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:e29de4ebae141d3ffd6e7df6b35a665409769b7df82095002e215592e57c074d
+oid sha256:c2747030eb99610319fcc9148e87a81c76ea077961f69f8648e8c292d6a1566b
 size 70430032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6389dc678ea51a8226bb3187634f9d93e21a64df094ae822da0aec1a1bcedf8a
+oid sha256:415250742aecd038338cea8405ec4ea03e6ae1e262b25824dad3f1512b0d0817
 size 141053442

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9309de91c19f74c0d371787f80125a755f2e19b18902ee00f097f8dc00587ada
+oid sha256:b974741303cf1340f4415fe4151a343a10bde8103e78a5a1cdde23a0445b3837
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e0b5c5f3e4b3509838e9a8196645d54ad5109cc2a1453795ffc6d5846b17788
+oid sha256:9c004fcf817425690bd95c90a8e8c8015e6ed37cf3666012fecd20fd9b9a3a47
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb8681594a1762c088907fae9a27ef10e14b9603ef059a7fa6add4c177d28f0d
+oid sha256:bad44c86947fb54047080b2ae63361b49383ad3be3db4eb0f31b986b697caf11
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e9a341c6823c44339f9d228578f874ce40925ac0d38bf0cbf906fc8596d4f01
+oid sha256:0038199309b6d2f8a97bc5cbb010d09721f50ff6c07756a948c84aecb5bb284e
 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": 0.8154560923576355,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.028115554930765445,
+  "best_metric": 0.5816426277160645,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.05623110986153089,
   "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": 67.318,
       "eval_steps_per_second": 8.418,
       "step": 25
+    },
+    {
+      "epoch": 0.029240177127996064,
+      "grad_norm": 3.9729034900665283,
+      "learning_rate": 5e-05,
+      "loss": 1.0358,
+      "step": 26
+    },
+    {
+      "epoch": 0.03036479932522668,
+      "grad_norm": 4.659002780914307,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.9305,
+      "step": 27
+    },
+    {
+      "epoch": 0.031489421522457296,
+      "grad_norm": 4.61726188659668,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.9645,
+      "step": 28
+    },
+    {
+      "epoch": 0.032614043719687916,
+      "grad_norm": 3.477609634399414,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.7763,
+      "step": 29
+    },
+    {
+      "epoch": 0.033738665916918535,
+      "grad_norm": 2.484680652618408,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.7179,
+      "step": 30
+    },
+    {
+      "epoch": 0.034863288114149155,
+      "grad_norm": 2.2007455825805664,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.6509,
+      "step": 31
+    },
+    {
+      "epoch": 0.035987910311379774,
+      "grad_norm": 1.9197261333465576,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.566,
+      "step": 32
+    },
+    {
+      "epoch": 0.03711253250861039,
+      "grad_norm": 2.2877860069274902,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.5644,
+      "step": 33
+    },
+    {
+      "epoch": 0.038237154705841006,
+      "grad_norm": 2.6936111450195312,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.5342,
+      "step": 34
+    },
+    {
+      "epoch": 0.039361776903071626,
+      "grad_norm": 2.989370584487915,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.545,
+      "step": 35
+    },
+    {
+      "epoch": 0.040486399100302245,
+      "grad_norm": 2.734513282775879,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.4799,
+      "step": 36
+    },
+    {
+      "epoch": 0.04161102129753286,
+      "grad_norm": 3.855745315551758,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.5051,
+      "step": 37
+    },
+    {
+      "epoch": 0.04273564349476348,
+      "grad_norm": 4.42442512512207,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.8314,
+      "step": 38
+    },
+    {
+      "epoch": 0.043860265691994096,
+      "grad_norm": 2.021456718444824,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.6981,
+      "step": 39
+    },
+    {
+      "epoch": 0.044984887889224716,
+      "grad_norm": 1.7155187129974365,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.6955,
+      "step": 40
+    },
+    {
+      "epoch": 0.04610951008645533,
+      "grad_norm": 1.8176416158676147,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.6259,
+      "step": 41
+    },
+    {
+      "epoch": 0.04723413228368595,
+      "grad_norm": 1.7540547847747803,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.561,
+      "step": 42
+    },
+    {
+      "epoch": 0.04835875448091657,
+      "grad_norm": 1.9893765449523926,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.6543,
+      "step": 43
+    },
+    {
+      "epoch": 0.04948337667814719,
+      "grad_norm": 1.8578767776489258,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.5677,
+      "step": 44
+    },
+    {
+      "epoch": 0.050607998875377806,
+      "grad_norm": 1.9309836626052856,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.5467,
+      "step": 45
+    },
+    {
+      "epoch": 0.05173262107260842,
+      "grad_norm": 2.186310291290283,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.5394,
+      "step": 46
+    },
+    {
+      "epoch": 0.05285724326983904,
+      "grad_norm": 1.9131931066513062,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.4731,
+      "step": 47
+    },
+    {
+      "epoch": 0.05398186546706966,
+      "grad_norm": 2.7403504848480225,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.4916,
+      "step": 48
+    },
+    {
+      "epoch": 0.05510648766430028,
+      "grad_norm": 2.281416416168213,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.4393,
+      "step": 49
+    },
+    {
+      "epoch": 0.05623110986153089,
+      "grad_norm": 5.036102294921875,
+      "learning_rate": 0.0,
+      "loss": 0.4817,
+      "step": 50
+    },
+    {
+      "epoch": 0.05623110986153089,
+      "eval_loss": 0.5816426277160645,
+      "eval_runtime": 88.7214,
+      "eval_samples_per_second": 67.515,
+      "eval_steps_per_second": 8.442,
+      "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": 1.4774273839202304e+16,
+  "total_flos": 2.9539319471407104e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null