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:b070a0755db800f94ff3eec79a4f0681b4a0a3d5c59f5a470f3e302f5ab1d3e6
+oid sha256:de1f9e9e7a2dd83fcba362c7f0fd7d8bbc5539a255bf937881f810d1040b2c55
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4da9c4a5407872194eaf9e5d6859b5b8d30f62c9c85bba3d0880c2b9aafdb680
+oid sha256:5eb08874e901617763f278f2692fafd3adbe294b1eb3f240ac7479db1f841a4d
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0d6e746be3c4c2ec79fe07e2c8c4488229d229ccb7bb6d8a76fbb0e308bce03
+oid sha256:9a0f52712fee09f816a8cfe3f1b9fb6da293e3c6c153bc306aa8af7b1c3617f8
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:511a3615967e3ac75c017a44c31031746fcca89ef1a40b394cbf070f3a8b4656
+oid sha256:e60f107627b360641b16b36926e54a3d78f1a3784c539aff19f15c46bf09082b
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d5c5410d4f2c90df47816e6a287d0412fe7aa10f7201f2db1b9d4202b767c83
+oid sha256:cb748fa00677a03e2adf7f89009eb05d7e96a71d3aa1d2836da5a6658148d484
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a02f2e528623ff2a9a57a036012ed36c58940a91a463a9209f34261c36390d10
+oid sha256:c1f6e62d160369f5dcf4a22cbfbc3eacceef5c7c2b59be47970a904c077c1025
 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": 2.517580032348633,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.15791551519936833,
+  "best_metric": 2.345757484436035,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.31583103039873667,
   "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": 86.172,
       "eval_steps_per_second": 10.822,
       "step": 25
+    },
+    {
+      "epoch": 0.16423213580734308,
+      "grad_norm": 0.7472804188728333,
+      "learning_rate": 5e-05,
+      "loss": 2.1701,
+      "step": 26
+    },
+    {
+      "epoch": 0.1705487564153178,
+      "grad_norm": 0.7590801119804382,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 2.3226,
+      "step": 27
+    },
+    {
+      "epoch": 0.17686537702329252,
+      "grad_norm": 0.8624691367149353,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 2.1347,
+      "step": 28
+    },
+    {
+      "epoch": 0.18318199763126727,
+      "grad_norm": 0.7706214189529419,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 2.2104,
+      "step": 29
+    },
+    {
+      "epoch": 0.189498618239242,
+      "grad_norm": 0.8338087201118469,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 2.4114,
+      "step": 30
+    },
+    {
+      "epoch": 0.19581523884721674,
+      "grad_norm": 0.9004456996917725,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 2.487,
+      "step": 31
+    },
+    {
+      "epoch": 0.20213185945519146,
+      "grad_norm": 0.9136253595352173,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 2.4893,
+      "step": 32
+    },
+    {
+      "epoch": 0.2084484800631662,
+      "grad_norm": 0.8845799565315247,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 2.2766,
+      "step": 33
+    },
+    {
+      "epoch": 0.21476510067114093,
+      "grad_norm": 1.1320760250091553,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.6643,
+      "step": 34
+    },
+    {
+      "epoch": 0.22108172127911568,
+      "grad_norm": 1.2713851928710938,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 2.7563,
+      "step": 35
+    },
+    {
+      "epoch": 0.2273983418870904,
+      "grad_norm": 0.9692124128341675,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 2.7175,
+      "step": 36
+    },
+    {
+      "epoch": 0.23371496249506515,
+      "grad_norm": 1.1749975681304932,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 2.5021,
+      "step": 37
+    },
+    {
+      "epoch": 0.24003158310303987,
+      "grad_norm": 0.8900548219680786,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.3335,
+      "step": 38
+    },
+    {
+      "epoch": 0.2463482037110146,
+      "grad_norm": 0.689755916595459,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 2.1621,
+      "step": 39
+    },
+    {
+      "epoch": 0.25266482431898935,
+      "grad_norm": 0.7295820713043213,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 2.0389,
+      "step": 40
+    },
+    {
+      "epoch": 0.25898144492696407,
+      "grad_norm": 0.7669286131858826,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 2.2391,
+      "step": 41
+    },
+    {
+      "epoch": 0.2652980655349388,
+      "grad_norm": 0.7550666332244873,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.0155,
+      "step": 42
+    },
+    {
+      "epoch": 0.27161468614291356,
+      "grad_norm": 0.7518640160560608,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 2.2435,
+      "step": 43
+    },
+    {
+      "epoch": 0.2779313067508883,
+      "grad_norm": 0.8904653191566467,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.4775,
+      "step": 44
+    },
+    {
+      "epoch": 0.284247927358863,
+      "grad_norm": 0.891883134841919,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 2.4781,
+      "step": 45
+    },
+    {
+      "epoch": 0.2905645479668377,
+      "grad_norm": 0.884515106678009,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 2.2253,
+      "step": 46
+    },
+    {
+      "epoch": 0.29688116857481245,
+      "grad_norm": 1.0977036952972412,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 2.4993,
+      "step": 47
+    },
+    {
+      "epoch": 0.3031977891827872,
+      "grad_norm": 1.0684934854507446,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 2.4539,
+      "step": 48
+    },
+    {
+      "epoch": 0.30951440979076195,
+      "grad_norm": 1.174559235572815,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 2.9581,
+      "step": 49
+    },
+    {
+      "epoch": 0.31583103039873667,
+      "grad_norm": 1.3068698644638062,
+      "learning_rate": 0.0,
+      "loss": 2.9451,
+      "step": 50
+    },
+    {
+      "epoch": 0.31583103039873667,
+      "eval_loss": 2.345757484436035,
+      "eval_runtime": 12.1674,
+      "eval_samples_per_second": 87.693,
+      "eval_steps_per_second": 11.013,
+      "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": 5.29768176943104e+16,
+  "total_flos": 1.059536353886208e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null