Upload logs/04516455_tf_soup.log with huggingface_hub
Browse files
logs/04516455_tf_soup.log
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[transformers] This model config has set a `rope_parameters['original_max_position_embeddings']` field, to be used together with `max_position_embeddings` to determine a scaling factor. Please set the `factor` field of `rope_parameters`with this ratio instead -- we recommend the use of this field over `original_max_position_embeddings`, as it is compatible with most model architectures.
|
| 2 |
+
19:49:42 held-out rows 583 (of 600)
|
| 3 |
+
20:12:03 TFM sft/m1_soup.pt r=0 step 0: ans_gold 0.082 last_step 0.041 tok_acc 0.903 ans_nll 2.878 (n=583)
|
| 4 |
+
20:12:03 TFM_TASKS sft/m1_soup.pt r=0 base_conversion:0.00/0.00 basic_arithmetic:0.00/0.00 calendar_arithmetic:0.09/0.05 chain_sum:0.00/0.00 count_primes:0.00/0.00 decimal_arithmetic:0.04/0.00 family_relationships:0.00/0.00 fraction_simplification:0.27/0.27 gcd:0.00/0.00 knights_knaves:0.39/0.30 lcm:0.04/0.00 leg_counting:0.12/0.03 letter_counting:0.00/0.00 number_filtering:0.38/0.00 number_sequence:0.00/0.00 number_sorting:0.50/0.00 prime_factorization:0.02/0.02 products:0.04/0.00 propositional_logic:0.28/0.17 simple_equations:0.00/0.00 spell_backward:0.00/0.00 syllogism:0.03/0.03 time_intervals:0.15/0.04 word_sorting:0.25/0.25
|
| 5 |
+
20:34:00 TFM sft/stage_a.pt r=0 step 2000: ans_gold 0.000 last_step 0.000 tok_acc 0.821 ans_nll 5.428 (n=583)
|
| 6 |
+
20:34:00 TFM_TASKS sft/stage_a.pt r=0 base_conversion:0.00/0.00 basic_arithmetic:0.00/0.00 calendar_arithmetic:0.00/0.00 chain_sum:0.00/0.00 count_primes:0.00/0.00 decimal_arithmetic:0.00/0.00 family_relationships:0.00/0.00 fraction_simplification:0.00/0.00 gcd:0.00/0.00 knights_knaves:0.00/0.00 lcm:0.00/0.00 leg_counting:0.00/0.00 letter_counting:0.00/0.00 number_filtering:0.00/0.00 number_sequence:0.00/0.00 number_sorting:0.00/0.00 prime_factorization:0.00/0.00 products:0.00/0.00 propositional_logic:0.00/0.00 simple_equations:0.00/0.00 spell_backward:0.00/0.00 syllogism:0.00/0.00 time_intervals:0.00/0.00 word_sorting:0.00/0.00
|
| 7 |
+
20:34:00 TFM DONE
|