Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9de9f26261a4859deb30baeda8dc4f22081adeeeec42a23940ed0c82b2189cc8
+oid sha256:ed6d91aeedd4d4e28d1164f4c0c3bd8b5ab0ec5f87f5e3cd66e4636e7982e507
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63a286cb9f950008bd1ec3bff91a9b6dc80993305c3d856ad9cf6bc42f4ca330
+oid sha256:98378691ffab601adcb040f192bf01d35ad928049d19fb4b41a6a628dd556f4f
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d9d491d834ffd9a92844cbf7ddda0d7caf4d9adad6558c3893bd18777e0a857
+oid sha256:3f73672f46ac4d93c91852a3d5d975f6a72e5d74155b74fad1b7fea4bb7db88a
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc5e453e686cf2d3ce0a6c7978f6412bf4011eac0c06b0998369e194965561fd
+oid sha256:f10feb7bb0469ecaa27aa3e664390a854e020caaac45b75c938afbb70699142c
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a240b9c5c547942858c59616c4cec7c88e74a339af7798d21a2b40c820f0fd5
+oid sha256:25ab94b2e6c5c211c54c59e0eeefaf43aad7436fa3b610c8bc6ddcff05a6f58a
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c567c5c27688f9e4971d9a93d7cdd2e3b9e63e5140f543af1db8f987d3942635
+oid sha256:e2b261d0830459a3e59c78afc13fdccae75022f2728717dd451e38f90cd9efc5
 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": 2.3048317432403564,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.025743338911056766,
+  "best_metric": 2.2921998500823975,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.05148667782211353,
   "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": 16.529,
       "eval_steps_per_second": 2.066,
       "step": 25
+    },
+    {
+      "epoch": 0.026773072467499034,
+      "grad_norm": 0.19370198249816895,
+      "learning_rate": 5e-05,
+      "loss": 2.1976,
+      "step": 26
+    },
+    {
+      "epoch": 0.027802806023941307,
+      "grad_norm": 0.24108867347240448,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 2.3017,
+      "step": 27
+    },
+    {
+      "epoch": 0.028832539580383575,
+      "grad_norm": 0.27671366930007935,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 2.2344,
+      "step": 28
+    },
+    {
+      "epoch": 0.029862273136825847,
+      "grad_norm": 0.31665876507759094,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 2.3259,
+      "step": 29
+    },
+    {
+      "epoch": 0.030892006693268116,
+      "grad_norm": 0.31963345408439636,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 2.2986,
+      "step": 30
+    },
+    {
+      "epoch": 0.03192174024971039,
+      "grad_norm": 0.3043651580810547,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 2.3242,
+      "step": 31
+    },
+    {
+      "epoch": 0.03295147380615266,
+      "grad_norm": 0.31157439947128296,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 2.3512,
+      "step": 32
+    },
+    {
+      "epoch": 0.033981207362594926,
+      "grad_norm": 0.3314283490180969,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 2.2847,
+      "step": 33
+    },
+    {
+      "epoch": 0.0350109409190372,
+      "grad_norm": 0.32019686698913574,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.3864,
+      "step": 34
+    },
+    {
+      "epoch": 0.03604067447547947,
+      "grad_norm": 0.36727410554885864,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 2.3033,
+      "step": 35
+    },
+    {
+      "epoch": 0.03707040803192174,
+      "grad_norm": 0.37023940682411194,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 2.3378,
+      "step": 36
+    },
+    {
+      "epoch": 0.03810014158836401,
+      "grad_norm": 0.41137710213661194,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 2.2779,
+      "step": 37
+    },
+    {
+      "epoch": 0.03912987514480628,
+      "grad_norm": 0.21810898184776306,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.2157,
+      "step": 38
+    },
+    {
+      "epoch": 0.04015960870124855,
+      "grad_norm": 0.1864442676305771,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 2.2263,
+      "step": 39
+    },
+    {
+      "epoch": 0.041189342257690824,
+      "grad_norm": 0.22965551912784576,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 2.2934,
+      "step": 40
+    },
+    {
+      "epoch": 0.042219075814133096,
+      "grad_norm": 0.21589107811450958,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 2.3018,
+      "step": 41
+    },
+    {
+      "epoch": 0.04324880937057536,
+      "grad_norm": 0.23642565310001373,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.2772,
+      "step": 42
+    },
+    {
+      "epoch": 0.04427854292701763,
+      "grad_norm": 0.25743380188941956,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 2.2781,
+      "step": 43
+    },
+    {
+      "epoch": 0.045308276483459906,
+      "grad_norm": 0.26554742455482483,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.344,
+      "step": 44
+    },
+    {
+      "epoch": 0.04633801003990218,
+      "grad_norm": 0.2861109673976898,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 2.3187,
+      "step": 45
+    },
+    {
+      "epoch": 0.04736774359634444,
+      "grad_norm": 0.3041130304336548,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 2.3098,
+      "step": 46
+    },
+    {
+      "epoch": 0.048397477152786715,
+      "grad_norm": 0.3207823634147644,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 2.2769,
+      "step": 47
+    },
+    {
+      "epoch": 0.04942721070922899,
+      "grad_norm": 0.38269367814064026,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 2.4022,
+      "step": 48
+    },
+    {
+      "epoch": 0.05045694426567126,
+      "grad_norm": 0.39273184537887573,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 2.3109,
+      "step": 49
+    },
+    {
+      "epoch": 0.05148667782211353,
+      "grad_norm": 0.5086196660995483,
+      "learning_rate": 0.0,
+      "loss": 2.3821,
+      "step": 50
+    },
+    {
+      "epoch": 0.05148667782211353,
+      "eval_loss": 2.2921998500823975,
+      "eval_runtime": 284.4612,
+      "eval_samples_per_second": 23.001,
+      "eval_steps_per_second": 2.876,
+      "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": 2.9859068337822106e+17,
+  "total_flos": 5.971813667564421e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null