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:d718c29c051645601ac37c2d382a56abfc1d94cc7227eac8757dc30a6b1f9388
+oid sha256:1c926962a02992d481422d266a03825a891728b2bded8be561a554db9673160b
 size 1521616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0880fe06eac4373ec67f2002196a011acaaa914f697547d81813899603db3e2
+oid sha256:649ea80df6b6bab7ba3fb21fb5ccce9e9b5937acc05c9ad69a2c014f8bd0fb0f
 size 3108666

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7eaa9ae26b32fff7aac40a0b8a77423d29b0399f265b814617955c0f2ebf50c
+oid sha256:262d21b57da5e0b6aa01ffa79551fc281c9c8d6c32cbee7698b830e969c32c8d
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc7d2c3f9ea396aa1c53f325d21996bac2723c3fe0d7bea44e177e8e30d7e9c0
+oid sha256:3677d8ef37e770efdb7a29d52e182df0168e948ca0a6228ee9bfc86ac46e0027
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbef77e130e79b09194e4f5a99edd0167837835041ad24d354833804c75333f6
+oid sha256:2fd32b35f7279c703791837140fdb9d5dd8019fd8b555d0662d7f88943dd5b9c
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:614d528884e530c0f660b4689cb372d932693b2fa14d084d9ef589c853b1e03a
+oid sha256:f2eeb19651be28ea5bd8c48064026de410b1e4c0f55bba7c34b2f391ea488ce7
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb0ce41087f0939d63a9a6eb297660d82f62bda022868309a8c97328e5da41a5
+oid sha256:0b823f3900a3c8aa20bff7ce05b4e552f6bc019793f00b0bb20027204b5c704a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 7.796533584594727,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.4625614339404452,
+  "best_metric": 7.713439464569092,
+  "best_model_checkpoint": "miner_id_24/checkpoint-75",
+  "epoch": 0.6938421509106678,
   "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": 199.255,
       "eval_steps_per_second": 51.806,
       "step": 50
+    },
+    {
+      "epoch": 0.47181266261925414,
+      "grad_norm": 3.21820330619812,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 8.093,
+      "step": 51
+    },
+    {
+      "epoch": 0.48106389129806304,
+      "grad_norm": 1.3702133893966675,
+      "learning_rate": 3.082151762439293e-05,
+      "loss": 7.9204,
+      "step": 52
+    },
+    {
+      "epoch": 0.49031511997687194,
+      "grad_norm": 1.031348705291748,
+      "learning_rate": 2.9189060364202943e-05,
+      "loss": 7.8885,
+      "step": 53
+    },
+    {
+      "epoch": 0.49956634865568084,
+      "grad_norm": 1.0596493482589722,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 7.843,
+      "step": 54
+    },
+    {
+      "epoch": 0.5088175773344897,
+      "grad_norm": 0.9369666576385498,
+      "learning_rate": 2.6074557564105727e-05,
+      "loss": 7.7847,
+      "step": 55
+    },
+    {
+      "epoch": 0.5180688060132986,
+      "grad_norm": 0.9409084320068359,
+      "learning_rate": 2.459844065729529e-05,
+      "loss": 7.8721,
+      "step": 56
+    },
+    {
+      "epoch": 0.5273200346921075,
+      "grad_norm": 1.0068604946136475,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 7.6884,
+      "step": 57
+    },
+    {
+      "epoch": 0.5365712633709164,
+      "grad_norm": 1.0114176273345947,
+      "learning_rate": 2.1822519843544424e-05,
+      "loss": 7.76,
+      "step": 58
+    },
+    {
+      "epoch": 0.5458224920497253,
+      "grad_norm": 1.04805588722229,
+      "learning_rate": 2.0528000059645997e-05,
+      "loss": 7.784,
+      "step": 59
+    },
+    {
+      "epoch": 0.5550737207285342,
+      "grad_norm": 1.1247358322143555,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 7.728,
+      "step": 60
+    },
+    {
+      "epoch": 0.5643249494073431,
+      "grad_norm": 1.232703447341919,
+      "learning_rate": 1.8138158006995364e-05,
+      "loss": 7.99,
+      "step": 61
+    },
+    {
+      "epoch": 0.573576178086152,
+      "grad_norm": 2.0546152591705322,
+      "learning_rate": 1.7047384938420154e-05,
+      "loss": 8.099,
+      "step": 62
+    },
+    {
+      "epoch": 0.5828274067649609,
+      "grad_norm": 3.923598527908325,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 8.0151,
+      "step": 63
+    },
+    {
+      "epoch": 0.5920786354437699,
+      "grad_norm": 1.3706938028335571,
+      "learning_rate": 1.5084512506980026e-05,
+      "loss": 7.9288,
+      "step": 64
+    },
+    {
+      "epoch": 0.6013298641225788,
+      "grad_norm": 0.9312557578086853,
+      "learning_rate": 1.4216149583350754e-05,
+      "loss": 7.7455,
+      "step": 65
+    },
+    {
+      "epoch": 0.6105810928013877,
+      "grad_norm": 0.908347487449646,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 7.7296,
+      "step": 66
+    },
+    {
+      "epoch": 0.6198323214801966,
+      "grad_norm": 0.9519467949867249,
+      "learning_rate": 1.2713832064634126e-05,
+      "loss": 7.7021,
+      "step": 67
+    },
+    {
+      "epoch": 0.6290835501590055,
+      "grad_norm": 0.8736981153488159,
+      "learning_rate": 1.2082737216329794e-05,
+      "loss": 7.7688,
+      "step": 68
+    },
+    {
+      "epoch": 0.6383347788378144,
+      "grad_norm": 0.9096718430519104,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 7.6644,
+      "step": 69
+    },
+    {
+      "epoch": 0.6475860075166233,
+      "grad_norm": 0.9509488940238953,
+      "learning_rate": 1.1066679679603e-05,
+      "loss": 7.7987,
+      "step": 70
+    },
+    {
+      "epoch": 0.6568372361954322,
+      "grad_norm": 0.9723087549209595,
+      "learning_rate": 1.0683651114450641e-05,
+      "loss": 7.6467,
+      "step": 71
+    },
+    {
+      "epoch": 0.6660884648742411,
+      "grad_norm": 1.0477325916290283,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 7.6163,
+      "step": 72
+    },
+    {
+      "epoch": 0.67533969355305,
+      "grad_norm": 1.1920454502105713,
+      "learning_rate": 1.017123858587145e-05,
+      "loss": 7.7597,
+      "step": 73
+    },
+    {
+      "epoch": 0.6845909222318589,
+      "grad_norm": 1.7579151391983032,
+      "learning_rate": 1.00428300288164e-05,
+      "loss": 7.9359,
+      "step": 74
+    },
+    {
+      "epoch": 0.6938421509106678,
+      "grad_norm": 3.6170880794525146,
+      "learning_rate": 1e-05,
+      "loss": 8.2457,
+      "step": 75
+    },
+    {
+      "epoch": 0.6938421509106678,
+      "eval_loss": 7.713439464569092,
+      "eval_runtime": 0.2521,
+      "eval_samples_per_second": 198.357,
+      "eval_steps_per_second": 51.573,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -404,12 +587,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 232340067975168.0,
+  "total_flos": 348419471704064.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null