Upload logs/0e2983ba_tf_sftT2.log with huggingface_hub
Browse files
logs/0e2983ba_tf_sftT2.log
CHANGED
|
@@ -1,2 +1,5 @@
|
|
| 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 |
14:25:01 held-out rows 583 (of 600)
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
14:25:01 held-out rows 583 (of 600)
|
| 3 |
+
14:34:43 TFM sft/sftT2_final.pt r=0 step 500: ans_gold 0.384 last_step 0.058 tok_acc 0.893 ans_nll 2.549 (n=583)
|
| 4 |
+
14:34:43 TFM_TASKS sft/sftT2_final.pt r=0 base_conversion:0.04/0.00 basic_arithmetic:0.83/0.06 calendar_arithmetic:0.32/0.05 chain_sum:0.83/0.03 count_primes:0.50/0.00 decimal_arithmetic:0.07/0.00 family_relationships:0.05/0.00 fraction_simplification:0.33/0.27 gcd:0.43/0.11 knights_knaves:0.30/0.26 lcm:0.79/0.04 leg_counting:0.38/0.00 letter_counting:0.22/0.00 number_filtering:0.05/0.00 number_sequence:0.63/0.00 number_sorting:0.00/0.00 prime_factorization:0.02/0.02 products:0.80/0.16 propositional_logic:0.33/0.22 simple_equations:0.97/0.03 spell_backward:0.00/0.00 syllogism:0.03/0.03 time_intervals:0.37/0.00 word_sorting:0.50/0.00
|
| 5 |
+
14:34:44 TFM DONE
|