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:c17d69bf2f5733995cbd0171841d052783efa4c1242aa536506ba28869277976
+oid sha256:e9f3f22e89e1324e6b00f6bb92b499182c193c9785bff4fab41e0c35c48c0c75
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e15981fe7b69e5eab15a555dab0535a4fbed295391249029a3285e2d476c28cb
+oid sha256:49ee79c8991a4559ccec9de73aa73e69fc217c025b1f0e0a99d32a161fbfcb9a
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2290c5c9027f05671573d4c71667fc8f55032670641ede9344662d1dc3100b0
+oid sha256:bb58d72fe1efb30ba9410a0f917f789ce6b8cc538c547fda0fb78b10741e77f5
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c2050a02596240fa7648a1ac0244b5bfc42ff23aa0b4b89573a4afad0d40eae
+oid sha256:9a1ac6737011b84fe6108ec79e4cda6d052381ef0d71a7f8ae6b92dc8ce19277
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5e066d9f49161943f049f1055577bdf80e12ab1ae8bdebdf94516debd7aa1ae
+oid sha256:d2013277fe85ed065e9f0541fd4c3e6a015d8b3e3797543f2fee691995814b0e
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:698d0f5c12e242b0f686cc60113ba38dac2f3d6a08d9e116880d3b602529d4d0
+oid sha256:606965e77d8a22b64a368c02574b8109bfd48e9a47a9ecba10f22974e1ef3b4f
 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": 3.590090274810791,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.0037015787233254985,
+  "best_metric": 3.509026050567627,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.007403157446650997,
   "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": 33.084,
       "eval_steps_per_second": 4.136,
       "step": 25
+    },
+    {
+      "epoch": 0.0038496418722585185,
+      "grad_norm": 0.6510112881660461,
+      "learning_rate": 5e-05,
+      "loss": 1.948,
+      "step": 26
+    },
+    {
+      "epoch": 0.003997705021191538,
+      "grad_norm": 0.7697362303733826,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 2.4195,
+      "step": 27
+    },
+    {
+      "epoch": 0.004145768170124558,
+      "grad_norm": 0.8203458189964294,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 2.8089,
+      "step": 28
+    },
+    {
+      "epoch": 0.004293831319057578,
+      "grad_norm": 1.0636454820632935,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 3.2538,
+      "step": 29
+    },
+    {
+      "epoch": 0.004441894467990598,
+      "grad_norm": 1.189513087272644,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 3.5219,
+      "step": 30
+    },
+    {
+      "epoch": 0.004589957616923618,
+      "grad_norm": 1.2705456018447876,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 3.452,
+      "step": 31
+    },
+    {
+      "epoch": 0.0047380207658566376,
+      "grad_norm": 1.2574220895767212,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 3.4839,
+      "step": 32
+    },
+    {
+      "epoch": 0.0048860839147896575,
+      "grad_norm": 1.1170214414596558,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 3.4407,
+      "step": 33
+    },
+    {
+      "epoch": 0.005034147063722677,
+      "grad_norm": 1.6142178773880005,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 3.5797,
+      "step": 34
+    },
+    {
+      "epoch": 0.005182210212655697,
+      "grad_norm": 1.546147346496582,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 3.4944,
+      "step": 35
+    },
+    {
+      "epoch": 0.005330273361588717,
+      "grad_norm": 1.5059351921081543,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 3.3299,
+      "step": 36
+    },
+    {
+      "epoch": 0.005478336510521737,
+      "grad_norm": 2.683159828186035,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 3.8225,
+      "step": 37
+    },
+    {
+      "epoch": 0.005626399659454757,
+      "grad_norm": 0.6003758907318115,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.857,
+      "step": 38
+    },
+    {
+      "epoch": 0.005774462808387777,
+      "grad_norm": 0.653516411781311,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 2.2992,
+      "step": 39
+    },
+    {
+      "epoch": 0.005922525957320797,
+      "grad_norm": 0.7188121676445007,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 2.6286,
+      "step": 40
+    },
+    {
+      "epoch": 0.006070589106253817,
+      "grad_norm": 0.7915568947792053,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 3.0216,
+      "step": 41
+    },
+    {
+      "epoch": 0.006218652255186837,
+      "grad_norm": 0.9499257206916809,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 3.4042,
+      "step": 42
+    },
+    {
+      "epoch": 0.006366715404119857,
+      "grad_norm": 1.0235894918441772,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 3.3445,
+      "step": 43
+    },
+    {
+      "epoch": 0.006514778553052877,
+      "grad_norm": 1.2685362100601196,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 3.5116,
+      "step": 44
+    },
+    {
+      "epoch": 0.006662841701985897,
+      "grad_norm": 1.3682130575180054,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 3.3778,
+      "step": 45
+    },
+    {
+      "epoch": 0.0068109048509189165,
+      "grad_norm": 1.3854373693466187,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 3.5084,
+      "step": 46
+    },
+    {
+      "epoch": 0.006958967999851936,
+      "grad_norm": 1.6270792484283447,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 3.458,
+      "step": 47
+    },
+    {
+      "epoch": 0.007107031148784957,
+      "grad_norm": 1.6105763912200928,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 3.4925,
+      "step": 48
+    },
+    {
+      "epoch": 0.007255094297717977,
+      "grad_norm": 1.7431771755218506,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 3.7432,
+      "step": 49
+    },
+    {
+      "epoch": 0.007403157446650997,
+      "grad_norm": 3.2638516426086426,
+      "learning_rate": 0.0,
+      "loss": 4.062,
+      "step": 50
+    },
+    {
+      "epoch": 0.007403157446650997,
+      "eval_loss": 3.509026050567627,
+      "eval_runtime": 1374.419,
+      "eval_samples_per_second": 33.105,
+      "eval_steps_per_second": 4.138,
+      "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