Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed2a352a96795d3d32decb918cae5ec466a329c7ead2afce5e6747750d2bfa8d
+oid sha256:5b951559027f05cdd508e75a9b8b5291b4be6ca167fd581fd4022e79ad96daae
 size 34456

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4f30e29bb3ce5fc5ba1851d8ee9383600ab136b41b472b3a6dfd3f9bd945eb6
+oid sha256:624aef0cdaccb14b46e711e1634878ef495b55181b07d161bb8babe26c1e5006
 size 73222

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9c1f84d56feb8ecdaa45c77bd1766d318fdfbb04f1a91acdbb0d8fc599a5cfb
+oid sha256:db042482eed41b4a8293a5813132253377a3868f30d03a54db92c917bf34e714
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4ae22b8777c8fce6f1216ac39bb3d1ef6dac6f58c5bece65cfca82402a3f43d
+oid sha256:baeb6e352a0effdb69f2c0143397f04c8fc09b30ad2a95a34c6e230fcf47a419
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6230483d6ee28269154958c0fa5b645e09d727df40a8dd926d53355a4b0929b
+oid sha256:5e397d451e9d940302bfe4521dd97ace70f13c66090df09f35aab6c46bcf5f09
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf5568fe5b96a56b888d855aa34b496612e1adf9733b80273d1e4b937ac60354
+oid sha256:a66ce8e08207715ba6adc2058badf02d74a42a155b993ab60c78abf493a5876b
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a54844723cfb539f71ee39e3d624e8fd63fc00d4f6a348e49479a30f72d4d8e5
+oid sha256:ef85a57294063fec92acd4d2dcff06a27d0c9ddfb7f8ed43d15fa73ed0b05aff
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b2bc5f6529ca7356495dd34558bc2503c9e1d48a6a3f5c1d227b22488fa056c
+oid sha256:9cbe6e8e77ec1269c3b051ea77445acde2244359e637a5cbdd6b07d933efc591
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8cd9cdac0a74a75804e468a24053cf9d4f95152e5812753f96579e4c0aa32a9
+oid sha256:93a58b4199776d2fe849ac943a842a33a4106fb39a9f221618f36cc16e9a9cb2
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b24e8137d3e3ca43be71e807b2a85bf25a29a342f6483be4dac499979d5c496f
+oid sha256:d74a28a4247163126264eefadb48d97419e5c5dc2cec2ebeb735374e2323e68e
 size 15984

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f343f6f656a006328f2f440ec0a3b58e81fe8cae5f660f6870d074aaeee04682
+oid sha256:059a5235389ab21b3c321dfd9de044664390d0d921d0f51228263094059c973e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 11.5,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 1.5037593984962405,
+  "epoch": 3.007518796992481,
   "eval_steps": 50,
-  "global_step": 50,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -373,6 +373,364 @@
       "eval_samples_per_second": 1458.84,
       "eval_steps_per_second": 45.896,
       "step": 50
+    },
+    {
+      "epoch": 1.5338345864661656,
+      "grad_norm": 0.0003437866980675608,
+      "learning_rate": 5.498888888888888e-05,
+      "loss": 46.0,
+      "step": 51
+    },
+    {
+      "epoch": 1.5639097744360901,
+      "grad_norm": 0.00032857232145033777,
+      "learning_rate": 5.3866666666666664e-05,
+      "loss": 46.0,
+      "step": 52
+    },
+    {
+      "epoch": 1.5939849624060152,
+      "grad_norm": 0.00038689709617756307,
+      "learning_rate": 5.274444444444445e-05,
+      "loss": 46.0,
+      "step": 53
+    },
+    {
+      "epoch": 1.6240601503759398,
+      "grad_norm": 0.0004355922865215689,
+      "learning_rate": 5.162222222222222e-05,
+      "loss": 46.0,
+      "step": 54
+    },
+    {
+      "epoch": 1.6541353383458648,
+      "grad_norm": 0.0005018658121116459,
+      "learning_rate": 5.05e-05,
+      "loss": 46.0,
+      "step": 55
+    },
+    {
+      "epoch": 1.6842105263157894,
+      "grad_norm": 0.00045422802213579416,
+      "learning_rate": 4.9377777777777776e-05,
+      "loss": 46.0,
+      "step": 56
+    },
+    {
+      "epoch": 1.7142857142857144,
+      "grad_norm": 0.0003774865763261914,
+      "learning_rate": 4.825555555555556e-05,
+      "loss": 46.0,
+      "step": 57
+    },
+    {
+      "epoch": 1.744360902255639,
+      "grad_norm": 0.00042634535930119455,
+      "learning_rate": 4.713333333333334e-05,
+      "loss": 46.0,
+      "step": 58
+    },
+    {
+      "epoch": 1.774436090225564,
+      "grad_norm": 0.000391370733268559,
+      "learning_rate": 4.601111111111111e-05,
+      "loss": 46.0,
+      "step": 59
+    },
+    {
+      "epoch": 1.8045112781954886,
+      "grad_norm": 0.00042282594949938357,
+      "learning_rate": 4.488888888888889e-05,
+      "loss": 46.0,
+      "step": 60
+    },
+    {
+      "epoch": 1.8345864661654137,
+      "grad_norm": 0.0005342218209989369,
+      "learning_rate": 4.376666666666667e-05,
+      "loss": 46.0,
+      "step": 61
+    },
+    {
+      "epoch": 1.8646616541353382,
+      "grad_norm": 0.0004987895372323692,
+      "learning_rate": 4.2644444444444443e-05,
+      "loss": 46.0,
+      "step": 62
+    },
+    {
+      "epoch": 1.8947368421052633,
+      "grad_norm": 0.00042961034341715276,
+      "learning_rate": 4.152222222222222e-05,
+      "loss": 46.0,
+      "step": 63
+    },
+    {
+      "epoch": 1.9248120300751879,
+      "grad_norm": 0.00040588382398709655,
+      "learning_rate": 4.0400000000000006e-05,
+      "loss": 46.0,
+      "step": 64
+    },
+    {
+      "epoch": 1.954887218045113,
+      "grad_norm": 0.00041778653394430876,
+      "learning_rate": 3.927777777777778e-05,
+      "loss": 46.0,
+      "step": 65
+    },
+    {
+      "epoch": 1.9849624060150375,
+      "grad_norm": 0.00044860667549073696,
+      "learning_rate": 3.8155555555555555e-05,
+      "loss": 46.0,
+      "step": 66
+    },
+    {
+      "epoch": 2.0150375939849625,
+      "grad_norm": 0.00040975239244289696,
+      "learning_rate": 3.703333333333333e-05,
+      "loss": 46.0,
+      "step": 67
+    },
+    {
+      "epoch": 2.045112781954887,
+      "grad_norm": 0.00044060847721993923,
+      "learning_rate": 3.591111111111111e-05,
+      "loss": 46.0,
+      "step": 68
+    },
+    {
+      "epoch": 2.075187969924812,
+      "grad_norm": 0.0006466583581641316,
+      "learning_rate": 3.4788888888888886e-05,
+      "loss": 46.0,
+      "step": 69
+    },
+    {
+      "epoch": 2.1052631578947367,
+      "grad_norm": 0.000526844582054764,
+      "learning_rate": 3.366666666666667e-05,
+      "loss": 46.0,
+      "step": 70
+    },
+    {
+      "epoch": 2.1353383458646618,
+      "grad_norm": 0.0005004553822800517,
+      "learning_rate": 3.254444444444445e-05,
+      "loss": 46.0,
+      "step": 71
+    },
+    {
+      "epoch": 2.1654135338345863,
+      "grad_norm": 0.0004915460012853146,
+      "learning_rate": 3.142222222222222e-05,
+      "loss": 46.0,
+      "step": 72
+    },
+    {
+      "epoch": 2.1954887218045114,
+      "grad_norm": 0.0004236290114931762,
+      "learning_rate": 3.0299999999999998e-05,
+      "loss": 46.0,
+      "step": 73
+    },
+    {
+      "epoch": 2.225563909774436,
+      "grad_norm": 0.000418194686062634,
+      "learning_rate": 2.9177777777777776e-05,
+      "loss": 46.0,
+      "step": 74
+    },
+    {
+      "epoch": 2.255639097744361,
+      "grad_norm": 0.0006017014384269714,
+      "learning_rate": 2.8055555555555557e-05,
+      "loss": 46.0,
+      "step": 75
+    },
+    {
+      "epoch": 2.2857142857142856,
+      "grad_norm": 0.0006093091797083616,
+      "learning_rate": 2.6933333333333332e-05,
+      "loss": 46.0,
+      "step": 76
+    },
+    {
+      "epoch": 2.3157894736842106,
+      "grad_norm": 0.0005279547767713666,
+      "learning_rate": 2.581111111111111e-05,
+      "loss": 46.0,
+      "step": 77
+    },
+    {
+      "epoch": 2.345864661654135,
+      "grad_norm": 0.000503562914673239,
+      "learning_rate": 2.4688888888888888e-05,
+      "loss": 46.0,
+      "step": 78
+    },
+    {
+      "epoch": 2.3759398496240602,
+      "grad_norm": 0.0005086955497972667,
+      "learning_rate": 2.356666666666667e-05,
+      "loss": 46.0,
+      "step": 79
+    },
+    {
+      "epoch": 2.406015037593985,
+      "grad_norm": 0.0005278786411508918,
+      "learning_rate": 2.2444444444444444e-05,
+      "loss": 46.0,
+      "step": 80
+    },
+    {
+      "epoch": 2.43609022556391,
+      "grad_norm": 0.0005769961280748248,
+      "learning_rate": 2.1322222222222222e-05,
+      "loss": 46.0,
+      "step": 81
+    },
+    {
+      "epoch": 2.4661654135338344,
+      "grad_norm": 0.0006405999301932752,
+      "learning_rate": 2.0200000000000003e-05,
+      "loss": 46.0,
+      "step": 82
+    },
+    {
+      "epoch": 2.4962406015037595,
+      "grad_norm": 0.000521977839525789,
+      "learning_rate": 1.9077777777777778e-05,
+      "loss": 46.0,
+      "step": 83
+    },
+    {
+      "epoch": 2.526315789473684,
+      "grad_norm": 0.0004871116252616048,
+      "learning_rate": 1.7955555555555556e-05,
+      "loss": 46.0,
+      "step": 84
+    },
+    {
+      "epoch": 2.556390977443609,
+      "grad_norm": 0.0005196544225327671,
+      "learning_rate": 1.6833333333333334e-05,
+      "loss": 46.0,
+      "step": 85
+    },
+    {
+      "epoch": 2.5864661654135337,
+      "grad_norm": 0.00043869740329682827,
+      "learning_rate": 1.571111111111111e-05,
+      "loss": 46.0,
+      "step": 86
+    },
+    {
+      "epoch": 2.6165413533834587,
+      "grad_norm": 0.0005383821553550661,
+      "learning_rate": 1.4588888888888888e-05,
+      "loss": 46.0,
+      "step": 87
+    },
+    {
+      "epoch": 2.6466165413533833,
+      "grad_norm": 0.0007268090848810971,
+      "learning_rate": 1.3466666666666666e-05,
+      "loss": 46.0,
+      "step": 88
+    },
+    {
+      "epoch": 2.6766917293233083,
+      "grad_norm": 0.0006505560595542192,
+      "learning_rate": 1.2344444444444444e-05,
+      "loss": 46.0,
+      "step": 89
+    },
+    {
+      "epoch": 2.706766917293233,
+      "grad_norm": 0.0005259292083792388,
+      "learning_rate": 1.1222222222222222e-05,
+      "loss": 46.0,
+      "step": 90
+    },
+    {
+      "epoch": 2.736842105263158,
+      "grad_norm": 0.0004948357818648219,
+      "learning_rate": 1.0100000000000002e-05,
+      "loss": 46.0,
+      "step": 91
+    },
+    {
+      "epoch": 2.7669172932330826,
+      "grad_norm": 0.00042854080675169826,
+      "learning_rate": 8.977777777777778e-06,
+      "loss": 46.0,
+      "step": 92
+    },
+    {
+      "epoch": 2.7969924812030076,
+      "grad_norm": 0.00048204101040028036,
+      "learning_rate": 7.855555555555556e-06,
+      "loss": 46.0,
+      "step": 93
+    },
+    {
+      "epoch": 2.827067669172932,
+      "grad_norm": 0.0006985705113038421,
+      "learning_rate": 6.733333333333333e-06,
+      "loss": 46.0,
+      "step": 94
+    },
+    {
+      "epoch": 2.857142857142857,
+      "grad_norm": 0.0005821044323965907,
+      "learning_rate": 5.611111111111111e-06,
+      "loss": 46.0,
+      "step": 95
+    },
+    {
+      "epoch": 2.887218045112782,
+      "grad_norm": 0.0005263919592835009,
+      "learning_rate": 4.488888888888889e-06,
+      "loss": 46.0,
+      "step": 96
+    },
+    {
+      "epoch": 2.917293233082707,
+      "grad_norm": 0.0005317186005413532,
+      "learning_rate": 3.3666666666666665e-06,
+      "loss": 46.0,
+      "step": 97
+    },
+    {
+      "epoch": 2.9473684210526314,
+      "grad_norm": 0.00046762413694523275,
+      "learning_rate": 2.2444444444444445e-06,
+      "loss": 46.0,
+      "step": 98
+    },
+    {
+      "epoch": 2.9774436090225564,
+      "grad_norm": 0.0006510710809379816,
+      "learning_rate": 1.1222222222222222e-06,
+      "loss": 46.0,
+      "step": 99
+    },
+    {
+      "epoch": 3.007518796992481,
+      "grad_norm": 0.00044690861250273883,
+      "learning_rate": 0.0,
+      "loss": 46.0,
+      "step": 100
+    },
+    {
+      "epoch": 3.007518796992481,
+      "eval_loss": 11.5,
+      "eval_runtime": 0.3049,
+      "eval_samples_per_second": 1459.491,
+      "eval_steps_per_second": 45.917,
+      "step": 100
     }
   ],
   "logging_steps": 1,
@@ -387,7 +745,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -396,12 +754,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 64316925542400.0,
+  "total_flos": 128633851084800.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null