Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:865466da178a1d3b4e4cf8129d74ebfbeb62c385b386e08edffffa30bebb4722
+oid sha256:b6e9b37da5390473c103ef0456a446bead88cdf5164ee2380e465482250efe8d
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b77b5617b80222b1e309ee038ef0d38966490d65a976c0fe239178be5251cc92
+oid sha256:6e2874403546556f764181c5e3767d2b412a6d3123d12177fd1b3666fa3715b2
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfdb9d1df92776a33867c3a03628e6d67196b80f37614993f50aff6da4cd69e0
+oid sha256:c0820b4021e8037c7a87138d4161de10a7347a12243f505e824df601a847f574
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7eb37991d2c110842bfb64c093158832a2ac87746297145e44b621165eca89ff
+oid sha256:8a977a3f00e3e25206510da1819c430db6586f4dc1dc17fb9d39af7fbab0cea0
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b86da3e2d3b66be4f686af79b65196d02ebf96aa588b3b12d9608f6730935462
+oid sha256:00546e5fb6508517b17d5673fcec75fd360ec6c1cd3da7719960d0020bc8305f
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2eeb0db58578e2dc7cf48ef4eac18d428b3dd94571db653a91d3e77d0f2dbaff
+oid sha256:e1d76772d79e2c7a533fb680c7c4536cf3d34a2a793f238390dc705518ff645e
 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": 0.9695191383361816,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.8032128514056225,
+  "best_metric": 0.9312173128128052,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.606425702811245,
   "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": 33.83,
       "eval_steps_per_second": 4.35,
       "step": 25
+    },
+    {
+      "epoch": 0.8353413654618473,
+      "grad_norm": 0.24048203229904175,
+      "learning_rate": 5e-05,
+      "loss": 0.8638,
+      "step": 26
+    },
+    {
+      "epoch": 0.8674698795180723,
+      "grad_norm": 0.2766144871711731,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.8763,
+      "step": 27
+    },
+    {
+      "epoch": 0.8995983935742972,
+      "grad_norm": 0.33197683095932007,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.9842,
+      "step": 28
+    },
+    {
+      "epoch": 0.9317269076305221,
+      "grad_norm": 0.4324350953102112,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.1282,
+      "step": 29
+    },
+    {
+      "epoch": 0.963855421686747,
+      "grad_norm": 0.529782235622406,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.0059,
+      "step": 30
+    },
+    {
+      "epoch": 0.9959839357429718,
+      "grad_norm": 0.8212984204292297,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.0078,
+      "step": 31
+    },
+    {
+      "epoch": 1.0281124497991967,
+      "grad_norm": 0.7191594243049622,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.7272,
+      "step": 32
+    },
+    {
+      "epoch": 1.0602409638554218,
+      "grad_norm": 0.21400919556617737,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.8034,
+      "step": 33
+    },
+    {
+      "epoch": 1.0923694779116466,
+      "grad_norm": 0.24180129170417786,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.8047,
+      "step": 34
+    },
+    {
+      "epoch": 1.1244979919678715,
+      "grad_norm": 0.2623453438282013,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.8572,
+      "step": 35
+    },
+    {
+      "epoch": 1.1566265060240963,
+      "grad_norm": 0.29567477107048035,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.9517,
+      "step": 36
+    },
+    {
+      "epoch": 1.1887550200803212,
+      "grad_norm": 0.3571619987487793,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.0344,
+      "step": 37
+    },
+    {
+      "epoch": 1.2208835341365463,
+      "grad_norm": 0.4931532144546509,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.8681,
+      "step": 38
+    },
+    {
+      "epoch": 1.2530120481927711,
+      "grad_norm": 0.26283013820648193,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.5412,
+      "step": 39
+    },
+    {
+      "epoch": 1.285140562248996,
+      "grad_norm": 0.3064008355140686,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.9181,
+      "step": 40
+    },
+    {
+      "epoch": 1.3172690763052208,
+      "grad_norm": 0.2527739107608795,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.7766,
+      "step": 41
+    },
+    {
+      "epoch": 1.3493975903614457,
+      "grad_norm": 0.25356173515319824,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.8179,
+      "step": 42
+    },
+    {
+      "epoch": 1.3815261044176708,
+      "grad_norm": 0.2498927116394043,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.8738,
+      "step": 43
+    },
+    {
+      "epoch": 1.4136546184738956,
+      "grad_norm": 0.29338541626930237,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.9786,
+      "step": 44
+    },
+    {
+      "epoch": 1.4457831325301205,
+      "grad_norm": 0.37280967831611633,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.9918,
+      "step": 45
+    },
+    {
+      "epoch": 1.4779116465863453,
+      "grad_norm": 0.5187456607818604,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.877,
+      "step": 46
+    },
+    {
+      "epoch": 1.5100401606425704,
+      "grad_norm": 0.2522510886192322,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.7026,
+      "step": 47
+    },
+    {
+      "epoch": 1.5421686746987953,
+      "grad_norm": 0.2333376705646515,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.854,
+      "step": 48
+    },
+    {
+      "epoch": 1.5742971887550201,
+      "grad_norm": 0.23066844046115875,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.8185,
+      "step": 49
+    },
+    {
+      "epoch": 1.606425702811245,
+      "grad_norm": 0.2516214847564697,
+      "learning_rate": 0.0,
+      "loss": 0.8216,
+      "step": 50
+    },
+    {
+      "epoch": 1.606425702811245,
+      "eval_loss": 0.9312173128128052,
+      "eval_runtime": 6.2026,
+      "eval_samples_per_second": 33.857,
+      "eval_steps_per_second": 4.353,
+      "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": 2.984041808658432e+17,
+  "total_flos": 5.968083617316864e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null