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:c87fade3cdfcdca3924c43bec71f4120152d1a5a34ca0f5aa18c8ed744b5677f
+oid sha256:a7d8aee4468cd551ea5147d193b1380813472062456c5f032abf97f5261b9f3b
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:564415ea6bab3eee503f12cbb878be4c1a8acc09671ec6db8522068c36b45180
+oid sha256:21126f402a875def2152b03977dfc7b88fb64b6dc02b30a4fd64388a8ec6776a
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88d7f4de72e6f8f4c152b0c4f117fc214c5a7d7c24906093065e9119bd96020b
+oid sha256:3f1e58ed610c5de483417320745354b74ccf0bbd7dab5962cf88a1dcfa788428
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e109bfeda7c2e3aab23fa8f761dcd316ba3f93debbf00a666aab4bd506ae46b5
+oid sha256:e29549a0acb0113a81c07737eeea03d936835cdcea1f5725d6dd76b9372a8aca
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1379e987fc3f1542705369da54ec9b04a2d86f8f769261a17a735c8c93dfd688
+oid sha256:ec794b0b6ef08316c2a5946cd765eb45ef0894dc2a02623390e594a9900ebead
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2557d1cac086316709302fe6995e0251ec7aeb8c1136545be73e19159087f8a7
+oid sha256:ca2905fe72e5fa57dd8d297c069d83a3c6ba9fec0d55ba5840c11961dc91d54f
 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": 1.3193860054016113,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.07714561234329798,
+  "best_metric": 1.02402925491333,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.15429122468659595,
   "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": 15.308,
       "eval_steps_per_second": 1.914,
       "step": 25
+    },
+    {
+      "epoch": 0.08023143683702989,
+      "grad_norm": 213.13775634765625,
+      "learning_rate": 5e-05,
+      "loss": 1.3893,
+      "step": 26
+    },
+    {
+      "epoch": 0.08331726133076181,
+      "grad_norm": 184.24436950683594,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.4026,
+      "step": 27
+    },
+    {
+      "epoch": 0.08640308582449373,
+      "grad_norm": 140.5086212158203,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.2069,
+      "step": 28
+    },
+    {
+      "epoch": 0.08948891031822565,
+      "grad_norm": 88.218994140625,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.1404,
+      "step": 29
+    },
+    {
+      "epoch": 0.09257473481195758,
+      "grad_norm": 96.05084228515625,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.1807,
+      "step": 30
+    },
+    {
+      "epoch": 0.0956605593056895,
+      "grad_norm": 174.5589599609375,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.3129,
+      "step": 31
+    },
+    {
+      "epoch": 0.09874638379942141,
+      "grad_norm": 183.8505096435547,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.3968,
+      "step": 32
+    },
+    {
+      "epoch": 0.10183220829315333,
+      "grad_norm": 127.412353515625,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.2247,
+      "step": 33
+    },
+    {
+      "epoch": 0.10491803278688525,
+      "grad_norm": 91.00982666015625,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.1556,
+      "step": 34
+    },
+    {
+      "epoch": 0.10800385728061716,
+      "grad_norm": 114.41508483886719,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.1534,
+      "step": 35
+    },
+    {
+      "epoch": 0.11108968177434908,
+      "grad_norm": 130.89572143554688,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.1666,
+      "step": 36
+    },
+    {
+      "epoch": 0.114175506268081,
+      "grad_norm": 133.42132568359375,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.8188,
+      "step": 37
+    },
+    {
+      "epoch": 0.11726133076181292,
+      "grad_norm": 95.00689697265625,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.9134,
+      "step": 38
+    },
+    {
+      "epoch": 0.12034715525554485,
+      "grad_norm": 94.86679077148438,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.1303,
+      "step": 39
+    },
+    {
+      "epoch": 0.12343297974927676,
+      "grad_norm": 98.16373443603516,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.1006,
+      "step": 40
+    },
+    {
+      "epoch": 0.12651880424300868,
+      "grad_norm": 99.14767456054688,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.1203,
+      "step": 41
+    },
+    {
+      "epoch": 0.12960462873674058,
+      "grad_norm": 101.3357162475586,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.1717,
+      "step": 42
+    },
+    {
+      "epoch": 0.13269045323047252,
+      "grad_norm": 86.6534652709961,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.0954,
+      "step": 43
+    },
+    {
+      "epoch": 0.13577627772420445,
+      "grad_norm": 94.54973602294922,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.1935,
+      "step": 44
+    },
+    {
+      "epoch": 0.13886210221793635,
+      "grad_norm": 114.60092163085938,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.1784,
+      "step": 45
+    },
+    {
+      "epoch": 0.14194792671166828,
+      "grad_norm": 92.37266540527344,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.9896,
+      "step": 46
+    },
+    {
+      "epoch": 0.14503375120540019,
+      "grad_norm": 109.13663482666016,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.9855,
+      "step": 47
+    },
+    {
+      "epoch": 0.14811957569913212,
+      "grad_norm": 108.86652374267578,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.1733,
+      "step": 48
+    },
+    {
+      "epoch": 0.15120540019286402,
+      "grad_norm": 98.48587036132812,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.0276,
+      "step": 49
+    },
+    {
+      "epoch": 0.15429122468659595,
+      "grad_norm": 126.57118225097656,
+      "learning_rate": 0.0,
+      "loss": 0.9324,
+      "step": 50
+    },
+    {
+      "epoch": 0.15429122468659595,
+      "eval_loss": 1.02402925491333,
+      "eval_runtime": 142.6345,
+      "eval_samples_per_second": 15.305,
+      "eval_steps_per_second": 1.914,
+      "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": 2.829013890367488e+17,
+  "total_flos": 5.658027780734976e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null