Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:662318c91e572b87fadc5148026ce17de34e7c5aa881599b8ddec923e8bb1582
+oid sha256:4a53ffcafe283cfb96ebce6f494e6aea37fb020f3bdd59cf2c55a48182428c5c
 size 550593184

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61572b99f1c672ca0f3909d647c91d5154216fd49d60cd0978f5175763de10e8
+oid sha256:db225a47e2bfb895a68b8e783e233cf8210220694dddcf1467b1c82878c2ff51
 size 1101572914

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7e8fcdab80ebfc3bb4d9d0fb450ae4b144e64d4b2987d4f7437f483865c7658
+oid sha256:f65ed51fdd838da849a99e59d71926d82e35c841ce4ebdac03d5f9170ac4245a
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:213635b15f6a9a03386a6603ee80e65bc4588f29b30f9060b14564807efd5237
+oid sha256:57af3a3a18f5600ed8df22e69a69704e2d6587a6a627cf04cedcbac5c8d20a85
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:122fb75297e6a6e8a398470d8c4cd95b13acebf9a279c1f67cd9ccf50208ec23
+oid sha256:5a5128d62c0aadce7f1d28fbc736c31298ad12bee610acfa6503dea5f4849010
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be61edcba9440eb58f59b331fa8a76f5f1f7bfc8a48f083dc4d0525e0dc4c8d7
+oid sha256:3a465bde1665f111b6894bd3a694eae678028aec4557d28d784c8940916bd7cd
 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": 0.22263145446777344,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.27952480782669464,
+  "best_metric": 0.09452027827501297,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.5590496156533893,
   "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": 8.659,
       "eval_steps_per_second": 1.091,
       "step": 25
+    },
+    {
+      "epoch": 0.2907058001397624,
+      "grad_norm": 5.87585973739624,
+      "learning_rate": 5e-05,
+      "loss": 0.5248,
+      "step": 26
+    },
+    {
+      "epoch": 0.3018867924528302,
+      "grad_norm": 4.513538360595703,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.3769,
+      "step": 27
+    },
+    {
+      "epoch": 0.31306778476589797,
+      "grad_norm": 2.861530065536499,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.2658,
+      "step": 28
+    },
+    {
+      "epoch": 0.32424877707896577,
+      "grad_norm": 0.7928971648216248,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.1659,
+      "step": 29
+    },
+    {
+      "epoch": 0.33542976939203356,
+      "grad_norm": 1.8722455501556396,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.1067,
+      "step": 30
+    },
+    {
+      "epoch": 0.3466107617051013,
+      "grad_norm": 2.7152228355407715,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.1319,
+      "step": 31
+    },
+    {
+      "epoch": 0.3577917540181691,
+      "grad_norm": 2.2692229747772217,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.1242,
+      "step": 32
+    },
+    {
+      "epoch": 0.3689727463312369,
+      "grad_norm": 0.5245362520217896,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.0629,
+      "step": 33
+    },
+    {
+      "epoch": 0.3801537386443047,
+      "grad_norm": 1.132564902305603,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0908,
+      "step": 34
+    },
+    {
+      "epoch": 0.3913347309573725,
+      "grad_norm": 1.2288964986801147,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.0981,
+      "step": 35
+    },
+    {
+      "epoch": 0.4025157232704403,
+      "grad_norm": 0.7781267762184143,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.0663,
+      "step": 36
+    },
+    {
+      "epoch": 0.413696715583508,
+      "grad_norm": 0.3532390892505646,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.0344,
+      "step": 37
+    },
+    {
+      "epoch": 0.4248777078965758,
+      "grad_norm": 0.6690967082977295,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.1157,
+      "step": 38
+    },
+    {
+      "epoch": 0.4360587002096436,
+      "grad_norm": 1.3647629022598267,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.2326,
+      "step": 39
+    },
+    {
+      "epoch": 0.4472396925227114,
+      "grad_norm": 0.9862391948699951,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.1719,
+      "step": 40
+    },
+    {
+      "epoch": 0.4584206848357792,
+      "grad_norm": 1.4872350692749023,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.1551,
+      "step": 41
+    },
+    {
+      "epoch": 0.469601677148847,
+      "grad_norm": 1.287073016166687,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.1289,
+      "step": 42
+    },
+    {
+      "epoch": 0.4807826694619147,
+      "grad_norm": 0.897722601890564,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.0894,
+      "step": 43
+    },
+    {
+      "epoch": 0.4919636617749825,
+      "grad_norm": 0.5648239850997925,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0794,
+      "step": 44
+    },
+    {
+      "epoch": 0.5031446540880503,
+      "grad_norm": 0.7147127389907837,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.0481,
+      "step": 45
+    },
+    {
+      "epoch": 0.5143256464011181,
+      "grad_norm": 0.3847064971923828,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.0593,
+      "step": 46
+    },
+    {
+      "epoch": 0.5255066387141859,
+      "grad_norm": 0.7142338752746582,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.0618,
+      "step": 47
+    },
+    {
+      "epoch": 0.5366876310272537,
+      "grad_norm": 0.399740070104599,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.0515,
+      "step": 48
+    },
+    {
+      "epoch": 0.5478686233403215,
+      "grad_norm": 1.3028299808502197,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.0517,
+      "step": 49
+    },
+    {
+      "epoch": 0.5590496156533893,
+      "grad_norm": 2.2355709075927734,
+      "learning_rate": 0.0,
+      "loss": 0.0565,
+      "step": 50
+    },
+    {
+      "epoch": 0.5590496156533893,
+      "eval_loss": 0.09452027827501297,
+      "eval_runtime": 32.1913,
+      "eval_samples_per_second": 18.732,
+      "eval_steps_per_second": 2.361,
+      "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": 5.555785010511872e+17,
+  "total_flos": 1.1111570021023744e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null