Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f6ed2e61326e441ff6609a196a622f5151c5c1b1ff65dc42700122f31fe7fae
+oid sha256:7f8f80f2386cb9db3ce12ff7ccaeb78eb6b9835458aadb1578a826de786cf982
 size 201892112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:851f14b04243a06811f4c79e5eccf5fd0e7feeef1ddd481d88e401fcfc9228d7
+oid sha256:15ad9ddaf822c024e0be348b39b84431a472a5905d910b63d90e55ef439c0325
 size 102864548

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99b7055de81db0ee829cd5e355a78a9c46dd242578f7176194b69b6241184dd4
+oid sha256:3dbdf0ec9db5c068d446dfcdd99b43f4ef46847a534d109eb799e0c987d54c77
 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": 1.1854989528656006,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.06532745386248572,
+  "epoch": 0.09799118079372857,
   "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": 22.835,
       "eval_steps_per_second": 5.713,
       "step": 50
+    },
+    {
+      "epoch": 0.06663400293973543,
+      "grad_norm": 0.3446987569332123,
+      "learning_rate": 4.007047666771274e-05,
+      "loss": 1.1683,
+      "step": 51
+    },
+    {
+      "epoch": 0.06794055201698514,
+      "grad_norm": 0.32134196162223816,
+      "learning_rate": 3.728908329032567e-05,
+      "loss": 1.1536,
+      "step": 52
+    },
+    {
+      "epoch": 0.06924710109423485,
+      "grad_norm": 0.3244422376155853,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 1.1818,
+      "step": 53
+    },
+    {
+      "epoch": 0.07055365017148457,
+      "grad_norm": 0.3293231427669525,
+      "learning_rate": 3.1859614732467954e-05,
+      "loss": 1.1682,
+      "step": 54
+    },
+    {
+      "epoch": 0.07186019924873428,
+      "grad_norm": 0.3526603579521179,
+      "learning_rate": 2.9229249349905684e-05,
+      "loss": 1.3071,
+      "step": 55
+    },
+    {
+      "epoch": 0.073166748325984,
+      "grad_norm": 0.32135894894599915,
+      "learning_rate": 2.6666633838716314e-05,
+      "loss": 1.0759,
+      "step": 56
+    },
+    {
+      "epoch": 0.0744732974032337,
+      "grad_norm": 0.34930694103240967,
+      "learning_rate": 2.418012691805191e-05,
+      "loss": 1.1261,
+      "step": 57
+    },
+    {
+      "epoch": 0.07577984648048343,
+      "grad_norm": 0.3539881706237793,
+      "learning_rate": 2.1777839056661554e-05,
+      "loss": 1.0906,
+      "step": 58
+    },
+    {
+      "epoch": 0.07708639555773314,
+      "grad_norm": 0.343544065952301,
+      "learning_rate": 1.946760601822809e-05,
+      "loss": 1.1448,
+      "step": 59
+    },
+    {
+      "epoch": 0.07839294463498285,
+      "grad_norm": 0.3482602536678314,
+      "learning_rate": 1.725696330273575e-05,
+      "loss": 1.1497,
+      "step": 60
+    },
+    {
+      "epoch": 0.07969949371223256,
+      "grad_norm": 0.4008278548717499,
+      "learning_rate": 1.5153121567235335e-05,
+      "loss": 1.2932,
+      "step": 61
+    },
+    {
+      "epoch": 0.08100604278948229,
+      "grad_norm": 0.3167479336261749,
+      "learning_rate": 1.3162943106179749e-05,
+      "loss": 1.0815,
+      "step": 62
+    },
+    {
+      "epoch": 0.082312591866732,
+      "grad_norm": 0.3656054139137268,
+      "learning_rate": 1.1292919468045877e-05,
+      "loss": 1.231,
+      "step": 63
+    },
+    {
+      "epoch": 0.0836191409439817,
+      "grad_norm": 0.3398679196834564,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.1555,
+      "step": 64
+    },
+    {
+      "epoch": 0.08492569002123142,
+      "grad_norm": 0.3247357904911041,
+      "learning_rate": 7.937323358440935e-06,
+      "loss": 1.1283,
+      "step": 65
+    },
+    {
+      "epoch": 0.08623223909848114,
+      "grad_norm": 0.35545697808265686,
+      "learning_rate": 6.462696144011149e-06,
+      "loss": 1.2001,
+      "step": 66
+    },
+    {
+      "epoch": 0.08753878817573085,
+      "grad_norm": 0.3901765048503876,
+      "learning_rate": 5.13007856543209e-06,
+      "loss": 1.1858,
+      "step": 67
+    },
+    {
+      "epoch": 0.08884533725298056,
+      "grad_norm": 0.3385303020477295,
+      "learning_rate": 3.9438173442575e-06,
+      "loss": 1.0452,
+      "step": 68
+    },
+    {
+      "epoch": 0.09015188633023027,
+      "grad_norm": 0.36181050539016724,
+      "learning_rate": 2.9077818180237693e-06,
+      "loss": 1.1804,
+      "step": 69
+    },
+    {
+      "epoch": 0.09145843540748,
+      "grad_norm": 0.32994315028190613,
+      "learning_rate": 2.0253513192751373e-06,
+      "loss": 1.1286,
+      "step": 70
+    },
+    {
+      "epoch": 0.09276498448472971,
+      "grad_norm": 0.364048033952713,
+      "learning_rate": 1.2994041528833266e-06,
+      "loss": 1.0935,
+      "step": 71
+    },
+    {
+      "epoch": 0.09407153356197942,
+      "grad_norm": 0.3363443613052368,
+      "learning_rate": 7.323082076153509e-07,
+      "loss": 1.1072,
+      "step": 72
+    },
+    {
+      "epoch": 0.09537808263922913,
+      "grad_norm": 0.34219974279403687,
+      "learning_rate": 3.2591323257248893e-07,
+      "loss": 1.168,
+      "step": 73
+    },
+    {
+      "epoch": 0.09668463171647886,
+      "grad_norm": 0.3555889129638672,
+      "learning_rate": 8.15448036932176e-08,
+      "loss": 1.1896,
+      "step": 74
+    },
+    {
+      "epoch": 0.09799118079372857,
+      "grad_norm": 0.33016109466552734,
+      "learning_rate": 0.0,
+      "loss": 1.135,
+      "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": 4.26629570494464e+16,
+  "total_flos": 6.39944355741696e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null