Training in progress, step 129, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56f105d80e43add9e28cdc56ffe995491a226d4158f6b9f7a3c0e0512990b1e8
+oid sha256:6087f1412432fe6e7a19fbac5890b1f61393d4fafff5c22530164d7a2462e468
 size 332316480

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17519092f21b83646bc69c019eb3a0a94542756f814a157af23f1e0cdc50a962
+oid sha256:f74d546e34abf136608c4ad7472988e56482ec78531c4520ce1664a42ae0132c
 size 169157892

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29cede69602d9069eda91e281a0d5378c703d3311f642430fac3d074099f06ee
+oid sha256:2f25a92e4f4be60975ae6fab70e6ca8904897fa21c93ce0df2ce8b7d994fa5de
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b50c067469c1b4b6cb25f6ad456ed01667d0d1e466ce910ba4e242673c657c6
+oid sha256:acd49f0ac2f43d9e345f567400b9b1c259ab7cf70ea7a5f3f1bc6679756e3efd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 2.5794575214385986,
   "best_model_checkpoint": "miner_id_24/checkpoint-100",
-  "epoch": 2.3391812865497075,
+  "epoch": 3.017543859649123,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 129,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -731,6 +731,209 @@
       "eval_samples_per_second": 22.0,
       "eval_steps_per_second": 5.5,
       "step": 100
+    },
+    {
+      "epoch": 2.3625730994152048,
+      "grad_norm": 3.9561784267425537,
+      "learning_rate": 1.3049554138967051e-05,
+      "loss": 1.5536,
+      "step": 101
+    },
+    {
+      "epoch": 2.3859649122807016,
+      "grad_norm": 3.936734914779663,
+      "learning_rate": 1.2173256946415212e-05,
+      "loss": 1.4171,
+      "step": 102
+    },
+    {
+      "epoch": 2.409356725146199,
+      "grad_norm": 4.206720352172852,
+      "learning_rate": 1.1323321826247346e-05,
+      "loss": 1.2999,
+      "step": 103
+    },
+    {
+      "epoch": 2.4327485380116958,
+      "grad_norm": 5.046553611755371,
+      "learning_rate": 1.0500341112070605e-05,
+      "loss": 1.0988,
+      "step": 104
+    },
+    {
+      "epoch": 2.456140350877193,
+      "grad_norm": 5.955111026763916,
+      "learning_rate": 9.704888352528258e-06,
+      "loss": 0.9185,
+      "step": 105
+    },
+    {
+      "epoch": 2.47953216374269,
+      "grad_norm": 3.576009511947632,
+      "learning_rate": 8.93751791158432e-06,
+      "loss": 1.9256,
+      "step": 106
+    },
+    {
+      "epoch": 2.502923976608187,
+      "grad_norm": 2.3604319095611572,
+      "learning_rate": 8.198764582178303e-06,
+      "loss": 1.9458,
+      "step": 107
+    },
+    {
+      "epoch": 2.526315789473684,
+      "grad_norm": 2.6111466884613037,
+      "learning_rate": 7.489143213519301e-06,
+      "loss": 1.7967,
+      "step": 108
+    },
+    {
+      "epoch": 2.5497076023391814,
+      "grad_norm": 3.0367538928985596,
+      "learning_rate": 6.809148352279182e-06,
+      "loss": 1.4832,
+      "step": 109
+    },
+    {
+      "epoch": 2.573099415204678,
+      "grad_norm": 3.416107416152954,
+      "learning_rate": 6.159253897935069e-06,
+      "loss": 1.6191,
+      "step": 110
+    },
+    {
+      "epoch": 2.5964912280701755,
+      "grad_norm": 3.648995876312256,
+      "learning_rate": 5.539912772500944e-06,
+      "loss": 1.4337,
+      "step": 111
+    },
+    {
+      "epoch": 2.6198830409356724,
+      "grad_norm": 3.623403310775757,
+      "learning_rate": 4.951556604879048e-06,
+      "loss": 1.1803,
+      "step": 112
+    },
+    {
+      "epoch": 2.6432748538011697,
+      "grad_norm": 4.428551197052002,
+      "learning_rate": 4.394595430050613e-06,
+      "loss": 1.1911,
+      "step": 113
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 4.538227558135986,
+      "learning_rate": 3.8694174033158555e-06,
+      "loss": 1.0355,
+      "step": 114
+    },
+    {
+      "epoch": 2.690058479532164,
+      "grad_norm": 5.722489833831787,
+      "learning_rate": 3.376388529782215e-06,
+      "loss": 0.9762,
+      "step": 115
+    },
+    {
+      "epoch": 2.7134502923976607,
+      "grad_norm": 3.4204437732696533,
+      "learning_rate": 2.9158524092894214e-06,
+      "loss": 1.7561,
+      "step": 116
+    },
+    {
+      "epoch": 2.736842105263158,
+      "grad_norm": 2.083275079727173,
+      "learning_rate": 2.488129996949251e-06,
+      "loss": 1.8624,
+      "step": 117
+    },
+    {
+      "epoch": 2.760233918128655,
+      "grad_norm": 2.574385404586792,
+      "learning_rate": 2.093519379466602e-06,
+      "loss": 1.7507,
+      "step": 118
+    },
+    {
+      "epoch": 2.783625730994152,
+      "grad_norm": 2.773837089538574,
+      "learning_rate": 1.7322955673980678e-06,
+      "loss": 1.6317,
+      "step": 119
+    },
+    {
+      "epoch": 2.807017543859649,
+      "grad_norm": 3.0657918453216553,
+      "learning_rate": 1.404710303492618e-06,
+      "loss": 1.7106,
+      "step": 120
+    },
+    {
+      "epoch": 2.8304093567251463,
+      "grad_norm": 3.1810173988342285,
+      "learning_rate": 1.1109918872479642e-06,
+      "loss": 1.4181,
+      "step": 121
+    },
+    {
+      "epoch": 2.853801169590643,
+      "grad_norm": 3.865628719329834,
+      "learning_rate": 8.513450158049108e-07,
+      "loss": 1.4733,
+      "step": 122
+    },
+    {
+      "epoch": 2.8771929824561404,
+      "grad_norm": 3.952064275741577,
+      "learning_rate": 6.259506412906402e-07,
+      "loss": 1.1925,
+      "step": 123
+    },
+    {
+      "epoch": 2.9005847953216373,
+      "grad_norm": 4.404904842376709,
+      "learning_rate": 4.349658447101612e-07,
+      "loss": 1.0374,
+      "step": 124
+    },
+    {
+      "epoch": 2.9239766081871346,
+      "grad_norm": 5.374385356903076,
+      "learning_rate": 2.785237264740781e-07,
+      "loss": 0.8663,
+      "step": 125
+    },
+    {
+      "epoch": 2.9473684210526314,
+      "grad_norm": 4.283792018890381,
+      "learning_rate": 1.567333136387017e-07,
+      "loss": 1.8765,
+      "step": 126
+    },
+    {
+      "epoch": 2.9707602339181287,
+      "grad_norm": 3.530892848968506,
+      "learning_rate": 6.967948392331835e-08,
+      "loss": 1.4727,
+      "step": 127
+    },
+    {
+      "epoch": 2.9941520467836256,
+      "grad_norm": 6.096131324768066,
+      "learning_rate": 1.742290655755707e-08,
+      "loss": 1.1021,
+      "step": 128
+    },
+    {
+      "epoch": 3.017543859649123,
+      "grad_norm": 3.1924569606781006,
+      "learning_rate": 0.0,
+      "loss": 2.1947,
+      "step": 129
     }
   ],
   "logging_steps": 1,
@@ -754,12 +957,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4.174757862624461e+16,
+  "total_flos": 5.386784338870272e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null