Upload logs/01849a17_tf_x1.log with huggingface_hub
Browse files- logs/01849a17_tf_x1.log +4 -0
logs/01849a17_tf_x1.log
CHANGED
|
@@ -3,3 +3,7 @@
|
|
| 3 |
. Make sure to double-check they do not contain any added malicious code. To avoid downloading new versions of the code file, you can pin a revision.
|
| 4 |
[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.
|
| 5 |
17:30:38 held-out rows 583 (of 600)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
. Make sure to double-check they do not contain any added malicious code. To avoid downloading new versions of the code file, you can pin a revision.
|
| 4 |
[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.
|
| 5 |
17:30:38 held-out rows 583 (of 600)
|
| 6 |
+
17:53:27 TFV ans_value 0.256
|
| 7 |
+
17:53:27 TFM sft/sftX1_latest.pt r=0 step 2000: ans_gold 0.057 last_step 0.036 tok_acc 0.911 ans_nll 3.522 (n=583)
|
| 8 |
+
17:53:27 TFM_TASKS sft/sftX1_latest.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:0.30/0.13 lcm:0.00/0.00 leg_counting:0.12/0.06 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:0.02/0.02 products:0.00/0.00 propositional_logic:0.22/0.17 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
|
| 9 |
+
17:53:27 TFM DONE
|