Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b8c30c6fcaa6ae63de91c6e6df0139440502164b00e6db8ba39a36bb5c8d22a
+oid sha256:aa26d9690acae831c95e9d0aaa0418c78a2b7b792257f90ac99b1f6bd88dfbe8
 size 70430032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e730c1d55dbf75be069dfbbda3ae59a352d4614078658e864f9d2bd0dc5e542b
+oid sha256:2885f8ffca668ca9e216c1bb7af1cee03638a395a27721d9c05bf0a06af845db
 size 141053442

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96203bc20319d22c2e28e2b03d87fad33af8e293abdb25f32eda01806707c935
+oid sha256:dceab4046c227d3598b46370e242ac139e7f40b3e24487dd364077928d320ae3
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc2621bd200b83fd70c2bcd884adac53474206783140d8b69f86c83aef50a760
+oid sha256:aa2df0a512ea1dc37c55c4e72f7f701cac86fa563ada24e91c4921738c3802d0
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ffe33115338b95dfc559f1f59d9f94085dccddc4ee9689e8bc239b1944c0a33
+oid sha256:46b8a69a87da9436e2e1130e5c8e11a68e2389d2e599bc3fc2178df956c544d9
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39fd3a5b4d46143a5d46e76fd8781e41b7f94e5f74e6ab9431b828c7f82c1764
+oid sha256:74c10c597b76b3a9e50c72912b3285d5fbd773c5306014380e7c8f07ee17db03
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5eda964d5b06109c7ff637060199d72e397eeb7027b50e10972a323edbe81312
+oid sha256:fb0ce41087f0939d63a9a6eb297660d82f62bda022868309a8c97328e5da41a5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.5558741092681885,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.32666394446712943,
+  "best_metric": 0.3033914864063263,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.6533278889342589,
   "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": 32.364,
       "eval_steps_per_second": 8.415,
       "step": 25
+    },
+    {
+      "epoch": 0.33973050224581464,
+      "grad_norm": 1.975691318511963,
+      "learning_rate": 7.917848237560709e-05,
+      "loss": 0.5943,
+      "step": 26
+    },
+    {
+      "epoch": 0.3527970600244998,
+      "grad_norm": 1.5834639072418213,
+      "learning_rate": 7.75e-05,
+      "loss": 0.5643,
+      "step": 27
+    },
+    {
+      "epoch": 0.365863617803185,
+      "grad_norm": 1.6365801095962524,
+      "learning_rate": 7.577868759557654e-05,
+      "loss": 0.4526,
+      "step": 28
+    },
+    {
+      "epoch": 0.37893017558187014,
+      "grad_norm": 1.463999629020691,
+      "learning_rate": 7.401782177833148e-05,
+      "loss": 0.4972,
+      "step": 29
+    },
+    {
+      "epoch": 0.39199673336055535,
+      "grad_norm": 1.2677172422409058,
+      "learning_rate": 7.222075445642904e-05,
+      "loss": 0.5389,
+      "step": 30
+    },
+    {
+      "epoch": 0.4050632911392405,
+      "grad_norm": 2.432539224624634,
+      "learning_rate": 7.03909064496551e-05,
+      "loss": 0.4597,
+      "step": 31
+    },
+    {
+      "epoch": 0.4181298489179257,
+      "grad_norm": 2.4917757511138916,
+      "learning_rate": 6.853176097769229e-05,
+      "loss": 0.4929,
+      "step": 32
+    },
+    {
+      "epoch": 0.43119640669661086,
+      "grad_norm": 1.3739546537399292,
+      "learning_rate": 6.664685702961344e-05,
+      "loss": 0.9248,
+      "step": 33
+    },
+    {
+      "epoch": 0.44426296447529606,
+      "grad_norm": 1.6721895933151245,
+      "learning_rate": 6.473978262721463e-05,
+      "loss": 0.6351,
+      "step": 34
+    },
+    {
+      "epoch": 0.4573295222539812,
+      "grad_norm": 1.3729504346847534,
+      "learning_rate": 6.281416799501188e-05,
+      "loss": 0.5844,
+      "step": 35
+    },
+    {
+      "epoch": 0.4703960800326664,
+      "grad_norm": 1.3768748044967651,
+      "learning_rate": 6.087367864990233e-05,
+      "loss": 0.6757,
+      "step": 36
+    },
+    {
+      "epoch": 0.48346263781135157,
+      "grad_norm": 2.0230472087860107,
+      "learning_rate": 5.8922008423644624e-05,
+      "loss": 1.0381,
+      "step": 37
+    },
+    {
+      "epoch": 0.4965291955900368,
+      "grad_norm": 1.3043603897094727,
+      "learning_rate": 5.696287243144013e-05,
+      "loss": 0.4569,
+      "step": 38
+    },
+    {
+      "epoch": 0.509595753368722,
+      "grad_norm": 0.9272847175598145,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.4936,
+      "step": 39
+    },
+    {
+      "epoch": 0.5226623111474071,
+      "grad_norm": 1.6384899616241455,
+      "learning_rate": 5.303712756855988e-05,
+      "loss": 0.4535,
+      "step": 40
+    },
+    {
+      "epoch": 0.5357288689260923,
+      "grad_norm": 1.546187400817871,
+      "learning_rate": 5.107799157635538e-05,
+      "loss": 0.3763,
+      "step": 41
+    },
+    {
+      "epoch": 0.5487954267047774,
+      "grad_norm": 1.2767608165740967,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.4207,
+      "step": 42
+    },
+    {
+      "epoch": 0.5618619844834626,
+      "grad_norm": 1.1065655946731567,
+      "learning_rate": 4.718583200498814e-05,
+      "loss": 0.3935,
+      "step": 43
+    },
+    {
+      "epoch": 0.5749285422621478,
+      "grad_norm": 2.4505350589752197,
+      "learning_rate": 4.526021737278538e-05,
+      "loss": 0.2702,
+      "step": 44
+    },
+    {
+      "epoch": 0.587995100040833,
+      "grad_norm": 1.1374635696411133,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.6616,
+      "step": 45
+    },
+    {
+      "epoch": 0.6010616578195181,
+      "grad_norm": 1.3470594882965088,
+      "learning_rate": 4.146823902230772e-05,
+      "loss": 0.7169,
+      "step": 46
+    },
+    {
+      "epoch": 0.6141282155982033,
+      "grad_norm": 1.4238591194152832,
+      "learning_rate": 3.960909355034491e-05,
+      "loss": 0.4089,
+      "step": 47
+    },
+    {
+      "epoch": 0.6271947733768886,
+      "grad_norm": 1.1624187231063843,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.5297,
+      "step": 48
+    },
+    {
+      "epoch": 0.6402613311555737,
+      "grad_norm": 1.2812923192977905,
+      "learning_rate": 3.598217822166854e-05,
+      "loss": 0.5576,
+      "step": 49
+    },
+    {
+      "epoch": 0.6533278889342589,
+      "grad_norm": 3.029040575027466,
+      "learning_rate": 3.422131240442349e-05,
+      "loss": 0.9427,
+      "step": 50
+    },
+    {
+      "epoch": 0.6533278889342589,
+      "eval_loss": 0.3033914864063263,
+      "eval_runtime": 1.537,
+      "eval_samples_per_second": 32.532,
+      "eval_steps_per_second": 8.458,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -226,7 +409,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.47650456322048e+16,
+  "total_flos": 2.95300912644096e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null