Training in progress, step 119, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f757c3e1b1a28ac8f73b2218643ddc385adca6f4a8a0dd016f0c4f246d712b3e
+oid sha256:e3dd7a21a4e569c749409d50ac89148aab852b4313f89d44feb028807cb75774
 size 231448

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:497ce543c979f2ce6f4ec604b6dbb0c254acac3c6ca06459b03a6c85dc28ab22
+oid sha256:ea48cc6707d7cc34eaad72e155840be4cdb3ccaf4dc2f287b343caf2c3cf839e
 size 254576

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82b356d78178e7a2ae49b0fb5f7a237878fdd3cbd73389518882f29c15bba89a
+oid sha256:c442b1586b35f38f53dc754b0acf3319f62d976794dea33e04f32e9234f79ce1
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e635241d528538f9bb04a27dca5fb22e408ffea565ee1b598b71a97a8d2e276e
+oid sha256:927e2892925a2a06cf03905ae7d4eaefc90931850a6059ce86cd9ecd4cda1939
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5b09a32341207947bc8fe88055fd4f4b39f334a2b00e666668ba1609a1ced5d
+oid sha256:760224d83793ba66736eaf062fd2ac4a49d7aacae3a6be37752aec8874bdd256
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de5a2676afef28fc154aabe5bdf74e4a7892b71f71996a710d1917fc7ca1b511
+oid sha256:3803ebbc7c0d6617f66382fc25c4c8883331a70a6b685548b808faceb8317259
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a6e11399356e19cdcb0f1309056bbc4f1328deb0ce732adfdc3024d8890e09c
+oid sha256:b2d9855d560c6215cd274a4aa0b1d0ae171e1a930f52123b698de04b2a488e0a
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b48b6dc79365b72e57891463df2fe10a703a10748598155ce0cfda494a19b72
+oid sha256:ee8ca76bc58688c439e07fb502a1e5217f6281b386c5dfdc0f2e522ced398a81
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1aa459af208bd13482a6f15758e0637d9fd1b243c7b5e2c58379848399e3547
+oid sha256:d7382f055d15bf806fc789a57b301a409008c8d57878842462ba7e76cbdbf2ee
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7091f6691296f0113046371fd5a02f74d9f53e794634f79726eeceeb49c779c1
+oid sha256:88a43a63ce63d2508c50e86ec058ecc0e3cd162a22083ad025498042ec775277
 size 15984

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d0cd91d59507c28bc18bd9b01764d373ca8bb673def2d9bd5d155d2ea42c3fa
+oid sha256:daeaa5730100adbc7e999120bcfde2edc17529df09920a58e9651489db9d4fe9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 10.305556297302246,
   "best_model_checkpoint": "miner_id_24/checkpoint-100",
-  "epoch": 2.5283018867924527,
+  "epoch": 3.0125786163522013,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 119,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -731,6 +731,139 @@
       "eval_samples_per_second": 3010.845,
       "eval_steps_per_second": 95.851,
       "step": 100
+    },
+    {
+      "epoch": 2.5534591194968552,
+      "grad_norm": 0.1466299146413803,
+      "learning_rate": 1.667889908256881e-05,
+      "loss": 10.3158,
+      "step": 101
+    },
+    {
+      "epoch": 2.5786163522012577,
+      "grad_norm": 0.17850784957408905,
+      "learning_rate": 1.5752293577981652e-05,
+      "loss": 10.2993,
+      "step": 102
+    },
+    {
+      "epoch": 2.6037735849056602,
+      "grad_norm": 0.2629879117012024,
+      "learning_rate": 1.4825688073394497e-05,
+      "loss": 10.2901,
+      "step": 103
+    },
+    {
+      "epoch": 2.6289308176100628,
+      "grad_norm": 0.3722081184387207,
+      "learning_rate": 1.389908256880734e-05,
+      "loss": 10.2754,
+      "step": 104
+    },
+    {
+      "epoch": 2.6540880503144653,
+      "grad_norm": 0.17005372047424316,
+      "learning_rate": 1.2972477064220185e-05,
+      "loss": 10.3255,
+      "step": 105
+    },
+    {
+      "epoch": 2.6792452830188678,
+      "grad_norm": 0.14880169928073883,
+      "learning_rate": 1.2045871559633028e-05,
+      "loss": 10.3339,
+      "step": 106
+    },
+    {
+      "epoch": 2.7044025157232703,
+      "grad_norm": 0.18930739164352417,
+      "learning_rate": 1.1119266055045872e-05,
+      "loss": 10.3178,
+      "step": 107
+    },
+    {
+      "epoch": 2.729559748427673,
+      "grad_norm": 0.18744437396526337,
+      "learning_rate": 1.0192660550458717e-05,
+      "loss": 10.2987,
+      "step": 108
+    },
+    {
+      "epoch": 2.7547169811320753,
+      "grad_norm": 0.27432578802108765,
+      "learning_rate": 9.26605504587156e-06,
+      "loss": 10.2927,
+      "step": 109
+    },
+    {
+      "epoch": 2.779874213836478,
+      "grad_norm": 0.31490325927734375,
+      "learning_rate": 8.339449541284405e-06,
+      "loss": 10.2855,
+      "step": 110
+    },
+    {
+      "epoch": 2.8050314465408803,
+      "grad_norm": 0.17064593732357025,
+      "learning_rate": 7.412844036697248e-06,
+      "loss": 10.3155,
+      "step": 111
+    },
+    {
+      "epoch": 2.830188679245283,
+      "grad_norm": 0.15425540506839752,
+      "learning_rate": 6.4862385321100925e-06,
+      "loss": 10.3282,
+      "step": 112
+    },
+    {
+      "epoch": 2.8553459119496853,
+      "grad_norm": 0.14992254972457886,
+      "learning_rate": 5.559633027522936e-06,
+      "loss": 10.3263,
+      "step": 113
+    },
+    {
+      "epoch": 2.880503144654088,
+      "grad_norm": 0.1558142602443695,
+      "learning_rate": 4.63302752293578e-06,
+      "loss": 10.3093,
+      "step": 114
+    },
+    {
+      "epoch": 2.9056603773584904,
+      "grad_norm": 0.2051534205675125,
+      "learning_rate": 3.706422018348624e-06,
+      "loss": 10.2948,
+      "step": 115
+    },
+    {
+      "epoch": 2.930817610062893,
+      "grad_norm": 0.2544957101345062,
+      "learning_rate": 2.779816513761468e-06,
+      "loss": 10.2848,
+      "step": 116
+    },
+    {
+      "epoch": 2.9559748427672954,
+      "grad_norm": 0.13796408474445343,
+      "learning_rate": 1.853211009174312e-06,
+      "loss": 10.3145,
+      "step": 117
+    },
+    {
+      "epoch": 2.981132075471698,
+      "grad_norm": 0.12653085589408875,
+      "learning_rate": 9.26605504587156e-07,
+      "loss": 10.3105,
+      "step": 118
+    },
+    {
+      "epoch": 3.0125786163522013,
+      "grad_norm": 0.185125932097435,
+      "learning_rate": 0.0,
+      "loss": 16.0677,
+      "step": 119
     }
   ],
   "logging_steps": 1,
@@ -754,12 +887,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 173649218764800.0,
+  "total_flos": 206642570330112.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null