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:e4f2e06f7b039976fc75df11142a1eceb6cd2f24db71c183879c42ac8f75e50d
+oid sha256:def1a51a308008829acbcdb0f385a2bc1d5565085f04593338bde30384faade0
 size 48552

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52c9bdf55e4ab322f074855d7832562a3dea7bf8a975330f34c34ce5ede432bb
+oid sha256:460fde84ee226f3d4a07bcd0732ce5e161a0a01df3e9be73d5298b4a87e80bd3
 size 113994

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29b60a19ed07327340e89c4cb2549ca22cbe049e758c4f1dbca79b88554e6dab
+oid sha256:9858fd98e669f0ca689f61f793b4b19851ed430df3dce9f6065f95a97dcfb0ab
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7ce98f853005751c467c733cd6172bca52c1651e435d66348ed7743cfb3f18b
+oid sha256:0b23ab703604fdd5bf3efa3688c186ecc0ed68fe7dce07dc788e5d6483bafbd3
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd9145236fb8777a05d0c70f7e959af256e266b6622a198fb59384cb946e1eb6
+oid sha256:2608e2e0fb7ac69593bc4e5ec5d85c55ff857e9d9c49427071665cd1cd468ebc
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a033f311926773e95431c59bc355ee81ee35a2f05e05339a21febec83f14e50
+oid sha256:29edb0290ab9a3d774de5d5527b49f700e9fc1cab3a7771a5f30228d8960cd7c
 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": 11.927395820617676,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.028310566919102553,
+  "best_metric": 11.925982475280762,
+  "best_model_checkpoint": "miner_id_24/checkpoint-75",
+  "epoch": 0.04246585037865383,
   "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": 290.181,
       "eval_steps_per_second": 75.447,
       "step": 50
+    },
+    {
+      "epoch": 0.028876778257484605,
+      "grad_norm": 0.019224930554628372,
+      "learning_rate": 5.192909139858981e-05,
+      "loss": 11.9278,
+      "step": 51
+    },
+    {
+      "epoch": 0.029442989595866657,
+      "grad_norm": 0.025018585845828056,
+      "learning_rate": 5.0398113297608465e-05,
+      "loss": 11.9295,
+      "step": 52
+    },
+    {
+      "epoch": 0.03000920093424871,
+      "grad_norm": 0.02429080568253994,
+      "learning_rate": 4.887250079066892e-05,
+      "loss": 11.9275,
+      "step": 53
+    },
+    {
+      "epoch": 0.030575412272630758,
+      "grad_norm": 0.024529896676540375,
+      "learning_rate": 4.7354032673710005e-05,
+      "loss": 11.9274,
+      "step": 54
+    },
+    {
+      "epoch": 0.03114162361101281,
+      "grad_norm": 0.027298960834741592,
+      "learning_rate": 4.584447941263149e-05,
+      "loss": 11.9275,
+      "step": 55
+    },
+    {
+      "epoch": 0.03170783494939486,
+      "grad_norm": 0.028562380000948906,
+      "learning_rate": 4.43456010790099e-05,
+      "loss": 11.9283,
+      "step": 56
+    },
+    {
+      "epoch": 0.032274046287776914,
+      "grad_norm": 0.03158874437212944,
+      "learning_rate": 4.285914529793391e-05,
+      "loss": 11.9261,
+      "step": 57
+    },
+    {
+      "epoch": 0.03284025762615896,
+      "grad_norm": 0.027021652087569237,
+      "learning_rate": 4.13868452103516e-05,
+      "loss": 11.9292,
+      "step": 58
+    },
+    {
+      "epoch": 0.03340646896454102,
+      "grad_norm": 0.030148476362228394,
+      "learning_rate": 3.9930417452305626e-05,
+      "loss": 11.9276,
+      "step": 59
+    },
+    {
+      "epoch": 0.03397268030292307,
+      "grad_norm": 0.03393995761871338,
+      "learning_rate": 3.8491560153412466e-05,
+      "loss": 11.9276,
+      "step": 60
+    },
+    {
+      "epoch": 0.034538891641305115,
+      "grad_norm": 0.03766351938247681,
+      "learning_rate": 3.707195095691913e-05,
+      "loss": 11.9288,
+      "step": 61
+    },
+    {
+      "epoch": 0.03510510297968717,
+      "grad_norm": 0.04133583977818489,
+      "learning_rate": 3.567324506364632e-05,
+      "loss": 11.9268,
+      "step": 62
+    },
+    {
+      "epoch": 0.03567131431806922,
+      "grad_norm": 0.027467934414744377,
+      "learning_rate": 3.4297073302098156e-05,
+      "loss": 11.9259,
+      "step": 63
+    },
+    {
+      "epoch": 0.03623752565645127,
+      "grad_norm": 0.027041316032409668,
+      "learning_rate": 3.2945040226989244e-05,
+      "loss": 11.9287,
+      "step": 64
+    },
+    {
+      "epoch": 0.03680373699483332,
+      "grad_norm": 0.0271934624761343,
+      "learning_rate": 3.16187222484055e-05,
+      "loss": 11.9281,
+      "step": 65
+    },
+    {
+      "epoch": 0.03736994833321537,
+      "grad_norm": 0.027144378051161766,
+      "learning_rate": 3.0319665793780648e-05,
+      "loss": 11.9272,
+      "step": 66
+    },
+    {
+      "epoch": 0.03793615967159742,
+      "grad_norm": 0.03089400939643383,
+      "learning_rate": 2.9049385504830985e-05,
+      "loss": 11.9273,
+      "step": 67
+    },
+    {
+      "epoch": 0.038502371009979476,
+      "grad_norm": 0.03256877884268761,
+      "learning_rate": 2.7809362471550748e-05,
+      "loss": 11.9265,
+      "step": 68
+    },
+    {
+      "epoch": 0.039068582348361525,
+      "grad_norm": 0.037180133163928986,
+      "learning_rate": 2.660104250532764e-05,
+      "loss": 11.9273,
+      "step": 69
+    },
+    {
+      "epoch": 0.03963479368674358,
+      "grad_norm": 0.03133248910307884,
+      "learning_rate": 2.5425834453191232e-05,
+      "loss": 11.9266,
+      "step": 70
+    },
+    {
+      "epoch": 0.04020100502512563,
+      "grad_norm": 0.036548782140016556,
+      "learning_rate": 2.4285108555160577e-05,
+      "loss": 11.928,
+      "step": 71
+    },
+    {
+      "epoch": 0.04076721636350768,
+      "grad_norm": 0.04202922433614731,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 11.929,
+      "step": 72
+    },
+    {
+      "epoch": 0.04133342770188973,
+      "grad_norm": 0.03880568593740463,
+      "learning_rate": 2.2112381607484417e-05,
+      "loss": 11.9272,
+      "step": 73
+    },
+    {
+      "epoch": 0.04189963904027178,
+      "grad_norm": 0.04478525370359421,
+      "learning_rate": 2.1082913860268765e-05,
+      "loss": 11.9271,
+      "step": 74
+    },
+    {
+      "epoch": 0.04246585037865383,
+      "grad_norm": 0.05667252466082573,
+      "learning_rate": 2.0092991918301108e-05,
+      "loss": 11.9239,
+      "step": 75
+    },
+    {
+      "epoch": 0.04246585037865383,
+      "eval_loss": 11.925982475280762,
+      "eval_runtime": 0.174,
+      "eval_samples_per_second": 287.402,
+      "eval_steps_per_second": 74.725,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -409,7 +592,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1042494259200.0,
+  "total_flos": 1563741388800.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null