crumbs-playground/clmr1-qwen3-8b-data-generator
Updated
d/loss_fake float64 0.31 1.02 | d/loss_true float64 0.31 1.25 | kl_loss float64 -0 0.09 | policy_loss float64 -6.18 0.93 | grad_norm float64 1.39 434 | mauve float64 0.07 0.08 ⌀ | rewards listlengths 4 4 | mean_reward float64 0.27 1.01 | mean_raw_score float64 -0.95 1.07 | d/accuracy float64 0.41 0.63 | ema_mean_rwd float64 0.64 0.98 | ema_std_rwd float64 0.01 0.35 | word_counts/em_dash_count float64 0 5.5 | word_counts/not_just_count float64 0 0.75 | word_counts/not_only_count float64 0 0.75 | word_counts/gt_em_dash_count float64 0 3.5 | word_counts/gt_not_just_count float64 0 0.5 | word_counts/gt_not_only_count float64 0 0.5 | all_prefix_strings listlengths 4 4 | all_suffix_strings listlengths 4 4 | all_outputs listlengths 2 2 | all_outputs_strings listlengths 4 4 | all_generated_completions listlengths 4 4 | minibatches int64 2 2 | minibatch_size int64 2 2 | gradient_accumulation_steps int64 1 1 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0.334961 | 1.253906 | 0.003868 | 0.927246 | 70.5 | null | [
0.9609375,
0.953125,
0.9765625,
0.98046875
] | 0.967773 | 0.673828 | 0.552066 | 0.958203 | 0.006902 | 2.5 | 0 | 0 | 0 | 0 | 0 | [
" only real solution was through the use of artificial selection, somehow. So far, I haven’t seen any entry using this at its core gameplay.\n\nAlas, this is just a fun competition and after a while I decided not to be as strict with the game idea, and allowed myself to pick whatever I thought would work out.\n\nMy... | [
" also created the “Mechanical Underdogs” signature logo for my intros) further matured the concept, as it involved into the idea of having individual pieces of pasta flying around and trying to evolve until they became all-powerful. A secondary idea here was that the game would work to explain how the Flying Spagh... | [
[
[
198,
151644,
8948,
198,
2610,
1160,
438,
264,
58457,
1614,
315,
4128,
624,
13314,
510,
7129,
872,
510,
7926,
5060,
397,
785,
1196,
686,
3042,
264,
... | [
"\n<|im_start|>system\nYou act as a causal model of language.\nExample:\n\"\"\"\nuser:\n<prefix>\nThe user will present a prefix they wish for you to continue, then you'll start at the last few words\n</prefix>\nassistant:\n...last few words, then continuation starts, and you just keep generating, without any other... | [
" only real solution was through the use of artificial selection, somehow. So far, I haven’t seen any entry using this at its core gameplay.\n\nAlas, this is just a fun competition and after a while I decided not to be as strict with the game idea, and allowed myself to pick whatever I thought would work out.\n\nMy... | 2 | 2 | 1 |
0.338867 | 1.109375 | -0.001419 | -0.037109 | 248 | null | [
0.93359375,
0.9765625,
0.98046875,
0.9453125
] | 0.958984 | 0.672852 | 0.507804 | 0.958027 | 0.009464 | 2.5 | 0 | 0 | 0 | 0 | 0 | [
" this is labor, I could handle it for sure I thought, but I knew this was only the beginning.\n\nMy husband nervously drove us to the hospital as if the baby would pop out any second. I had to remind him to not worry. Things usually didn’t happen that fast for first-time moms (or at least I hoped it wouldn’t). I h... | [
" aches over a 10 hour period. I started googling my symptoms (never a good thing!) and discovered there are people who have this uncomfortable feeling for days and weeks! “Fake labor” would not be in my cards, I had hoped.\n\nFortunately, I had an appointment with a midwife in the afternoon and was checked again f... | [
[
[
151643,
151643,
151643,
151643,
151643,
151643,
151643,
151643,
151643,
151643,
151643,
151643,
151643,
151643,
151643,
151643,
151643,
151643,
151643,
151643,
151643,
151643,
... | [
"\n<|im_start|>system\nYou act as a causal model of language.\nExample:\n\"\"\"\nuser:\n<prefix>\nThe user will present a prefix they wish for you to continue, then you'll start at the last few words\n</prefix>\nassistant:\n...last few words, then continuation starts, and you just keep generating, without any other... | [
" this is labor, I could handle it for sure I thought, but I knew this was only the beginning.\n\nMy husband nervously drove us to the hospital as if the baby would pop out any second. I had to remind him to not worry. Things usually didn’t happen that fast for first-time moms (or at least I hoped it wouldn’t). I h... | 2 | 2 | 1 |
0.330078 | 1.214844 | 0.003098 | 0.582031 | 129 | null | [
0.96875,
0.96484375,
0.96484375,
0.9765625
] | 0.96875 | 0.556641 | 0.518342 | 0.959636 | 0.008762 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | [
"-time processing of streaming data at massive scale. Amazon Kinesis can collect and process hundreds of terabytes of data per hour from hundreds of thousands of sources, so you can write applications that process information in real-time. With Amazon Kinesis applications, you can build real-time dashboards,",
" ... | [
" capture exceptions and generate alerts, drive recommendations, and make other real-time business or operational decisions. You can also easily send data to other services such as Amazon Simple Storage Service, Amazon DynamoDB, and Amazon Redshift.\n\nThe Kinesis Data Streams `KinesisRecorder` client lets you stor... | [
[
[
151643,
151643,
151643,
151643,
151643,
151643,
151643,
151643,
151643,
151643,
151643,
151643,
151643,
151643,
151643,
151643,
151643,
151643,
151643,
151643,
151643,
151643,
... | [
"\n<|im_start|>system\nYou act as a causal model of language.\nExample:\n\"\"\"\nuser:\n<prefix>\nThe user will present a prefix they wish for you to continue, then you'll start at the last few words\n</prefix>\nassistant:\n...last few words, then continuation starts, and you just keep generating, without any other... | [
"-time processing of streaming data at massive scale. Amazon Kinesis can collect and process hundreds of terabytes of data per hour from hundreds of thousands of sources, so you can write applications that process information in real-time. With Amazon Kinesis applications, you can build real-time dashboards, analyz... | 2 | 2 | 1 |
0.431641 | 1.136719 | 0.00341 | -6.181641 | 190 | null | [
0.98046875,
0.91796875,
0.91015625,
0.54296875
] | 0.837891 | 0.777344 | 0.533105 | 0.941081 | 0.033815 | 0.25 | 0 | 0.25 | 0 | 0 | 0 | [" trafficking of PC1. In this proposal we will take advantage of advances in next generation sequen(...TRUNCATED) | [" alleles partially explains phenotypic variability in PKD1 populations. In Aim 2 improved in silic(...TRUNCATED) | [[[151643,151643,151643,151643,151643,151643,151643,151643,151643,151643,151643,151643,151643,151643(...TRUNCATED) | ["\n<|im_start|>system\nYou act as a causal model of language.\nExample:\n\"\"\"\nuser:\n<prefix>\nT(...TRUNCATED) | [" trafficking of PC1. In this proposal we will take advantage of advances in next generation sequen(...TRUNCATED) | 2 | 2 | 1 |
0.34375 | 1.171875 | 0.001987 | 0.289063 | 187 | null | [
0.96875,
0.91015625,
0.96875,
0.953125
] | 0.950195 | 0.323242 | 0.544625 | 0.942302 | 0.032585 | 0.5 | 0.25 | 0 | 0 | 0 | 0 | [" historically low interest rates\nrepresent a real opportunity to reduce your total debt level, ho(...TRUNCATED) | ["\ndoing just that despite having the same everyday financial pressures of\nthose who say they are (...TRUNCATED) | [[[151643,151643,151643,151643,151643,198,151644,8948,198,2610,1160,438,264,58457,1614,315,4128,624,(...TRUNCATED) | ["\n<|im_start|>system\nYou act as a causal model of language.\nExample:\n\"\"\"\nuser:\n<prefix>\nT(...TRUNCATED) | [" historically low interest rates\nrepresent a real opportunity to reduce your total debt level, ho(...TRUNCATED) | 2 | 2 | 1 |
0.335938 | 1.242188 | 0.000351 | 0.375977 | 96.5 | null | [
0.96875,
0.95703125,
0.96484375,
0.953125
] | 0.960938 | 0.309082 | 0.61241 | 0.945097 | 0.028624 | 0.5 | 0 | 0 | 0.25 | 0 | 0 | ["Published: October 25, 1995\n\nProduction notes for Gregg Araki's \"Doom Generation\" say it is \"(...TRUNCATED) | [" energy of his earlier work. That this film includes a teen-age girl, Amy Blue (Rose McGowan), as (...TRUNCATED) | [[[151643,151643,151643,151643,151643,151643,151643,151643,151643,151643,151643,151643,151643,151643(...TRUNCATED) | ["\n<|im_start|>system\nYou act as a causal model of language.\nExample:\n\"\"\"\nuser:\n<prefix>\nT(...TRUNCATED) | ["Published: October 25, 1995\n\nProduction notes for Gregg Araki's \"Doom Generation\" say it is \"(...TRUNCATED) | 2 | 2 | 1 |
0.356445 | 1.214844 | 0.002792 | -0.157227 | 115 | null | [
0.9453125,
0.83984375,
0.95703125,
0.96875
] | 0.927734 | -0.251953 | 0.620083 | 0.9422 | 0.032293 | 0.25 | 0 | 0 | 0 | 0 | 0 | [" also allows you to add Wi-Fi to the 40HX803 via an optional USB dongle. It’s a touch disappoint(...TRUNCATED) | [" you to take the TV online to experience Sony’s Bravia Internet Video platform, which we’ll re(...TRUNCATED) | [[[151643,151643,151643,151643,151643,151643,151643,151643,151643,151643,151643,151643,151643,151643(...TRUNCATED) | ["\n<|im_start|>system\nYou act as a causal model of language.\nExample:\n\"\"\"\nuser:\n<prefix>\nT(...TRUNCATED) | [" also allows you to add Wi-Fi to the 40HX803 via an optional USB dongle. It’s a touch disappoint(...TRUNCATED) | 2 | 2 | 1 |
0.355469 | 1.105469 | 0.003784 | -0.328125 | 179 | null | [
0.9609375,
0.96875,
0.97265625,
0.82421875
] | 0.931641 | -0.102783 | 0.580741 | 0.940323 | 0.036773 | 0.25 | 0 | 0 | 0.5 | 0 | 0 | [" actually learn—but that information \"has not yet been translated effectively into methods and (...TRUNCATED) | [" the new efforts is on identifying promising new developments and ideas in three main areas:\n\nIm(...TRUNCATED) | [[[151643,151643,151643,151643,151643,151643,151643,151643,151643,151643,151643,151643,151643,151643(...TRUNCATED) | ["\n<|im_start|>system\nYou act as a causal model of language.\nExample:\n\"\"\"\nuser:\n<prefix>\nT(...TRUNCATED) | [" actually learn—but that information \"has not yet been translated effectively into methods and (...TRUNCATED) | 2 | 2 | 1 |
0.348633 | 1.238281 | 0.004723 | -0.00293 | 102 | null | [
0.9609375,
0.9375,
0.92578125,
0.93359375
] | 0.939453 | 0.15918 | 0.600543 | 0.939899 | 0.033223 | 0 | 0 | 0 | 0 | 0 | 0 | [" doesn't include a ride on the infamous cable car going down Powell Street? MobileMuni is a comple(...TRUNCATED) | [" on the fly. FreeAlso available for Android\n\nShopNear.meThis app was designed for trendy shopper(...TRUNCATED) | [[[198,151644,8948,198,2610,1160,438,264,58457,1614,315,4128,624,13314,510,7129,872,510,7926,5060,39(...TRUNCATED) | ["\n<|im_start|>system\nYou act as a causal model of language.\nExample:\n\"\"\"\nuser:\n<prefix>\nT(...TRUNCATED) | [" doesn't include a ride on the infamous cable car going down Powell Street? MobileMuni is a comple(...TRUNCATED) | 2 | 2 | 1 |
0.34668 | 1.210938 | 0.001644 | -0.015869 | 115.5 | null | [
0.91015625,
0.96875,
0.94140625,
0.94921875
] | 0.942383 | 0.563477 | 0.513397 | 0.940125 | 0.031405 | 0.5 | 0.25 | 0.25 | 0 | 0.25 | 0.5 | [" to read/watch the story. A player’s capacity, unlike motivation, is intrinsically tied to game (...TRUNCATED) | ["” of great value from the game’s primary villain, Saddler. But Saddler kills Luis, taking back(...TRUNCATED) | [[[198,151644,8948,198,2610,1160,438,264,58457,1614,315,4128,624,13314,510,7129,872,510,7926,5060,39(...TRUNCATED) | ["\n<|im_start|>system\nYou act as a causal model of language.\nExample:\n\"\"\"\nuser:\n<prefix>\nT(...TRUNCATED) | [" to read/watch the story. A player’s capacity, unlike motivation, is intrinsically tied to game (...TRUNCATED) | 2 | 2 | 1 |
End of preview. Expand in Data Studio
~0.075
- Downloads last month
- 6
Models trained or fine-tuned on crumbs-playground/clmr-rollouts-qwen3-8b-03