Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2499173ca9627ea8d47157d85ba483690a1ada977809f7bbbb36b6e77b0d66db
+oid sha256:a0e37d48b591f0fa2abbaebf2458c1b70bc3713d02dd32e6f2d9a673911c7c02
 size 78207176

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f16ccb35941229e08d71ee4e53936c232d1eb36c8e82568bcb01662a13983f2d
+oid sha256:a07ccf07ac65a216d13e71c319644813b0144eb67709fcf862f886209f6c145d
 size 40177764

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:331a62d0e9a334aa77de1efe3dc1a910e9e59b6e241d5b946ccc99fff34c3fc0
+oid sha256:83b0dc76f150db82fe47abf0879fc1b926557eed62d77835e12b4774bd405020
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb15fdd4c0ab874f4afa0ea95fae119cbc74554df5fbe92ab825fe27063eaa04
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.4904130697250366,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.016302575806977502,
+  "best_metric": 1.4647512435913086,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.032605151613955004,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 120.604,
       "eval_steps_per_second": 15.081,
       "step": 25
+    },
+    {
+      "epoch": 0.016954678839256603,
+      "grad_norm": 0.2123045027256012,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 1.3638,
+      "step": 26
+    },
+    {
+      "epoch": 0.017606781871535703,
+      "grad_norm": 0.19667382538318634,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 1.4593,
+      "step": 27
+    },
+    {
+      "epoch": 0.018258884903814804,
+      "grad_norm": 0.21623675525188446,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 1.3836,
+      "step": 28
+    },
+    {
+      "epoch": 0.018910987936093904,
+      "grad_norm": 0.2061716467142105,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 1.5142,
+      "step": 29
+    },
+    {
+      "epoch": 0.019563090968373,
+      "grad_norm": 0.21938467025756836,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 1.4625,
+      "step": 30
+    },
+    {
+      "epoch": 0.020215194000652102,
+      "grad_norm": 0.22383436560630798,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 1.4316,
+      "step": 31
+    },
+    {
+      "epoch": 0.020867297032931203,
+      "grad_norm": 0.21363838016986847,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 1.5011,
+      "step": 32
+    },
+    {
+      "epoch": 0.021519400065210303,
+      "grad_norm": 0.23454470932483673,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 1.4714,
+      "step": 33
+    },
+    {
+      "epoch": 0.022171503097489404,
+      "grad_norm": 0.2438150942325592,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 1.4566,
+      "step": 34
+    },
+    {
+      "epoch": 0.022823606129768505,
+      "grad_norm": 0.24382317066192627,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.394,
+      "step": 35
+    },
+    {
+      "epoch": 0.023475709162047602,
+      "grad_norm": 0.26105523109436035,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 1.5844,
+      "step": 36
+    },
+    {
+      "epoch": 0.024127812194326703,
+      "grad_norm": 0.25343576073646545,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 1.5326,
+      "step": 37
+    },
+    {
+      "epoch": 0.024779915226605803,
+      "grad_norm": 0.2793176472187042,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 1.4606,
+      "step": 38
+    },
+    {
+      "epoch": 0.025432018258884904,
+      "grad_norm": 0.2861690819263458,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 1.5886,
+      "step": 39
+    },
+    {
+      "epoch": 0.026084121291164004,
+      "grad_norm": 0.3055659532546997,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 1.6292,
+      "step": 40
+    },
+    {
+      "epoch": 0.026736224323443105,
+      "grad_norm": 0.3592061698436737,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.6955,
+      "step": 41
+    },
+    {
+      "epoch": 0.027388327355722206,
+      "grad_norm": 0.3756411373615265,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 1.6397,
+      "step": 42
+    },
+    {
+      "epoch": 0.028040430388001303,
+      "grad_norm": 0.3495422303676605,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 1.4516,
+      "step": 43
+    },
+    {
+      "epoch": 0.028692533420280403,
+      "grad_norm": 0.41340503096580505,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 1.7137,
+      "step": 44
+    },
+    {
+      "epoch": 0.029344636452559504,
+      "grad_norm": 0.46326860785484314,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 1.6484,
+      "step": 45
+    },
+    {
+      "epoch": 0.029996739484838605,
+      "grad_norm": 0.44499802589416504,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 1.6504,
+      "step": 46
+    },
+    {
+      "epoch": 0.030648842517117705,
+      "grad_norm": 0.5560527443885803,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 1.7462,
+      "step": 47
+    },
+    {
+      "epoch": 0.0313009455493968,
+      "grad_norm": 0.609457790851593,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 1.7769,
+      "step": 48
+    },
+    {
+      "epoch": 0.03195304858167591,
+      "grad_norm": 0.597760021686554,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 1.9396,
+      "step": 49
+    },
+    {
+      "epoch": 0.032605151613955004,
+      "grad_norm": 0.8746095895767212,
+      "learning_rate": 0.0,
+      "loss": 2.2609,
+      "step": 50
+    },
+    {
+      "epoch": 0.032605151613955004,
+      "eval_loss": 1.4647512435913086,
+      "eval_runtime": 21.4373,
+      "eval_samples_per_second": 120.491,
+      "eval_steps_per_second": 15.067,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 605683131088896.0,
+  "total_flos": 914705136746496.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null