Training in progress, step 95, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9557cb894adec00be02d9818be5443d40ee978747e3b97b860f5995a3d7a38a
+oid sha256:de020aec0402fc571942660d5064453b2b2d3d10473170a35f45d0bdd564f577
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d10bb0ee6b7204907de663f12e513153570397209855b6fdbb8b4b7cb57bf40
+oid sha256:f296447dc712cd8381c00da5d004ddb5dda8aced0f465e60fa6fb2e0c673826c
 size 212298

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b82663215514d2e15e138bd5f29cc14a027613fadf5ec71d5efb38b975dd0ed
+oid sha256:a9436b1a9ca74e57e27525024f8ac8793e48e7a6c569a57636bed6f667398943
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8df72f092075a52322208049c03f4b09cc9f34969610024acd4dbbce4825748
+oid sha256:47b29d9e86310c1aa57b9cd4977d6293e8829df1d170e34383d8789062ab16ec
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:051c0f2a65f962c7ac612cd6d98aea8a58f1c2488407511d82a87a1e624f3e95
+oid sha256:acb3fc8efa286017667a3525f78d7b9792ac6dce142c561c4261ea8485112d89
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7322c1e75872ff8babcdb0f085ede43acec91dddbc0972f496bf5275436824db
+oid sha256:a8e9a7ae6751deff3fa8faa5c7235343b9e7f1c2f195da9eda59ff789f7f1669
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5b53655d80c3ade692dacae57cafa4aff84c325b5cb8d0fba89d01b50d41566
+oid sha256:1fd9769bcb04586b7ead175b588f12a0bbbeba72d5f308b868ba8f36b77aa801
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 10.12276840209961,
   "best_model_checkpoint": "miner_id_24/checkpoint-75",
-  "epoch": 0.061949872228388526,
+  "epoch": 0.0784698381559588,
   "eval_steps": 25,
-  "global_step": 75,
+  "global_step": 95,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -564,6 +564,146 @@
       "eval_samples_per_second": 624.742,
       "eval_steps_per_second": 162.433,
       "step": 75
+    },
+    {
+      "epoch": 0.06277587052476705,
+      "grad_norm": 0.5765253901481628,
+      "learning_rate": 1.91437699862843e-05,
+      "loss": 10.1609,
+      "step": 76
+    },
+    {
+      "epoch": 0.06360186882114556,
+      "grad_norm": 0.5583258271217346,
+      "learning_rate": 1.8236354814530112e-05,
+      "loss": 10.1337,
+      "step": 77
+    },
+    {
+      "epoch": 0.06442786711752407,
+      "grad_norm": 0.5325179696083069,
+      "learning_rate": 1.7371804408538024e-05,
+      "loss": 10.1365,
+      "step": 78
+    },
+    {
+      "epoch": 0.06525386541390259,
+      "grad_norm": 0.5995349884033203,
+      "learning_rate": 1.6551126795408016e-05,
+      "loss": 10.1319,
+      "step": 79
+    },
+    {
+      "epoch": 0.0660798637102811,
+      "grad_norm": 0.596726655960083,
+      "learning_rate": 1.577527884852619e-05,
+      "loss": 10.1265,
+      "step": 80
+    },
+    {
+      "epoch": 0.06690586200665961,
+      "grad_norm": 0.574684202671051,
+      "learning_rate": 1.5045165171893116e-05,
+      "loss": 10.1292,
+      "step": 81
+    },
+    {
+      "epoch": 0.06773186030303813,
+      "grad_norm": 0.5674662590026855,
+      "learning_rate": 1.4361637045396029e-05,
+      "loss": 10.1308,
+      "step": 82
+    },
+    {
+      "epoch": 0.06855785859941664,
+      "grad_norm": 0.6809078454971313,
+      "learning_rate": 1.3725491432254624e-05,
+      "loss": 10.12,
+      "step": 83
+    },
+    {
+      "epoch": 0.06938385689579515,
+      "grad_norm": 0.5955153703689575,
+      "learning_rate": 1.313747004979751e-05,
+      "loss": 10.1294,
+      "step": 84
+    },
+    {
+      "epoch": 0.07020985519217367,
+      "grad_norm": 0.6445745825767517,
+      "learning_rate": 1.2598258504653081e-05,
+      "loss": 10.1313,
+      "step": 85
+    },
+    {
+      "epoch": 0.07103585348855218,
+      "grad_norm": 0.611798107624054,
+      "learning_rate": 1.2108485493362765e-05,
+      "loss": 10.1273,
+      "step": 86
+    },
+    {
+      "epoch": 0.0718618517849307,
+      "grad_norm": 0.5751798152923584,
+      "learning_rate": 1.1668722069349041e-05,
+      "loss": 10.1307,
+      "step": 87
+    },
+    {
+      "epoch": 0.07268785008130921,
+      "grad_norm": 0.5628722310066223,
+      "learning_rate": 1.1279480977092635e-05,
+      "loss": 10.1329,
+      "step": 88
+    },
+    {
+      "epoch": 0.07351384837768772,
+      "grad_norm": 0.6203532814979553,
+      "learning_rate": 1.094121605429547e-05,
+      "loss": 10.125,
+      "step": 89
+    },
+    {
+      "epoch": 0.07433984667406623,
+      "grad_norm": 0.6454430818557739,
+      "learning_rate": 1.0654321702726141e-05,
+      "loss": 10.1345,
+      "step": 90
+    },
+    {
+      "epoch": 0.07516584497044475,
+      "grad_norm": 0.6020610928535461,
+      "learning_rate": 1.0419132428365116e-05,
+      "loss": 10.1286,
+      "step": 91
+    },
+    {
+      "epoch": 0.07599184326682326,
+      "grad_norm": 0.6609290242195129,
+      "learning_rate": 1.0235922451385733e-05,
+      "loss": 10.1331,
+      "step": 92
+    },
+    {
+      "epoch": 0.07681784156320177,
+      "grad_norm": 0.6074327230453491,
+      "learning_rate": 1.0104905386425733e-05,
+      "loss": 10.1268,
+      "step": 93
+    },
+    {
+      "epoch": 0.07764383985958029,
+      "grad_norm": 0.5935200452804565,
+      "learning_rate": 1.002623399352217e-05,
+      "loss": 10.1335,
+      "step": 94
+    },
+    {
+      "epoch": 0.0784698381559588,
+      "grad_norm": 0.6691338419914246,
+      "learning_rate": 1e-05,
+      "loss": 10.1336,
+      "step": 95
     }
   ],
   "logging_steps": 1,
@@ -587,12 +727,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 64152089395200.0,
+  "total_flos": 81259313233920.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null