237 lines
26 KiB
Plaintext
237 lines
26 KiB
Plaintext
|
o
|
|||
|
|
=—°hAŸ ã @ sÆ d Z ddlmZ ddlZddlmZ ddlmZ ddlmZm Z m
|
|||
|
|
Z
|
|||
|
|
m Z m Z m
|
|||
|
|
Z
|
|||
|
|
mZmZ ddlmZmZmZmZmZmZmZm
|
|||
|
|
Z
|
|||
|
|
mZmZmZmZmZm Z m Z m Z m Z m Z m Z m!Z!m"Z"m#Z#m$Z$m%Z%m&Z&m'Z'm(Z(mZm)Z)m*Z*m+Z+mZm,Z,m
|
|||
|
|
Z
|
|||
|
|
mZm Z m Z m'Z'm)Z)mZ ddl)Z)ddlT ddl-m.Z.m/Z/ dd l0m1Z1 ddlZddl2Z3dd
|
|||
|
|
l4m5Z5 ddlmZ dd l6m7Z7m8Z9 d d
|
|||
|
|
d d
|
|||
|
|
d
|
|||
|
|
dœZ:ej;d d e:d�dd„ ƒZ<e.G dd„ deƒƒZ= G dd„ de ƒZ>G dd„ de>ƒZ?dS )z9
|
|||
|
|
2025.8.9
|
|||
|
|
2025.8.10
|
|||
|
|
4.55.4
|
|||
|
|
0.21.0
|
|||
|
|
__UNSLOTH_VERSIONING__
|
|||
|
|
é )ÚTensorN)Ú
|
|||
|
|
functional)ÚAnyÚListÚOptionalÚTupleÚUnionÚDictÚSetÚCallable)(ÚBaseImageProcessorr Ú DataCollatorÚ"DataCollatorForTokenClassificationÚDatasetÚEvalPredictionÚFeatureExtractionMixinr Ú PRMConfigÚ
|
|||
|
|
PRMTrainerÚ PartialStateÚPathÚ PeftModelÚPreTrainedModelÚPreTrainedTokenizerBaseÚProcessorMixinÚTrainerÚTrainerCallbackr ÚchainÚcompute_accuracyÚdisable_dropout_in_modelÚfeaturesÚgenerate_model_cardÚinspectÚis_peft_availableÚis_wandb_availableÚnnÚosÚ prepare_model_for_kbit_trainingÚtextwrapÚtorchÚwarningsr r r r r" r% r( )Ú*)Ú dataclassÚfield)ÚVersion)Ú nullcontext)ÚDataCollatorForSeq2SeqÚ DataCollatorForLanguageModelingTF)Úepilogue_fusionÚ max_autotuneÚ
|
|||
|
|
shape_paddingz
|
|||
|
|
trace.enabledztriton.cudagraphs)ÚdynamicÚ fullgraphÚoptionsc
|
|||
|
|
C s¾ t j| d| jd ¡ddd�}t j| d¡ddd�}g }t||ƒD ](\}}| t j¡}t j|d| d¡d� d¡}t j
|
|||
|
|
|dd�}|| } | | ¡ q! t |¡}| | jd | jd f¡}|S )Néÿÿÿÿé r )ÚchunksÚdim)r: Úindex)r: é )
|
|||
|
|
r( ÚchunkÚreshapeÚshapeÚzipÚtoÚfloat32ÚgatherÚ unsqueezeÚsqueezeÚ logsumexpÚappendÚconcat)
|
|||
|
|
Úlogitsr; Úchunked_logitsÚ
|
|||
|
|
chunked_indexÚall_per_token_logpsÚ chunk_logitsÚ chunk_indexÚselected_logitsÚlogsumexp_valuesÚper_token_logps© rR úQ/workspace/DS-LLM-TEMPLATE-FINETUNING/unsloth_compiled_cache/UnslothPRMTrainer.pyÚ chunked_selective_log_softmax" s
|
|||
|
|
rT c sŒ e Zd ZU dZedddid�Zee ed< edddid�Z ee
|
|||
|
|
ed < eddd
|
|||
|
|
id�Z ee
|
|||
|
|
ed <
|
|||
|
|
! ! " # $ $ % & ' ( # $ ) * + , $ d/‡ fd-d.„ Z ‡ Z
|
|||
|
|
S )0ÚUnslothPRMConfiga:
|
|||
|
|
|
|||
|
|
Configuration class for the [`PRMTrainer`].
|
|||
|
|
|
|||
|
|
This class includes only the parameters that are specific to PRM training. For a full list of training arguments,
|
|||
|
|
please refer to the [`~transformers.TrainingArguments`] documentation. Note that default values in this class may
|
|||
|
|
differ from those in [`~transformers.TrainingArguments`].
|
|||
|
|
|
|||
|
|
Using [`~transformers.HfArgumentParser`] we can turn this class into
|
|||
|
|
[argparse](https://docs.python.org/3/library/argparse#module-argparse) arguments that can be specified on the
|
|||
|
|
command line.
|
|||
|
|
|
|||
|
|
Parameters:
|
|||
|
|
max_length (`int` or `None`, *optional*, defaults to `1024`):
|
|||
|
|
Maximum length of the sequences (prompt + completion) used for truncation.
|
|||
|
|
max_prompt_length (`int` or `None`, *optional*, defaults to `512`):
|
|||
|
|
Maximum length of the prompt used for truncation.
|
|||
|
|
max_completion_length (`int` or `None`, *optional*, defaults to `None`):
|
|||
|
|
Maximum length of the completion used for truncation. The completion is the concatenation of the steps.
|
|||
|
|
disable_dropout (`bool`, *optional*, defaults to `True`):
|
|||
|
|
Whether to disable dropout in the model.
|
|||
|
|
step_separator (`str`, *optional*, defaults to `"
|
|||
|
|
"`):
|
|||
|
|
Separator used to separate each step of the reasoning process.
|
|||
|
|
train_on_last_step_only (`bool`, *optional*, defaults to `False`):
|
|||
|
|
Whether to train only on the last step.
|
|||
|
|
dataset_num_proc (`int`, *optional*, defaults to `None`):
|
|||
|
|
Number of processes to use for processing the dataset.
|
|||
|
|
|
|||
|
|
NÚhelpzvLLM SamplingParams)ÚdefaultÚmetadataÚvllm_sampling_paramsr7 z8Chunk size to reduce memory usage. -1 is most efficient.Úunsloth_num_chunksz'Maximum sequence length to truncate to.Úmax_seq_lengthFÚnor8 é r éú ç-C ëâ6
|
|||
|
|
?ç{®Gáz„?çÍÌÌÌÌÌì?ç+‡ÙÎ÷ï?ç:Œ0âŽyE>ç ð?ç @Úlinearçš™™™™™¹?ÚpassiveÚwarningTÚstepsr< éô éO
|
|||
|
|
ÚO1ÚautoÚ ç Ú
|
|||
|
|
adamw_8bitÚlengthÚ
|
|||
|
|
every_saveÚlasté é é c‹ � sÆ |dk r t d|› d�ƒ‚|dkrtd|› d�ƒ‚|d u r(|#dkr(|$dkr(d}d }#|‡d u r:d
|
|||
|
|
d lm}Œ t|Œƒ d d
|
|||
|
|
ƒ}‡tƒ jd•i d|“d|“d|“d|“d|“d|“d|“d|“d| “d|
|
|||
|
|
“d| “d| “d|
|
|||
|
|
“d|“d |“d |“d |“d |“d |“d!|“d"|“d#|“d$|“d%|“d&|“d'|“d(|“d)| “d*| “d+| “d,| “d-| “d.|!“d/|"“d0|#“d1|$“d2|%“d3|&“d4|'“d5|(“d6|)“d7|*“d8|+“d9|,“d:|-“d;|.“d<|/“d=|0“d>|1“d?|2“d@|3“dA|4“dB|5“dC|6“dD|7“dE|8“dF|9“dG|:“dH|;“dI|<“dJ|=“dK|>“dL|?“dM|@“dN|A“dO|B“dP|C“dQ|D“dR|E“dS|F“dT|G“dU|H“dV|I“dW|J“dX|K“dY|L“dZ|M“d[|N“d\|O“d]|P“d^|Q“d_|R“d`|S“da|T“db|U“dc|V“dd|W“de|X“df|Y“dg|Z“dh|[“di|\“dj|]“dk|^“dl|_“dm|`“dn|a“do|b“dp|c“dq|d“dr|e“ds|f“dt|g“du|h“dv|i“dw|j“dx|k“dy|l“dz|m“d{|n“d||o“d}|p“d~|q“d|r“d€|s“d�|t“d‚|u“dƒ|v“d„|w“d…|x“d†|y“d‡|z“dˆ|{“d‰||“dŠ|}“d‹|~“dŒ|“d�|€“dŽ|�“d�|‚“d�|ƒ“d‘|„“d’|…“d“|†“d”|‡“|‹¤Ž |ˆ| _|‰| _|Š| _ d S )–NgH¯¼šò×z>z Unsloth: Your learning rate of `zi` is too small and less than 1e-7! Consider increasing it, otherwise gradient updates will be close to 0!r< za` is way too larger > 1! Consider decreasing it to 1e-1, otherwise gradient updates will explode!rj rk Ú unsloth_training_checkpointsr\ r )Ú cpu_countr8 r] Ú
|
|||
|
|
output_dirÚoverwrite_output_dirÚdo_trainÚdo_evalÚ
|
|||
|
|
do_predictÚ
|
|||
|
|
eval_strategyÚprediction_loss_onlyÚper_device_train_batch_sizeÚper_device_eval_batch_sizeÚper_gpu_train_batch_sizeÚper_gpu_eval_batch_sizeÚgradient_accumulation_stepsÚeval_accumulation_stepsÚ
|
|||
|
|
eval_delayÚtorch_empty_cache_stepsÚ
|
|||
|
|
learning_rateÚ weight_decayÚ
|
|||
|
|
adam_beta1Ú
|
|||
|
|
adam_beta2Ú adam_epsilonÚ
|
|||
|
|
max_grad_normÚnum_train_epochsÚ max_stepsÚlr_scheduler_typeÚ warmup_ratioÚ warmup_stepsÚ log_levelÚlog_level_replicaÚlog_on_each_nodeÚ logging_dirÚlogging_strategyÚlogging_first_stepÚ
|
|||
|
|
logging_stepsÚlogging_nan_inf_filterÚ
|
|||
|
|
save_strategyÚ
|
|||
|
|
save_stepsÚsave_total_limitÚsave_safetensorsÚsave_on_each_nodeÚsave_only_modelÚ'restore_callback_states_from_checkpointÚno_cudaÚuse_cpuÚuse_mps_deviceÚseedÚ data_seedÚ
|
|||
|
|
jit_mode_evalÚuse_ipexÚbf16Úfp16Úfp16_opt_levelÚhalf_precision_backendÚbf16_full_evalÚfp16_full_evalÚtf32Ú
|
|||
|
|
local_rankÚ ddp_backendÚ
|
|||
|
|
tpu_num_coresÚtpu_metrics_debugÚdebugÚdataloader_drop_lastÚ
|
|||
|
|
eval_stepsÚdataloader_num_workersÚdataloader_prefetch_factorÚ
|
|||
|
|
past_indexÚrun_nameÚ disable_tqdmÚremove_unused_columnsÚ label_namesÚload_best_model_at_endÚmetric_for_best_modelÚgreater_is_betterÚignore_data_skipÚfsdpÚfsdp_min_num_paramsÚ fsdp_configÚ"fsdp_transformer_layer_cls_to_wrapÚaccelerator_configÚ deepspeedÚlabel_smoothing_factorÚoptimÚ
|
|||
|
|
optim_argsÚ adafactorÚgroup_by_lengthÚlength_column_nameÚ report_toÚddp_find_unused_parametersÚddp_bucket_cap_mbÚddp_broadcast_buffersÚdataloader_pin_memoryÚ dataloader_persistent_workersÚskip_memory_metricsÚuse_legacy_prediction_loopÚ push_to_hubÚresume_from_checkpointÚ hub_model_idÚ hub_strategyÚ hub_tokenÚhub_private_repoÚhub_always_pushÚ hub_revisionÚgradient_checkpointingÚ gradient_checkpointing_kwargsÚinclude_inputs_for_metricsÚeval_do_concat_batchesÚ fp16_backendÚpush_to_hub_model_idÚpush_to_hub_organizationÚpush_to_hub_tokenÚ
|
|||
|
|
mp_parametersÚauto_find_batch_sizeÚfull_determinismÚ torchdynamoÚ ray_scopeÚ ddp_timeoutÚ
|
|||
|
|
torch_compileÚtorch_compile_backendÚtorch_compile_modeÚinclude_tokens_per_secondÚ include_num_input_tokens_seenÚneftune_noise_alphaÚoptim_target_modulesÚbatch_eval_metricsÚ
|
|||
|
|
eval_on_startÚuse_liger_kernelÚliger_kernel_configÚeval_use_gather_objectÚ average_tokens_across_devicesÚ
|
|||
|
|
max_lengthÚmax_prompt_lengthÚmax_completion_lengthÚdisable_dropoutÚstep_separatorÚtrain_on_last_step_onlyÚdataset_num_procrR )
|
|||
|
|
ÚFloatingPointErrorÚ
|
|||
|
|
OverflowErrorÚmultiprocessingry ÚmaxÚsuperÚ__init__rY rZ r[ )�Úselfrz r{ r| r} r~ r r€ r� r‚ rƒ r„ r… r† r‡ rˆ r‰ rŠ r‹ rŒ r� rŽ r� r� r‘ r’ r“ r” r• r– r— r˜ r™ rš r› rœ r� rž rŸ r r¡ r¢ r£ r¤ r¥ r¦ r§ r¨ r© rª r« r¬ r r® r¯ r° r± r² r³ r´ rµ r¶ r· r¸ r¹ rº r» r¼ r½ r¾ r¿ rÀ rÁ r rà rÄ rÅ rÆ rÇ rÈ rÉ rÊ rË rÌ rÍ rÎ rÏ rÐ rÑ rÒ rÓ rÔ rÕ rÖ r× rØ rÙ rÚ rÛ rÜ rÝ rÞ rß rà rá râ rã rä rå ræ rç rè ré rê rë rì rí rî rï rð rñ rò ró rô rõ rö r÷ rø rù rú rû rü rý rþ rÿ r rY rZ r[ Úkwargsry ©Ú __class__rR rS r ^ sX ÿþýüûúùø ÷
|
|||
|
|
ö õ ô
|
|||
|
|
óòñðïîíìëêéèçæå ä ã â á à!ß"Þ#Ý$Ü%Û&Ú'Ù(Ø)×*Ö+Õ,Ô-Ó.Ò/Ñ0Ð1Ï2Î3Í4Ì5Ë6Ê7É8È9Ç:Æ;Å<Ä=Ã>Â?Á@ÀA¿B¾C½D¼E»FºG¹H¸I·J¶KµL´M³N²O±P°Q¯R®ST¬U«VªW©X¨Y§Z¦[¥\¤]£^¢_¡` aŸbžc�dœe›fšg™h˜i—j–k•l”m“n’o‘p�q�rŽs�tŒu‹vŠw‰xˆy‡z†{…|„}ƒ~‚� �ÿ �þ �ý �ü �û �ú �ù �ø
|
|||
|
|
zUnslothPRMConfig.__init__)ŠNNFFFr\ Fr8 r8 NNr] r] r r^ r_ r` ra rb rc rd re r7 rf rg r rh ri TNrj Fr< Frj rk NTFFFFFFrl rl FFFFrm rn FFNr7 NNFro FNr Nr7 NNTNFNNFro r NNNNrp rq NFFrr NNNNTFTFFNNrs NNFNFNFTrn NNNro TFNrt ru FNNFFNNFFFNFTrv rw NTro FNNr7 N)Ú__name__Ú
|
|||
|
|
__module__Ú __qualname__Ú__doc__r, rY r r Ú__annotations__rZ Úintr[ r Ú
|
|||
|
|
__classcell__rR rR r rS rU 3 s4
|
|||
|
|
þþþ �órU c sL e Zd ZdZddgZ d deeeej f dee
|
|||
|
|
dee d ee d
|
|||
|
|
eee e
|
|||
|
|
ee f f d eeeeeef d eeg ef d
|
|||
|
|
eeege
|
|||
|
|
f deee deejjejjj f deeej ej gej f dee
|
|||
|
|
f‡ fdd„
|
|||
|
|
Z e dd„ ƒZ ‡ fdd„Z! d dee dee deeee df fdd „Z"‡ Z#S ) Ú_UnslothPRMTrainerro ÚtrlÚprmN©NNÚmodelÚargsÚ
|
|||
|
|
data_collatorÚ
|
|||
|
|
train_datasetÚ eval_datasetÚprocessing_classÚ
|
|||
|
|
model_initÚcompute_metricsÚ callbacksÚ
|
|||
|
|
optimizersÚ preprocess_logits_for_metricsÚ peft_configc
|
|||
|
|
s( t ƒ s | d ur tdƒ‚t ƒ rU| d urUt|tƒsUt|ddƒs#t|ddƒrSdtt t¡j ƒv }
|
|||
|
|
d|j
|
|||
|
|
i}|
|
|||
|
|
s?|j d ur?t
|
|||
|
|
d¡ n |
|
|||
|
|
rK|j d urK|j |d< t|fi |¤Ž}|}|jr\t|ƒ |d u rbt}|d u ru|d u rntdƒ‚t||jd �}d
|
|||
|
|
|jvrñtƒ ¡ �j ||j|j|j|j|jd œ}i |¥d di¥}|j| j||j |j d
|
|||
|
|
t t t d¡¡t t d¡¡dœ¡d�}i |¥d di¥}|d urâ|j| j||j |j dt t t d¡¡t t d¡¡dœ¡d�}W d ƒ n1 sìw Y t!ƒ j"||||||||| |
|
|||
|
|
| d� t#| j$dƒ�r| j$ %| j&¡ d S d S )NzvPEFT is not installed and you passed a `peft_config` in the trainer's kwargs, please install it to use the PEFT modelsÚis_loaded_in_8bitFÚ is_quantizedrà Úuse_gradient_checkpointingzÂYou passed `gradient_checkpointing_kwargs` in the trainer's kwargs, but your peft version does not support it. please update to the latest version of peft to use `gradient_checkpointing_kwargs`.z^A processing_class must be specified when using the default DataCollatorForTokenClassification)rú Ú input_ids)Ú tokenizerrþ rú rû rü rÿ Úis_evalzTokenizing train datasetÚint64)Úlabelsr% )Ú fn_kwargsÚnum_procÚremove_columnsÚdescr TzTokenizing eval dataset) r r r r r r r r r r r Úadd_model_tags)'r" Ú
|
|||
|
|
ValueErrorÚ
|
|||
|
|
isinstancer ÚgetattrÚlistr! Ú signaturer& Ú
|
|||
|
|
parametersrß rà r) Úwarnrý r r r rú Ú column_namesr Úmain_process_firstrþ rû rü rÿ ÚmapÚ tokenize_rowr r ÚFeaturesÚSequenceÚValuer r Úhasattrr r. Ú
|
|||
|
|
_tag_names)r r r r r r r r r r r r r! Ú_supports_gc_kwargsÚprepare_model_kwargsr* Útrain_fn_kwargsÚeval_fn_kwargsr rR rS r ˆ s¦ ÿ
|
|||
|
|
|
|||
|
|
ÿ
|
|||
|
|
ÿ
|
|||
|
|
ÿ
|
|||
|
|
úþÿúþÿú€ æ(õÿz_UnslothPRMTrainer.__init__c
|
|||
|
|
sJ ˆ| d dd�d }‡fdd„| d D ƒ} |r.|s.dgt | d ƒd
|
|||
|
|
t| d d ƒg }
|
|||
|
|
n d d„ | d D ƒ}
|
|||
|
|
ˆj|dd�‰ ‡ fd
|
|||
|
|
d„| D ƒ} dd„ t| |
|
|||
|
|
ƒD ƒ}
|
|||
|
|
tt| Ž ƒ} tt|
|
|||
|
|
Ž ƒ}
|
|||
|
|
ˆjdurhˆjg| }|durs|| d… }|durƒ| d|… } |
|
|||
|
|
d|… }
|
|||
|
|
|| } dgt |ƒ |
|
|||
|
|
}
|
|||
|
|
|dur | d|… } |
|
|||
|
|
d|… }
|
|||
|
|
| |
|
|||
|
|
dœS )a/
|
|||
|
|
Tokenize a row of the dataset.
|
|||
|
|
|
|||
|
|
Args:
|
|||
|
|
features (`dict[str, str]`):
|
|||
|
|
Row of the dataset, should contain the keys `"prompt"`, `"completions"`, and `"labels"`.
|
|||
|
|
tokenizer (`PreTrainedTokenizerBase`):
|
|||
|
|
Tokenizer used to process the data.
|
|||
|
|
step_separator (`str`):
|
|||
|
|
Separator between steps in the completion.
|
|||
|
|
max_length (`int` or `None`):
|
|||
|
|
Maximum length of the sequences (prompt + completion). If `None`, the sequences are not truncated.
|
|||
|
|
max_prompt_length (`int` or `None`):
|
|||
|
|
Maximum length of the prompt. If `None`, the prompt is not truncated.
|
|||
|
|
max_completion_length (`int` or `None`):
|
|||
|
|
Maximum length of the completion sequences. If `None`, the completion sequences are not truncated.
|
|||
|
|
train_on_last_step_only (`bool`):
|
|||
|
|
Whether to train only on the last step. If `True`, the labels are `-100` for all tokens except the last
|
|||
|
|
token of the completion.
|
|||
|
|
is_eval (`bool`):
|
|||
|
|
Whether the function is used to tokenize samples from a training or an evaluation dataset. Used only if
|
|||
|
|
`train_on_last_step_only` is set to `True`.
|
|||
|
|
|
|||
|
|
Returns:
|
|||
|
|
`dict[str, list[int]]`:
|
|||
|
|
Tokenized sequences with the keys `"input_ids"`, and `"labels".
|
|||
|
|
|
|||
|
|
Example:
|
|||
|
|
```python
|
|||
|
|
>>> from transformers import AutoTokenizer
|
|||
|
|
|
|||
|
|
>>> tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-0.5B")
|
|||
|
|
>>> features = {
|
|||
|
|
... "prompt": "Which number is larger, 9.8 or 9.11?",
|
|||
|
|
... "completions": ["11 is greater than 8.", "Hence, 9.11 > 9.8."],
|
|||
|
|
... "labels": [True, False],
|
|||
|
|
... }
|
|||
|
|
>>> PRMTrainer.tokenize_row(
|
|||
|
|
... features, tokenizer, "\n", max_completion_length=None, train_on_last_step_only=False, is_eval=False
|
|||
|
|
... )
|
|||
|
|
{'input_ids': [23085, 1372, 374, 8131, 11, 220, 24, 13, 23, 476, 220, 24, 13, 16, 16, 30, 16, 16, 374, 7046, 1091, 220, 23, 13, 198, 39, 763, 11, 220, 24, 13, 16, 16, 861, 220, 24, 13, 23, 13, 198],
|
|||
|
|
'labels': [-100, -100, -100, -100, -100, -100, -100, -100, 1, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, 0]}
|
|||
|
|
```
|
|||
|
|
ÚpromptF©Úadd_special_tokensr% c s g | ]
|
|||
|
|
}ˆ |d d�d ‘qS )FrD r% rR ©Ú.0Ú
|
|||
|
|
completion)r& rR rS Ú
|
|||
|
|
<listcomp>7 s ÿz3_UnslothPRMTrainer.tokenize_row.<locals>.<listcomp>Ú completionséœÿÿÿr) r< r7 c S s g | ]}t |ƒ‘qS rR )r )rG ÚlabelrR rR rS rI = ó c s g | ]}|ˆ ‘qS rR rR rF )Ú
|
|||
|
|
separator_idsrR rS rI A rM c S s( g | ]\}}d gt |ƒd |g ‘qS )rK r< )Úlen)rG rH rL rR rR rS rI D s ( N)r% r) )rO r Úencoder@ r2 r Ú bos_token_id)
|
|||
|
|
r r& rþ rú rû rü rÿ r' Ú
|
|||
|
|
prompt_idsÚcompletions_idsr) Úcompletion_idsr% rR )rN r& rS r9 þ s2 8
|
|||
|
|
ÿ*
|
|||
|
|
|
|||
|
|
z _UnslothPRMTrainer.tokenize_rowc sL | j jd u rt| j jƒj}n | j j d¡d }| j|d� tƒ ||¡ d S )Nú/r7 )Ú
|
|||
|
|
model_name) r rÙ r rz ÚnameÚsplitÚcreate_model_cardr Ú_save_checkpoint)r r ÚtrialrV r rR rS rZ ^ s
|
|||
|
|
z#_UnslothPRMTrainer._save_checkpointrV Ú dataset_nameÚtagsc C sä | ¡ sdS t| jjdƒr tj | jjj¡s | jjj}nd}|du r&tƒ }n
|
|||
|
|
t |t
|
|||
|
|
ƒr/|h}nt|ƒ}t| jjdƒr?| d¡ | | j
|
|||
|
|
¡ t d¡}t||| j||tƒ r]tjdur]tjjndd|dd� }| tj | jjd ¡¡ dS )
|
|||
|
|
aî
|
|||
|
|
Creates a draft of a model card using the information available to the `Trainer`.
|
|||
|
|
|
|||
|
|
Args:
|
|||
|
|
model_name (`str` or `None`, *optional*, defaults to `None`):
|
|||
|
|
Name of the model.
|
|||
|
|
dataset_name (`str` or `None`, *optional*, defaults to `None`):
|
|||
|
|
Name of the dataset used for training.
|
|||
|
|
tags (`str`, `list[str]` or `None`, *optional*, defaults to `None`):
|
|||
|
|
Tags to be associated with the model card.
|
|||
|
|
NÚ
|
|||
|
|
_name_or_pathÚunsloth_versionÚunslotha² @article{uesato2022solving,
|
|||
|
|
title = {{Solving Math Word Problems With Process- and Outcome-Based Feedback}},
|
|||
|
|
author = {Uesato, Jonathan and Kushman, Nate and Kumar, Ramana and Song, Francis and Siegel, Noah and Wang, Lisa and Creswell, Antonia and Irving, Geoffrey and Higgins, Irina},
|
|||
|
|
year = 2022,
|
|||
|
|
journal = {arXiv preprint arXiv:2211.14275}
|
|||
|
|
}ÚPRMzBSolving math word problems with process-and outcome-based feedback) Ú
|
|||
|
|
base_modelrV rÙ r\ r] Ú wandb_urlÚ trainer_nameÚtrainer_citationÚ paper_titlez README.md)Úis_world_process_zeror= r Úconfigr% ÚpathÚisdirr^ Úsetr0 ÚstrÚaddÚupdater> r' Údedentr rÙ r# ÚwandbÚrunÚurlÚsaveÚjoinr rz )r rV r\ r] rb ÚcitationÚ
|
|||
|
|
model_cardrR rR rS rY f s4
|
|||
|
|
|
|||
|
|
|
|||
|
|
÷ z$_UnslothPRMTrainer.create_model_card) NNNNNNNNNr NN)NNN)$r r r
|
|||
|
|
r r> r r r r$ ÚModuler r
|
|||
|
|
r Údictrl r r r r r r r2 r Útupler( rÊ Ú OptimizerÚ lr_schedulerÚLambdaLRr r Ú staticmethodr9 rZ rY r rR rR r rS r ƒ sn îþýüûúÿù
|
|||
|
|
ö õ
|
|||
|
|
ô
|
|||
|
|
óïîv
|
|||
|
|
_
|
|||
|
|
üþýür c s8 e Zd ZdZ d‡ fdd„ Z‡ ZS )ÚUnslothPRMTrainera@
|
|||
|
|
|
|||
|
|
Initialize PRMTrainer.
|
|||
|
|
|
|||
|
|
Args:
|
|||
|
|
model (`transformers.PreTrainedModel`):
|