Training in progress, step 360, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8bcebe942c9a8b99ef56e2c5446f9da9d60e5a25fc8214a7efdd1e72a32d1e8
+oid sha256:145c54eac1ed297a2be387fb3da1ca50f3997b3a4ad127c5ef0a43dbc2b62306
 size 80792880

last-checkpoint/global_step360/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37321759e325e8f28673e9f84f6c30337b948e8504dcc735f2ea68ac33fc875a
+size 50635184

last-checkpoint/global_step360/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab46a061ba4255ab5eb5bf9538f1e050241474360869db22a40d322d051341ca
+size 50635248

last-checkpoint/global_step360/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cafea06a22eaea8301f18737cdaaad4292543e1aac3ac5467258b2e0f7fd110
+size 50635248

last-checkpoint/global_step360/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a501920a2f435e14830b91b8794ade47441ece0f291b92eea363012e9eaf5c54
+size 50635248

last-checkpoint/global_step360/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df26171df51686229492d5e3350890bc09c6eabfed73df3178d05a938d5edbbc
+size 81040172

last-checkpoint/latest

@@ -1 +1 @@
-global_step340
+global_step360

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9ee4edfcbe4b77ace2b87141b8bd957560ff5cf1e9769ddb40bc10245e61753
+oid sha256:2a6f1f4c8f24e0c563b224df07f972a9c03fd55885f468ac05d4936cb17a58f2
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1a8214cc5d40141141c8f71962d04bf800f999c32180dcd7ec3ae74c2cfd33a
+oid sha256:f53fbbfc6f98216ba3e33af1efdac4f926f502586f2aaf9e56b638c8ee8c6ad2
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cdcbe52a4efc157b4e1fec0014b1ef1c4a099e5954abc079e099fd3c7d5f7e77
+oid sha256:df243d851095642cd3b676fddc7012d10efdba379f7ecb37a141453a1d3a54dc
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ebda69adf36c903e083c2a9ebbd95cf2d544fccc910933692d5edd4959d5b9e
+oid sha256:a873ca510bfc78f1c5c1aee0fe58b28053e6be23007bbef3d27b40cf337bee9f
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15b9006a0f681367a429404e804cfe8e2e383020b17f445e8fea72a4879f60b6
+oid sha256:3fcd358d907eb48a96def3a4b1ad085129b5a2436573e5c22da7e483872863ef
 size 1064

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 330,
-  "best_metric": 0.5116480588912964,
-  "best_model_checkpoint": "miner_id_24/checkpoint-320",
-  "epoch": 0.06859333232460786,
+  "best_global_step": 360,
+  "best_metric": 0.5115170478820801,
+  "best_model_checkpoint": "miner_id_24/checkpoint-360",
+  "epoch": 0.07262823422605538,
   "eval_steps": 10,
-  "global_step": 340,
+  "global_step": 360,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -764,6 +764,50 @@
       "eval_samples_per_second": 7.829,
       "eval_steps_per_second": 0.49,
       "step": 340
+    },
+    {
+      "epoch": 0.06960205779996974,
+      "grad_norm": 0.14681710302829742,
+      "learning_rate": 4.179195491219353e-05,
+      "loss": 0.6052,
+      "step": 345
+    },
+    {
+      "epoch": 0.07061078327533162,
+      "grad_norm": 0.21438910067081451,
+      "learning_rate": 4.1552103789056286e-05,
+      "loss": 0.4697,
+      "step": 350
+    },
+    {
+      "epoch": 0.07061078327533162,
+      "eval_loss": 0.5133654475212097,
+      "eval_runtime": 1026.2871,
+      "eval_samples_per_second": 8.586,
+      "eval_steps_per_second": 0.537,
+      "step": 350
+    },
+    {
+      "epoch": 0.07161950875069349,
+      "grad_norm": 0.0766027569770813,
+      "learning_rate": 4.130950877214683e-05,
+      "loss": 0.3593,
+      "step": 355
+    },
+    {
+      "epoch": 0.07262823422605538,
+      "grad_norm": 0.09048033505678177,
+      "learning_rate": 4.106421007719631e-05,
+      "loss": 0.4417,
+      "step": 360
+    },
+    {
+      "epoch": 0.07262823422605538,
+      "eval_loss": 0.5115170478820801,
+      "eval_runtime": 817.5154,
+      "eval_samples_per_second": 10.779,
+      "eval_steps_per_second": 0.674,
+      "step": 360
     }
   ],
   "logging_steps": 5,
@@ -778,7 +822,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 0
       }
     },
     "TrainerControl": {
@@ -792,7 +836,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.901385200214999e+18,
+  "total_flos": 2.0132313884629402e+18,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null