Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ec65998dd025edbdfb02f752aec42b64524e0802d72d61d2d72a6bc44e1785f
+oid sha256:87bff26ead8d4fae2d925671ce76896cd8cef3ff19e435f6aea5480f1b622ccf
 size 113284112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5064723f9055905a21cba08ae9209b73a59a3b84bb7950f75faca248fd3780b4
+oid sha256:48a262ab4717a93b850dda3df35a83dbd824bd5d9a7cd9f2001b5ae6b9ddabc3
 size 226735226

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df2eeecbc154b9331c74f0831fe29afab996f95e61ef1a758a6caf6827382f4c
+oid sha256:ae54447ee58ec850ede3dcf31d65b23cf0633379e56a8331a35d8e2fcc1ac6a3
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b796811d4733068b0b6ab227202953c8c15b7705505f89116c7d57692a29b23
+oid sha256:cc6f08a6602e3be9d6e82a1c4cc04632110d01301d58aa388d3538e776a6b45e
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d362e0890a1e18ed4664aeccb29f669347c315cd118ee0a1555b111159fee04d
+oid sha256:7fb13fa6960b609423f1c3aacf1dcb30851fa0f344cb02d979b3249ce17c519c
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a2f6940b6e32835120396a89734ca3d0b7a5db14ca28e4706bb3ebad2b2b0b6
+oid sha256:10deeb728a8fe136ce56355014f9bf0b523bae8072420c637964c7a8a6aabdfb
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5eda964d5b06109c7ff637060199d72e397eeb7027b50e10972a323edbe81312
+oid sha256:fb0ce41087f0939d63a9a6eb297660d82f62bda022868309a8c97328e5da41a5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.718066692352295,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.4106776180698152,
+  "best_metric": 2.5712802410125732,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.8213552361396304,
   "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": 24.49,
       "eval_steps_per_second": 6.367,
       "step": 25
+    },
+    {
+      "epoch": 0.4271047227926078,
+      "grad_norm": 0.8887903690338135,
+      "learning_rate": 7.917848237560709e-05,
+      "loss": 3.0674,
+      "step": 26
+    },
+    {
+      "epoch": 0.44353182751540043,
+      "grad_norm": 0.8925255537033081,
+      "learning_rate": 7.75e-05,
+      "loss": 2.9501,
+      "step": 27
+    },
+    {
+      "epoch": 0.459958932238193,
+      "grad_norm": 0.8643532395362854,
+      "learning_rate": 7.577868759557654e-05,
+      "loss": 2.8978,
+      "step": 28
+    },
+    {
+      "epoch": 0.47638603696098564,
+      "grad_norm": 0.781319797039032,
+      "learning_rate": 7.401782177833148e-05,
+      "loss": 3.0056,
+      "step": 29
+    },
+    {
+      "epoch": 0.4928131416837782,
+      "grad_norm": 0.6614418625831604,
+      "learning_rate": 7.222075445642904e-05,
+      "loss": 2.794,
+      "step": 30
+    },
+    {
+      "epoch": 0.5092402464065708,
+      "grad_norm": 0.5951665043830872,
+      "learning_rate": 7.03909064496551e-05,
+      "loss": 2.8334,
+      "step": 31
+    },
+    {
+      "epoch": 0.5256673511293635,
+      "grad_norm": 0.5194978713989258,
+      "learning_rate": 6.853176097769229e-05,
+      "loss": 2.7077,
+      "step": 32
+    },
+    {
+      "epoch": 0.5420944558521561,
+      "grad_norm": 0.5276866555213928,
+      "learning_rate": 6.664685702961344e-05,
+      "loss": 2.6171,
+      "step": 33
+    },
+    {
+      "epoch": 0.5585215605749486,
+      "grad_norm": 0.5625050663948059,
+      "learning_rate": 6.473978262721463e-05,
+      "loss": 2.549,
+      "step": 34
+    },
+    {
+      "epoch": 0.5749486652977412,
+      "grad_norm": 0.6556904911994934,
+      "learning_rate": 6.281416799501188e-05,
+      "loss": 2.7686,
+      "step": 35
+    },
+    {
+      "epoch": 0.5913757700205339,
+      "grad_norm": 0.8730102181434631,
+      "learning_rate": 6.087367864990233e-05,
+      "loss": 2.8905,
+      "step": 36
+    },
+    {
+      "epoch": 0.6078028747433265,
+      "grad_norm": 1.161773681640625,
+      "learning_rate": 5.8922008423644624e-05,
+      "loss": 2.7177,
+      "step": 37
+    },
+    {
+      "epoch": 0.6242299794661191,
+      "grad_norm": 0.5960615277290344,
+      "learning_rate": 5.696287243144013e-05,
+      "loss": 2.7356,
+      "step": 38
+    },
+    {
+      "epoch": 0.6406570841889117,
+      "grad_norm": 0.5807135105133057,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 2.7539,
+      "step": 39
+    },
+    {
+      "epoch": 0.6570841889117043,
+      "grad_norm": 0.5186903476715088,
+      "learning_rate": 5.303712756855988e-05,
+      "loss": 2.8117,
+      "step": 40
+    },
+    {
+      "epoch": 0.6735112936344969,
+      "grad_norm": 0.5063162446022034,
+      "learning_rate": 5.107799157635538e-05,
+      "loss": 2.9084,
+      "step": 41
+    },
+    {
+      "epoch": 0.6899383983572895,
+      "grad_norm": 0.5014790892601013,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 2.7374,
+      "step": 42
+    },
+    {
+      "epoch": 0.7063655030800822,
+      "grad_norm": 0.43926894664764404,
+      "learning_rate": 4.718583200498814e-05,
+      "loss": 2.6996,
+      "step": 43
+    },
+    {
+      "epoch": 0.7227926078028748,
+      "grad_norm": 0.49418267607688904,
+      "learning_rate": 4.526021737278538e-05,
+      "loss": 2.6503,
+      "step": 44
+    },
+    {
+      "epoch": 0.7392197125256673,
+      "grad_norm": 0.5326753258705139,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 2.7032,
+      "step": 45
+    },
+    {
+      "epoch": 0.75564681724846,
+      "grad_norm": 0.6158781051635742,
+      "learning_rate": 4.146823902230772e-05,
+      "loss": 2.7546,
+      "step": 46
+    },
+    {
+      "epoch": 0.7720739219712526,
+      "grad_norm": 0.687337338924408,
+      "learning_rate": 3.960909355034491e-05,
+      "loss": 2.7108,
+      "step": 47
+    },
+    {
+      "epoch": 0.7885010266940452,
+      "grad_norm": 0.8074669241905212,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 2.735,
+      "step": 48
+    },
+    {
+      "epoch": 0.8049281314168378,
+      "grad_norm": 1.0225483179092407,
+      "learning_rate": 3.598217822166854e-05,
+      "loss": 2.5535,
+      "step": 49
+    },
+    {
+      "epoch": 0.8213552361396304,
+      "grad_norm": 1.648162841796875,
+      "learning_rate": 3.422131240442349e-05,
+      "loss": 2.565,
+      "step": 50
+    },
+    {
+      "epoch": 0.8213552361396304,
+      "eval_loss": 2.5712802410125732,
+      "eval_runtime": 2.0469,
+      "eval_samples_per_second": 24.427,
+      "eval_steps_per_second": 6.351,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -226,7 +409,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.27587608625152e+16,
+  "total_flos": 1.055175217250304e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null