Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93687b280ee3b57565942dd5a1b28421a8d93bcd46ef3887a93f8fd0bdefedba
+oid sha256:f583834bbce9dff3c4190e4b544b32cc3e6b8aad0c2cc4db78f90c32b494c6d5
 size 1521616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e91d4f88bd79beb1c72af0cdae8374284090306de813be81a6d7814a2419edad
+oid sha256:5f703d7b3e3b461cee90be78974a3149b62f1634412ab8d20eb71e6af8041e7b
 size 3108666

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8066a8fce9d55dac9daad2ad7a95eee3ca41a28c3ca97002ba6d884580d00ab6
+oid sha256:348423016cd468e87bf1055688f8279d584df3402114224ced597d402741a6c2
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7728bbd8c2b314bc5cc878c06847c81f1886c79d3f48803f64a02a522dcee135
+oid sha256:9e423371f7241bbc318ffebfbb1762f075f08a1dfc821d8377483824ee44ae67
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d98e76b5d6907d288fe29a1b37db6d8c6501718be49c5826034cc22d2baf037
+oid sha256:225aef233c53e245d3147cba77ccbcd1c9ff6db4d8ad774acf8f7604b5685443
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f991b0b770a9b4b790ae4822e231cee53fd7e3e7642bce4020b2ffa8635a6cd5
+oid sha256:9c55d4b9e6b75c072d7f3861825bd82916294198d7211847ee3bf7eacf37cec4
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df19ed1a9610a5422497073697cbf4575f80de47fbb46ef0cdd2779386b031fa
+oid sha256:a5b53655d80c3ade692dacae57cafa4aff84c325b5cb8d0fba89d01b50d41566
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 8.629364013671875,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.03555634569657103,
+  "best_metric": 8.485151290893555,
+  "best_model_checkpoint": "miner_id_24/checkpoint-75",
+  "epoch": 0.05333451854485655,
   "eval_steps": 25,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -381,6 +381,189 @@
       "eval_samples_per_second": 105.064,
       "eval_steps_per_second": 27.317,
       "step": 50
+    },
+    {
+      "epoch": 0.036267472610502456,
+      "grad_norm": 1.2948602437973022,
+      "learning_rate": 5.192909139858981e-05,
+      "loss": 8.3854,
+      "step": 51
+    },
+    {
+      "epoch": 0.03697859952443388,
+      "grad_norm": 1.202957272529602,
+      "learning_rate": 5.0398113297608465e-05,
+      "loss": 8.4592,
+      "step": 52
+    },
+    {
+      "epoch": 0.037689726438365295,
+      "grad_norm": 1.0991284847259521,
+      "learning_rate": 4.887250079066892e-05,
+      "loss": 8.3654,
+      "step": 53
+    },
+    {
+      "epoch": 0.03840085335229672,
+      "grad_norm": 1.049133539199829,
+      "learning_rate": 4.7354032673710005e-05,
+      "loss": 8.5559,
+      "step": 54
+    },
+    {
+      "epoch": 0.03911198026622814,
+      "grad_norm": 1.0683585405349731,
+      "learning_rate": 4.584447941263149e-05,
+      "loss": 8.8506,
+      "step": 55
+    },
+    {
+      "epoch": 0.03982310718015956,
+      "grad_norm": 1.2173759937286377,
+      "learning_rate": 4.43456010790099e-05,
+      "loss": 8.7193,
+      "step": 56
+    },
+    {
+      "epoch": 0.04053423409409098,
+      "grad_norm": 1.0298593044281006,
+      "learning_rate": 4.285914529793391e-05,
+      "loss": 8.8945,
+      "step": 57
+    },
+    {
+      "epoch": 0.0412453610080224,
+      "grad_norm": 1.0951929092407227,
+      "learning_rate": 4.13868452103516e-05,
+      "loss": 9.0274,
+      "step": 58
+    },
+    {
+      "epoch": 0.04195648792195382,
+      "grad_norm": 0.9960741996765137,
+      "learning_rate": 3.9930417452305626e-05,
+      "loss": 8.904,
+      "step": 59
+    },
+    {
+      "epoch": 0.04266761483588524,
+      "grad_norm": 1.194457769393921,
+      "learning_rate": 3.8491560153412466e-05,
+      "loss": 8.9637,
+      "step": 60
+    },
+    {
+      "epoch": 0.043378741749816666,
+      "grad_norm": 1.4879592657089233,
+      "learning_rate": 3.707195095691913e-05,
+      "loss": 9.1381,
+      "step": 61
+    },
+    {
+      "epoch": 0.04408986866374808,
+      "grad_norm": 1.7354305982589722,
+      "learning_rate": 3.567324506364632e-05,
+      "loss": 8.9569,
+      "step": 62
+    },
+    {
+      "epoch": 0.044800995577679505,
+      "grad_norm": 1.2308183908462524,
+      "learning_rate": 3.4297073302098156e-05,
+      "loss": 8.0746,
+      "step": 63
+    },
+    {
+      "epoch": 0.04551212249161093,
+      "grad_norm": 1.1788955926895142,
+      "learning_rate": 3.2945040226989244e-05,
+      "loss": 8.4578,
+      "step": 64
+    },
+    {
+      "epoch": 0.046223249405542344,
+      "grad_norm": 1.1902447938919067,
+      "learning_rate": 3.16187222484055e-05,
+      "loss": 8.1835,
+      "step": 65
+    },
+    {
+      "epoch": 0.04693437631947377,
+      "grad_norm": 1.241468906402588,
+      "learning_rate": 3.0319665793780648e-05,
+      "loss": 8.0961,
+      "step": 66
+    },
+    {
+      "epoch": 0.04764550323340519,
+      "grad_norm": 1.0362024307250977,
+      "learning_rate": 2.9049385504830985e-05,
+      "loss": 8.6565,
+      "step": 67
+    },
+    {
+      "epoch": 0.048356630147336606,
+      "grad_norm": 0.9590556621551514,
+      "learning_rate": 2.7809362471550748e-05,
+      "loss": 8.8393,
+      "step": 68
+    },
+    {
+      "epoch": 0.04906775706126803,
+      "grad_norm": 0.9237630367279053,
+      "learning_rate": 2.660104250532764e-05,
+      "loss": 8.8098,
+      "step": 69
+    },
+    {
+      "epoch": 0.04977888397519945,
+      "grad_norm": 0.9075753092765808,
+      "learning_rate": 2.5425834453191232e-05,
+      "loss": 8.8575,
+      "step": 70
+    },
+    {
+      "epoch": 0.05049001088913087,
+      "grad_norm": 1.0483438968658447,
+      "learning_rate": 2.4285108555160577e-05,
+      "loss": 8.9505,
+      "step": 71
+    },
+    {
+      "epoch": 0.05120113780306229,
+      "grad_norm": 1.1041228771209717,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 8.9506,
+      "step": 72
+    },
+    {
+      "epoch": 0.051912264716993714,
+      "grad_norm": 1.2572849988937378,
+      "learning_rate": 2.2112381607484417e-05,
+      "loss": 8.8908,
+      "step": 73
+    },
+    {
+      "epoch": 0.05262339163092513,
+      "grad_norm": 1.5153453350067139,
+      "learning_rate": 2.1082913860268765e-05,
+      "loss": 9.1148,
+      "step": 74
+    },
+    {
+      "epoch": 0.05333451854485655,
+      "grad_norm": 2.149052619934082,
+      "learning_rate": 2.0092991918301108e-05,
+      "loss": 9.13,
+      "step": 75
+    },
+    {
+      "epoch": 0.05333451854485655,
+      "eval_loss": 8.485151290893555,
+      "eval_runtime": 0.4834,
+      "eval_samples_per_second": 103.437,
+      "eval_steps_per_second": 26.894,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -409,7 +592,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 232013797785600.0,
+  "total_flos": 348020696678400.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null