "learning_rate": 8.15448036932176e-08,
+      "loss": 0.5348,
+      "step": 74
+    },
+    {
+      "epoch": 0.4106776180698152,
+      "grad_norm": 0.35341641306877136,
+      "learning_rate": 0.0,
+      "loss": 0.6889,
+      "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": 3.028341009332306e+17,
+  "total_flos": 4.548168439918756e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null