Merge pull request #182 from foundation-model-stack/revert-179-fix_add_eos_id

Revert "pass EOS token id to validate"

Author: Ssukriti

aiu_fms_testing_utils/scripts/drive_paged_programs.py

@@ -682,7 +682,6 @@ def __metric_calculator(r: torch.Tensor, t: torch.Tensor):
                 max_new_tokens,
                 LogitsExtractorHook(),
                 attn_algorithm="math",
-                eos_token_id=tokenizer.eos_token_id,
                 **extra_kwargs,
             )
             # save the cpu validation info for later consumption
@@ -707,7 +706,6 @@ def __metric_calculator(r: torch.Tensor, t: torch.Tensor):
                 input_ids,
                 max_new_tokens,
                 GoldenTokenHook(cpu_validation_info.get_info("tokens")),
-                eos_token_id=tokenizer.eos_token_id,
                 last_n_tokens=64,
                 timing=TIMING,
                 prefill_chunk_size=args.prefill_chunk_size,
@@ -753,7 +751,6 @@ def __metric_calculator(r: torch.Tensor, t: torch.Tensor):
                 input_ids,
                 max_new_tokens,
                 None,
-                eos_token_id=tokenizer.eos_token_id,
                 last_n_tokens=64,
                 timing=TIMING,
                 prefill_chunk_size=args.prefill_chunk_size,
@@ -797,7 +794,6 @@ def __metric_calculator(r: torch.Tensor, t: torch.Tensor):
             input_ids,
             max_new_tokens,
             None,
-            eos_token_id=tokenizer.eos_token_id,
             last_n_tokens=64,
             timing=TIMING,
             prefill_chunk_size=args.prefill_chunk_size,

aiu_fms_testing_utils/scripts/generate_metrics.py

@@ -245,7 +245,6 @@ def write_csv(metrics, path, metric_name):
         args.max_new_tokens,
         LogitsExtractorHook(),
         attn_algorithm="math",
-        eos_token_id=tokenizer.eos_token_id,
         **padding_kwargs,
     )
     cpu_static_tokens = cpu_validation_info.get_info("tokens")
@@ -260,7 +259,6 @@ def write_csv(metrics, path, metric_name):
         ids.to("cuda"),
         args.max_new_tokens,
         None,
-        eos_token_id=tokenizer.eos_token_id,
         last_n_tokens=1,
         **{k: v.to("cuda") for k, v in padding_kwargs.items()},
     )
@@ -327,7 +325,6 @@ def write_csv(metrics, path, metric_name):
                 args.max_new_tokens,
                 LogitsExtractorHook(),
                 attn_algorithm="math",
-                eos_token_id=tokenizer.eos_token_id,
                 **padding_kwargs,
             )
 
@@ -337,7 +334,6 @@ def write_csv(metrics, path, metric_name):
             ids.to("cuda"),
             args.max_new_tokens,
             GoldenTokenHook(cpu_validation_info.get_info("tokens"), "cuda"),
-            eos_token_id=tokenizer.eos_token_id,
             last_n_tokens=1,
             **{k: v.to("cuda") for k, v in padding_kwargs.items()},
         )

aiu_fms_testing_utils/scripts/save_cpu_data.py

@@ -97,7 +97,6 @@ def process_row(row):
             max_new_tokens,
             LogitsExtractorHook(),
             attn_algorithm="math",
-            eos_token_id=tokenizer.eos_token_id,
         )
     return {"id": id, "input_ids": input_ids, "validation": cpu_validation_info}
 

aiu_fms_testing_utils/scripts/validation.py

@@ -690,7 +690,6 @@ def print_result(result, result_idx: int = 0, file_prefix: str = ""):
         ids.to(validation_device),
         args.max_new_tokens,
         LogitsExtractorHook(),
-        eos_token_id=None if args.no_early_termination else tokenizer.eos_token_id,
         attn_algorithm="math",
         **padding_kwargs,
     )

tests/models/test_decoders.py

@@ -612,7 +612,6 @@ def _get_device_validation_information(
         max_new_tokens,
         post_iteration_hook,
         timing=TIMING,
-        eos_token_id=tokenizer.eos_token_id,
         **extra_kwargs,
         **device_dependent_kwargs,
     )