Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72ebf9da260be86c30d6530c28d324831f3dcd3f11984d33e803f6a6d2c275fb
+oid sha256:89ee29f100ea27b48d63419dddd1b60ad79c3d0e4dce336dced7d962afe7f007
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3971269301fc7ff21e38243cb63295e475ca84f36593afac098ad6f6c23d6ac7
+oid sha256:fd0696e8124158222486435e76cbc3024001a76d4c0d2dbdbdcd4797863a5a84
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a15c6b2c27ab037cf0b7923f4758c27f8a1e64e20a700bd13ed80e6d6fcd4f7
+oid sha256:9b8a8793908920ec40ea57375c95c628ce057ba201773e8f90bf77374d4f40e3
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2de53d3ee79a74b24d0beb15d36cc222159874beee1032fde5499bde6c68ff3b
+oid sha256:1f8cd8d5c99c7f2e701401e538147297004460a8951bef0c587205d0b6da73c0
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:faa03bff3916fe57724fdb0c58c7aa5aa64dd844c36c8190d23f8a42bc244f44
+oid sha256:a217f28058d568dd66a2307906a018cc403032a18bec1cc7837223fe191936a5
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a5b6e7fff73d7327625897e7fa1d48e786183615a8be92353c0c559dd309ac0
+oid sha256:d1cd85a66c42b2788830c77b7a864271557ed63157fb267860fe7b8aad0ecf1b
 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": 0.5700125098228455,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.011235323858210213,
+  "best_metric": 0.5595068335533142,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.022470647716420426,
   "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": 31.714,
       "eval_steps_per_second": 3.965,
       "step": 25
+    },
+    {
+      "epoch": 0.01168473681253862,
+      "grad_norm": 0.1263992190361023,
+      "learning_rate": 5e-05,
+      "loss": 0.429,
+      "step": 26
+    },
+    {
+      "epoch": 0.01213414976686703,
+      "grad_norm": 0.15916909277439117,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.5305,
+      "step": 27
+    },
+    {
+      "epoch": 0.012583562721195438,
+      "grad_norm": 0.17371866106987,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.6146,
+      "step": 28
+    },
+    {
+      "epoch": 0.013032975675523847,
+      "grad_norm": 0.1692039966583252,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.6,
+      "step": 29
+    },
+    {
+      "epoch": 0.013482388629852255,
+      "grad_norm": 0.17027397453784943,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.6335,
+      "step": 30
+    },
+    {
+      "epoch": 0.013931801584180665,
+      "grad_norm": 0.15436020493507385,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.5825,
+      "step": 31
+    },
+    {
+      "epoch": 0.014381214538509072,
+      "grad_norm": 0.16566522419452667,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.598,
+      "step": 32
+    },
+    {
+      "epoch": 0.014830627492837482,
+      "grad_norm": 0.15967965126037598,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.5444,
+      "step": 33
+    },
+    {
+      "epoch": 0.01528004044716589,
+      "grad_norm": 0.18588681519031525,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.5535,
+      "step": 34
+    },
+    {
+      "epoch": 0.015729453401494297,
+      "grad_norm": 0.19929379224777222,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.5366,
+      "step": 35
+    },
+    {
+      "epoch": 0.016178866355822708,
+      "grad_norm": 0.1949024200439453,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.5704,
+      "step": 36
+    },
+    {
+      "epoch": 0.016628279310151116,
+      "grad_norm": 0.2263709455728531,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.6167,
+      "step": 37
+    },
+    {
+      "epoch": 0.017077692264479524,
+      "grad_norm": 0.11454346776008606,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.3696,
+      "step": 38
+    },
+    {
+      "epoch": 0.01752710521880793,
+      "grad_norm": 0.12531691789627075,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.497,
+      "step": 39
+    },
+    {
+      "epoch": 0.01797651817313634,
+      "grad_norm": 0.15047413110733032,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.5884,
+      "step": 40
+    },
+    {
+      "epoch": 0.01842593112746475,
+      "grad_norm": 0.16039173305034637,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.6083,
+      "step": 41
+    },
+    {
+      "epoch": 0.018875344081793158,
+      "grad_norm": 0.16336725652217865,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.5901,
+      "step": 42
+    },
+    {
+      "epoch": 0.019324757036121566,
+      "grad_norm": 0.1778741180896759,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.623,
+      "step": 43
+    },
+    {
+      "epoch": 0.019774169990449973,
+      "grad_norm": 0.15356756746768951,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.5577,
+      "step": 44
+    },
+    {
+      "epoch": 0.020223582944778384,
+      "grad_norm": 0.15940482914447784,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.536,
+      "step": 45
+    },
+    {
+      "epoch": 0.020672995899106792,
+      "grad_norm": 0.1604880392551422,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.5568,
+      "step": 46
+    },
+    {
+      "epoch": 0.0211224088534352,
+      "grad_norm": 0.1606569141149521,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.5275,
+      "step": 47
+    },
+    {
+      "epoch": 0.021571821807763607,
+      "grad_norm": 0.1797308474779129,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.5776,
+      "step": 48
+    },
+    {
+      "epoch": 0.02202123476209202,
+      "grad_norm": 0.21886350214481354,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.556,
+      "step": 49
+    },
+    {
+      "epoch": 0.022470647716420426,
+      "grad_norm": 0.26146650314331055,
+      "learning_rate": 0.0,
+      "loss": 0.6368,
+      "step": 50
+    },
+    {
+      "epoch": 0.022470647716420426,
+      "eval_loss": 0.5595068335533142,
+      "eval_runtime": 473.6482,
+      "eval_samples_per_second": 31.648,
+      "eval_steps_per_second": 3.957,
+      "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": 2.9989620096486605e+17,
+  "total_flos": 5.9997890444211e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null