Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f7d4159c4fb0f7150b60995f440691f165789ca10ef3fea70ded92482e2169a
+oid sha256:4a6f3ff017dc77866b77e93fdfcc9e8b83c2e9d63687db50140eaaa8d4b26b12
 size 432223744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6534424072e1693e872d05eb0791df7e935766e9f30ca3dacc03a35d71e60433
+oid sha256:2933b3dcca5c866f3985d430a79beb09ec25d3b288d8a2caba7cec68aa927c09
 size 864785974

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e944a2413c07a8a3b2bb11838743b1b12c3463e3b50822445acefc31d953023
+oid sha256:bcff768af514de73213c4367373d77e562b503656a0e86166d785b6aae178639
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5f11c345065950be5a402710d3e26a36cb47ec06109b159795f3911bb8777f3
+oid sha256:adc1809aacd748b3d97735b569d8d921f8e9651db8fc5b2290e30fac9bafdf2c
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddaf914f9600211365d89d848a14a787abe6a575b94b4abc8c6f84aa941a6a92
+oid sha256:3ae97f320f2cfb5bcf00923f5b5c4b9fa04b76bf235d69778c8c0385bbc33238
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3534b6255da9af0991427cdb9baba1fa554e04ee0656d504f623835dda04bd3
+oid sha256:c8ed8fcfee32cfd3c35333c367a0f8146d086ddfb44d492f9a5595ed82979197
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.6429993510246277,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.05466721333880006,
+  "best_metric": 0.6260138750076294,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.10933442667760011,
   "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": 17.044,
       "eval_steps_per_second": 2.135,
       "step": 25
+    },
+    {
+      "epoch": 0.05685390187235206,
+      "grad_norm": 0.16069209575653076,
+      "learning_rate": 5e-05,
+      "loss": 0.3299,
+      "step": 26
+    },
+    {
+      "epoch": 0.05904059040590406,
+      "grad_norm": 0.17538459599018097,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.5203,
+      "step": 27
+    },
+    {
+      "epoch": 0.061227278939456065,
+      "grad_norm": 0.1931326687335968,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.5735,
+      "step": 28
+    },
+    {
+      "epoch": 0.06341396747300806,
+      "grad_norm": 0.206190824508667,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.5574,
+      "step": 29
+    },
+    {
+      "epoch": 0.06560065600656007,
+      "grad_norm": 0.20361047983169556,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.5864,
+      "step": 30
+    },
+    {
+      "epoch": 0.06778734454011207,
+      "grad_norm": 0.24747894704341888,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.6423,
+      "step": 31
+    },
+    {
+      "epoch": 0.06997403307366407,
+      "grad_norm": 0.23271162807941437,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.6678,
+      "step": 32
+    },
+    {
+      "epoch": 0.07216072160721607,
+      "grad_norm": 0.24798904359340668,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.6408,
+      "step": 33
+    },
+    {
+      "epoch": 0.07434741014076808,
+      "grad_norm": 0.28206339478492737,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.6489,
+      "step": 34
+    },
+    {
+      "epoch": 0.07653409867432008,
+      "grad_norm": 0.33762359619140625,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.7041,
+      "step": 35
+    },
+    {
+      "epoch": 0.07872078720787208,
+      "grad_norm": 0.41767123341560364,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.7162,
+      "step": 36
+    },
+    {
+      "epoch": 0.08090747574142408,
+      "grad_norm": 0.4611891806125641,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.7631,
+      "step": 37
+    },
+    {
+      "epoch": 0.08309416427497608,
+      "grad_norm": 0.1755916178226471,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.3483,
+      "step": 38
+    },
+    {
+      "epoch": 0.08528085280852808,
+      "grad_norm": 0.15542787313461304,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.4641,
+      "step": 39
+    },
+    {
+      "epoch": 0.08746754134208008,
+      "grad_norm": 0.14870032668113708,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.5253,
+      "step": 40
+    },
+    {
+      "epoch": 0.0896542298756321,
+      "grad_norm": 0.15303368866443634,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.5764,
+      "step": 41
+    },
+    {
+      "epoch": 0.0918409184091841,
+      "grad_norm": 0.17057447135448456,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.6111,
+      "step": 42
+    },
+    {
+      "epoch": 0.0940276069427361,
+      "grad_norm": 0.1693965494632721,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.6094,
+      "step": 43
+    },
+    {
+      "epoch": 0.0962142954762881,
+      "grad_norm": 0.18184174597263336,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.6249,
+      "step": 44
+    },
+    {
+      "epoch": 0.0984009840098401,
+      "grad_norm": 0.23067162930965424,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.654,
+      "step": 45
+    },
+    {
+      "epoch": 0.1005876725433921,
+      "grad_norm": 0.25408676266670227,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.6695,
+      "step": 46
+    },
+    {
+      "epoch": 0.1027743610769441,
+      "grad_norm": 0.28090396523475647,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.6815,
+      "step": 47
+    },
+    {
+      "epoch": 0.1049610496104961,
+      "grad_norm": 0.38103654980659485,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.7202,
+      "step": 48
+    },
+    {
+      "epoch": 0.10714773814404811,
+      "grad_norm": 0.4314904510974884,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.7642,
+      "step": 49
+    },
+    {
+      "epoch": 0.10933442667760011,
+      "grad_norm": 0.5988128781318665,
+      "learning_rate": 0.0,
+      "loss": 0.7072,
+      "step": 50
+    },
+    {
+      "epoch": 0.10933442667760011,
+      "eval_loss": 0.6260138750076294,
+      "eval_runtime": 181.3493,
+      "eval_samples_per_second": 16.989,
+      "eval_steps_per_second": 2.128,
+      "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": 3.4068723732054016e+17,
+  "total_flos": 6.813744746410803e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null