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:be2cdc9b7ce8dcb284902a96981e16dc701c0ffec1ea253c7f1bb5694506721a
+oid sha256:a66f25ee2fed464548452fb2a60bdb28d8f82b6ed6c6ea1df69a0bb29c2c8a4d
 size 48552

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:100ad461e8d4ad4462240765229d93ff37a6483ba48209835b06e6c036e7a5ff
+oid sha256:aad080622957a85dce2218b16182ea70a817fc941fde1a6b5fd46a2729409b03
 size 113994

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86556344de920fe43d329034bb740375cf66aadfaa5e1fd459c34bcf3d2b4c77
+oid sha256:1f422b45365cb3be603c2a123b6b91d5919a15ea9396db867356cd456f0536d7
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3be56923d6a9d5cea3456e8f309490172a5ad932fdf15a749e294eb6a809ef7f
+oid sha256:b31c416067751e91fdf60f0b4e564040ba5187a21030a9801ca159fe9b2c757c
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1479f80d61560df7dac391de081439d95b89699f831bcc28065d8345f554ac31
+oid sha256:7edf9d81a212f43af864e6439eb461fe315e0aa83217b2ba2f18cfc14b3dfb5f
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68aa51309bb9546620e0e7ccd79f0563fc0a682244573ba0d1f3c63a101cc612
+oid sha256:cfafa4ed81be4ca2385537d5878755fb45dbb03e4792d704a6acc91fd4ee7e97
 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": 11.927906036376953,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.12569722680493361,
+  "best_metric": 11.926774978637695,
+  "best_model_checkpoint": "miner_id_24/checkpoint-75",
+  "epoch": 0.18854584020740042,
   "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": 197.706,
       "eval_steps_per_second": 51.404,
       "step": 50
+    },
+    {
+      "epoch": 0.1282111713410323,
+      "grad_norm": 0.05173062905669212,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 11.93,
+      "step": 51
+    },
+    {
+      "epoch": 0.13072511587713095,
+      "grad_norm": 0.05328970402479172,
+      "learning_rate": 3.082151762439293e-05,
+      "loss": 11.9296,
+      "step": 52
+    },
+    {
+      "epoch": 0.13323906041322964,
+      "grad_norm": 0.056689877063035965,
+      "learning_rate": 2.9189060364202943e-05,
+      "loss": 11.9302,
+      "step": 53
+    },
+    {
+      "epoch": 0.1357530049493283,
+      "grad_norm": 0.06390019506216049,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 11.9286,
+      "step": 54
+    },
+    {
+      "epoch": 0.13826694948542698,
+      "grad_norm": 0.06817812472581863,
+      "learning_rate": 2.6074557564105727e-05,
+      "loss": 11.9289,
+      "step": 55
+    },
+    {
+      "epoch": 0.14078089402152566,
+      "grad_norm": 0.05301738157868385,
+      "learning_rate": 2.459844065729529e-05,
+      "loss": 11.9298,
+      "step": 56
+    },
+    {
+      "epoch": 0.14329483855762432,
+      "grad_norm": 0.059947434812784195,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 11.9289,
+      "step": 57
+    },
+    {
+      "epoch": 0.145808783093723,
+      "grad_norm": 0.07889833301305771,
+      "learning_rate": 2.1822519843544424e-05,
+      "loss": 11.9266,
+      "step": 58
+    },
+    {
+      "epoch": 0.14832272762982165,
+      "grad_norm": 0.06598637998104095,
+      "learning_rate": 2.0528000059645997e-05,
+      "loss": 11.9268,
+      "step": 59
+    },
+    {
+      "epoch": 0.15083667216592034,
+      "grad_norm": 0.08608434349298477,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 11.9247,
+      "step": 60
+    },
+    {
+      "epoch": 0.15335061670201902,
+      "grad_norm": 0.10251203924417496,
+      "learning_rate": 1.8138158006995364e-05,
+      "loss": 11.9256,
+      "step": 61
+    },
+    {
+      "epoch": 0.15586456123811768,
+      "grad_norm": 0.0993577390909195,
+      "learning_rate": 1.7047384938420154e-05,
+      "loss": 11.9241,
+      "step": 62
+    },
+    {
+      "epoch": 0.15837850577421636,
+      "grad_norm": 0.07237444818019867,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 11.9288,
+      "step": 63
+    },
+    {
+      "epoch": 0.16089245031031502,
+      "grad_norm": 0.05976445600390434,
+      "learning_rate": 1.5084512506980026e-05,
+      "loss": 11.9289,
+      "step": 64
+    },
+    {
+      "epoch": 0.1634063948464137,
+      "grad_norm": 0.06411750614643097,
+      "learning_rate": 1.4216149583350754e-05,
+      "loss": 11.9291,
+      "step": 65
+    },
+    {
+      "epoch": 0.16592033938251238,
+      "grad_norm": 0.0686773806810379,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 11.9287,
+      "step": 66
+    },
+    {
+      "epoch": 0.16843428391861104,
+      "grad_norm": 0.06071595102548599,
+      "learning_rate": 1.2713832064634126e-05,
+      "loss": 11.9295,
+      "step": 67
+    },
+    {
+      "epoch": 0.17094822845470972,
+      "grad_norm": 0.06004241108894348,
+      "learning_rate": 1.2082737216329794e-05,
+      "loss": 11.9284,
+      "step": 68
+    },
+    {
+      "epoch": 0.17346217299080838,
+      "grad_norm": 0.07173370569944382,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 11.9266,
+      "step": 69
+    },
+    {
+      "epoch": 0.17597611752690706,
+      "grad_norm": 0.06722280383110046,
+      "learning_rate": 1.1066679679603e-05,
+      "loss": 11.9268,
+      "step": 70
+    },
+    {
+      "epoch": 0.17849006206300574,
+      "grad_norm": 0.07276538014411926,
+      "learning_rate": 1.0683651114450641e-05,
+      "loss": 11.9266,
+      "step": 71
+    },
+    {
+      "epoch": 0.1810040065991044,
+      "grad_norm": 0.08135631680488586,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 11.9252,
+      "step": 72
+    },
+    {
+      "epoch": 0.18351795113520308,
+      "grad_norm": 0.11169477552175522,
+      "learning_rate": 1.017123858587145e-05,
+      "loss": 11.9248,
+      "step": 73
+    },
+    {
+      "epoch": 0.18603189567130174,
+      "grad_norm": 0.12029822915792465,
+      "learning_rate": 1.00428300288164e-05,
+      "loss": 11.9263,
+      "step": 74
+    },
+    {
+      "epoch": 0.18854584020740042,
+      "grad_norm": 0.15942874550819397,
+      "learning_rate": 1e-05,
+      "loss": 11.9266,
+      "step": 75
+    },
+    {
+      "epoch": 0.18854584020740042,
+      "eval_loss": 11.926774978637695,
+      "eval_runtime": 0.2466,
+      "eval_samples_per_second": 202.779,
+      "eval_steps_per_second": 52.723,
+      "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": 1042494259200.0,
+  "total_flos": 1563741388800.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null