Upload final model (step 78) and all checkpoints at 2025-07-16T19:21:53.266656
Browse files- .gitattributes +1 -0
- README.md +7 -0
- checkpoints/checkpoint-1.pt +3 -0
- checkpoints/checkpoint-78.pt +3 -0
- config.json +12 -0
- data.yaml +14 -0
- generation_config.json +4 -0
- model.safetensors +3 -0
- model.yaml +6 -0
- special_tokens_map.json +24 -0
- step0/.locks/models--EleutherAI--pythia-14m/1d531ed95e6a866521b683d8054fdf83ed660886e5cdf24c83552a009101aa6a.lock +0 -0
- step0/.locks/models--EleutherAI--pythia-14m/3068f16784f184f2b6a048f1c242a5040fde4916.lock +0 -0
- step0/.locks/models--EleutherAI--pythia-14m/a7e13441cbf9bd1527e87f7fe1abc961d8a83ded.lock +0 -0
- step0/models--EleutherAI--pythia-14m/.no_exist/5e79bd3bc1ebd3f03db0af32781a176d10237d60/model.safetensors +0 -0
- step0/models--EleutherAI--pythia-14m/.no_exist/5e79bd3bc1ebd3f03db0af32781a176d10237d60/model.safetensors.index.json +0 -0
- step0/models--EleutherAI--pythia-14m/.no_exist/f33025648652797a390d8c54835273845b437161/adapter_config.json +0 -0
- step0/models--EleutherAI--pythia-14m/blobs/1d531ed95e6a866521b683d8054fdf83ed660886e5cdf24c83552a009101aa6a +3 -0
- step0/models--EleutherAI--pythia-14m/blobs/3068f16784f184f2b6a048f1c242a5040fde4916 +6 -0
- step0/models--EleutherAI--pythia-14m/blobs/a7e13441cbf9bd1527e87f7fe1abc961d8a83ded +25 -0
- step0/models--EleutherAI--pythia-14m/refs/main +1 -0
- step0/models--EleutherAI--pythia-14m/refs/step0 +1 -0
- step0/models--EleutherAI--pythia-14m/snapshots/5e79bd3bc1ebd3f03db0af32781a176d10237d60/config.json +25 -0
- step0/models--EleutherAI--pythia-14m/snapshots/5e79bd3bc1ebd3f03db0af32781a176d10237d60/generation_config.json +6 -0
- step0/models--EleutherAI--pythia-14m/snapshots/5e79bd3bc1ebd3f03db0af32781a176d10237d60/pytorch_model.bin +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +222 -0
- training.yaml +140 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
step0/models--EleutherAI--pythia-14m/blobs/1d531ed95e6a866521b683d8054fdf83ed660886e5cdf24c83552a009101aa6a filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# EleutherAI/pythia-14m_distilled_from_pythia-14m Checkpoints
|
| 2 |
+
|
| 3 |
+
This repository contains the final trained model and intermediate checkpoints.
|
| 4 |
+
|
| 5 |
+
- The main directory contains the fully trained model (checkpoint 0).
|
| 6 |
+
- The `checkpoints` directory contains all intermediate checkpoints.
|
| 7 |
+
|
checkpoints/checkpoint-1.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:61a77182bbaed58df9c3149b1209ef372d1d4d92aa1dcce2ad2e21e0f9db4424
|
| 3 |
+
size 110369580
|
checkpoints/checkpoint-78.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:773b42e1c4be67f2e6a19749bf3dd991ce65a2c9cd997a5a090009dd85d28c08
|
| 3 |
+
size 110369911
|
config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"HFHookedTransformer"
|
| 4 |
+
],
|
| 5 |
+
"hidden_size": 128,
|
| 6 |
+
"n_ctx": 2048,
|
| 7 |
+
"num_attention_heads": 4,
|
| 8 |
+
"num_hidden_layers": 6,
|
| 9 |
+
"torch_dtype": "bfloat16",
|
| 10 |
+
"transformers_version": "4.45.2",
|
| 11 |
+
"vocab_size": 50304
|
| 12 |
+
}
|
data.yaml
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
task: pile10k
|
| 2 |
+
task_config: '{''task'': ''pile10k'', ''dataset_path'': ''timaeus/dsir-pile-10k'',
|
| 3 |
+
''output_type'': ''loglikelihood_rolling'', ''training_split'': ''train'', ''test_split'':
|
| 4 |
+
''train'', ''validation_split'': None, ''doc_to_target'': ''{{contents}}'', ''doc_to_text'':
|
| 5 |
+
''{{contents}}'', ''process_docs'': None, ''process_results'': None, ''should_decontaminate'':
|
| 6 |
+
True, ''doc_to_decontamination_query'': ''{{page}}'', ''metric_list'': [{''metric'':
|
| 7 |
+
''word_perplexity''}, {''metric'': ''byte_perplexity''}, {''metric'': ''bits_per_byte''}],
|
| 8 |
+
''metadata'': {''version'': 1.0}, ''dataset_kwargs'': {''trust_remote_code'': True}}'
|
| 9 |
+
dataset_split: training_split
|
| 10 |
+
include_path: shared/aether/config/tasks/
|
| 11 |
+
save_path: .//data/
|
| 12 |
+
force_reload: 'False'
|
| 13 |
+
truncate: auto
|
| 14 |
+
prefix: ''
|
generation_config.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"transformers_version": "4.45.2"
|
| 4 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4e8bbb7fd722696d4d3e4a3e5472e8db98f4577219cb9db57afa513599b33c33
|
| 3 |
+
size 53797624
|
model.yaml
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
dtype: torch.bfloat16
|
| 2 |
+
implementation: pythia
|
| 3 |
+
model_name: EleutherAI/pythia-14m
|
| 4 |
+
n_ctx: '2048'
|
| 5 |
+
n_heads: '4'
|
| 6 |
+
n_layers: '6'
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|endoftext|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|endoftext|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "<|endoftext|>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<|endoftext|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
step0/.locks/models--EleutherAI--pythia-14m/1d531ed95e6a866521b683d8054fdf83ed660886e5cdf24c83552a009101aa6a.lock
ADDED
|
File without changes
|
step0/.locks/models--EleutherAI--pythia-14m/3068f16784f184f2b6a048f1c242a5040fde4916.lock
ADDED
|
File without changes
|
step0/.locks/models--EleutherAI--pythia-14m/a7e13441cbf9bd1527e87f7fe1abc961d8a83ded.lock
ADDED
|
File without changes
|
step0/models--EleutherAI--pythia-14m/.no_exist/5e79bd3bc1ebd3f03db0af32781a176d10237d60/model.safetensors
ADDED
|
File without changes
|
step0/models--EleutherAI--pythia-14m/.no_exist/5e79bd3bc1ebd3f03db0af32781a176d10237d60/model.safetensors.index.json
ADDED
|
File without changes
|
step0/models--EleutherAI--pythia-14m/.no_exist/f33025648652797a390d8c54835273845b437161/adapter_config.json
ADDED
|
File without changes
|
step0/models--EleutherAI--pythia-14m/blobs/1d531ed95e6a866521b683d8054fdf83ed660886e5cdf24c83552a009101aa6a
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1d531ed95e6a866521b683d8054fdf83ed660886e5cdf24c83552a009101aa6a
|
| 3 |
+
size 53331721
|
step0/models--EleutherAI--pythia-14m/blobs/3068f16784f184f2b6a048f1c242a5040fde4916
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"eos_token_id": 0,
|
| 5 |
+
"transformers_version": "4.29.2"
|
| 6 |
+
}
|
step0/models--EleutherAI--pythia-14m/blobs/a7e13441cbf9bd1527e87f7fe1abc961d8a83ded
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"GPTNeoXForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"bos_token_id": 0,
|
| 6 |
+
"classifier_dropout": 0.1,
|
| 7 |
+
"eos_token_id": 0,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_size": 128,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 512,
|
| 12 |
+
"layer_norm_eps": 1e-05,
|
| 13 |
+
"max_position_embeddings": 2048,
|
| 14 |
+
"model_type": "gpt_neox",
|
| 15 |
+
"num_attention_heads": 4,
|
| 16 |
+
"num_hidden_layers": 6,
|
| 17 |
+
"rotary_emb_base": 10000,
|
| 18 |
+
"rotary_pct": 0.25,
|
| 19 |
+
"tie_word_embeddings": false,
|
| 20 |
+
"torch_dtype": "float16",
|
| 21 |
+
"transformers_version": "4.29.2",
|
| 22 |
+
"use_cache": true,
|
| 23 |
+
"use_parallel_residual": true,
|
| 24 |
+
"vocab_size": 50304
|
| 25 |
+
}
|
step0/models--EleutherAI--pythia-14m/refs/main
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
f33025648652797a390d8c54835273845b437161
|
step0/models--EleutherAI--pythia-14m/refs/step0
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
5e79bd3bc1ebd3f03db0af32781a176d10237d60
|
step0/models--EleutherAI--pythia-14m/snapshots/5e79bd3bc1ebd3f03db0af32781a176d10237d60/config.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"GPTNeoXForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"bos_token_id": 0,
|
| 6 |
+
"classifier_dropout": 0.1,
|
| 7 |
+
"eos_token_id": 0,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_size": 128,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 512,
|
| 12 |
+
"layer_norm_eps": 1e-05,
|
| 13 |
+
"max_position_embeddings": 2048,
|
| 14 |
+
"model_type": "gpt_neox",
|
| 15 |
+
"num_attention_heads": 4,
|
| 16 |
+
"num_hidden_layers": 6,
|
| 17 |
+
"rotary_emb_base": 10000,
|
| 18 |
+
"rotary_pct": 0.25,
|
| 19 |
+
"tie_word_embeddings": false,
|
| 20 |
+
"torch_dtype": "float16",
|
| 21 |
+
"transformers_version": "4.29.2",
|
| 22 |
+
"use_cache": true,
|
| 23 |
+
"use_parallel_residual": true,
|
| 24 |
+
"vocab_size": 50304
|
| 25 |
+
}
|
step0/models--EleutherAI--pythia-14m/snapshots/5e79bd3bc1ebd3f03db0af32781a176d10237d60/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"eos_token_id": 0,
|
| 5 |
+
"transformers_version": "4.29.2"
|
| 6 |
+
}
|
step0/models--EleutherAI--pythia-14m/snapshots/5e79bd3bc1ebd3f03db0af32781a176d10237d60/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1d531ed95e6a866521b683d8054fdf83ed660886e5cdf24c83552a009101aa6a
|
| 3 |
+
size 53331721
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,222 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": false,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<|endoftext|>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<|padding|>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"50254": {
|
| 23 |
+
"content": " ",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": true,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": false
|
| 29 |
+
},
|
| 30 |
+
"50255": {
|
| 31 |
+
"content": " ",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": false
|
| 37 |
+
},
|
| 38 |
+
"50256": {
|
| 39 |
+
"content": " ",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": true,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": false
|
| 45 |
+
},
|
| 46 |
+
"50257": {
|
| 47 |
+
"content": " ",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": true,
|
| 50 |
+
"rstrip": false,
|
| 51 |
+
"single_word": false,
|
| 52 |
+
"special": false
|
| 53 |
+
},
|
| 54 |
+
"50258": {
|
| 55 |
+
"content": " ",
|
| 56 |
+
"lstrip": false,
|
| 57 |
+
"normalized": true,
|
| 58 |
+
"rstrip": false,
|
| 59 |
+
"single_word": false,
|
| 60 |
+
"special": false
|
| 61 |
+
},
|
| 62 |
+
"50259": {
|
| 63 |
+
"content": " ",
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"normalized": true,
|
| 66 |
+
"rstrip": false,
|
| 67 |
+
"single_word": false,
|
| 68 |
+
"special": false
|
| 69 |
+
},
|
| 70 |
+
"50260": {
|
| 71 |
+
"content": " ",
|
| 72 |
+
"lstrip": false,
|
| 73 |
+
"normalized": true,
|
| 74 |
+
"rstrip": false,
|
| 75 |
+
"single_word": false,
|
| 76 |
+
"special": false
|
| 77 |
+
},
|
| 78 |
+
"50261": {
|
| 79 |
+
"content": " ",
|
| 80 |
+
"lstrip": false,
|
| 81 |
+
"normalized": true,
|
| 82 |
+
"rstrip": false,
|
| 83 |
+
"single_word": false,
|
| 84 |
+
"special": false
|
| 85 |
+
},
|
| 86 |
+
"50262": {
|
| 87 |
+
"content": " ",
|
| 88 |
+
"lstrip": false,
|
| 89 |
+
"normalized": true,
|
| 90 |
+
"rstrip": false,
|
| 91 |
+
"single_word": false,
|
| 92 |
+
"special": false
|
| 93 |
+
},
|
| 94 |
+
"50263": {
|
| 95 |
+
"content": " ",
|
| 96 |
+
"lstrip": false,
|
| 97 |
+
"normalized": true,
|
| 98 |
+
"rstrip": false,
|
| 99 |
+
"single_word": false,
|
| 100 |
+
"special": false
|
| 101 |
+
},
|
| 102 |
+
"50264": {
|
| 103 |
+
"content": " ",
|
| 104 |
+
"lstrip": false,
|
| 105 |
+
"normalized": true,
|
| 106 |
+
"rstrip": false,
|
| 107 |
+
"single_word": false,
|
| 108 |
+
"special": false
|
| 109 |
+
},
|
| 110 |
+
"50265": {
|
| 111 |
+
"content": " ",
|
| 112 |
+
"lstrip": false,
|
| 113 |
+
"normalized": true,
|
| 114 |
+
"rstrip": false,
|
| 115 |
+
"single_word": false,
|
| 116 |
+
"special": false
|
| 117 |
+
},
|
| 118 |
+
"50266": {
|
| 119 |
+
"content": " ",
|
| 120 |
+
"lstrip": false,
|
| 121 |
+
"normalized": true,
|
| 122 |
+
"rstrip": false,
|
| 123 |
+
"single_word": false,
|
| 124 |
+
"special": false
|
| 125 |
+
},
|
| 126 |
+
"50267": {
|
| 127 |
+
"content": " ",
|
| 128 |
+
"lstrip": false,
|
| 129 |
+
"normalized": true,
|
| 130 |
+
"rstrip": false,
|
| 131 |
+
"single_word": false,
|
| 132 |
+
"special": false
|
| 133 |
+
},
|
| 134 |
+
"50268": {
|
| 135 |
+
"content": " ",
|
| 136 |
+
"lstrip": false,
|
| 137 |
+
"normalized": true,
|
| 138 |
+
"rstrip": false,
|
| 139 |
+
"single_word": false,
|
| 140 |
+
"special": false
|
| 141 |
+
},
|
| 142 |
+
"50269": {
|
| 143 |
+
"content": " ",
|
| 144 |
+
"lstrip": false,
|
| 145 |
+
"normalized": true,
|
| 146 |
+
"rstrip": false,
|
| 147 |
+
"single_word": false,
|
| 148 |
+
"special": false
|
| 149 |
+
},
|
| 150 |
+
"50270": {
|
| 151 |
+
"content": " ",
|
| 152 |
+
"lstrip": false,
|
| 153 |
+
"normalized": true,
|
| 154 |
+
"rstrip": false,
|
| 155 |
+
"single_word": false,
|
| 156 |
+
"special": false
|
| 157 |
+
},
|
| 158 |
+
"50271": {
|
| 159 |
+
"content": " ",
|
| 160 |
+
"lstrip": false,
|
| 161 |
+
"normalized": true,
|
| 162 |
+
"rstrip": false,
|
| 163 |
+
"single_word": false,
|
| 164 |
+
"special": false
|
| 165 |
+
},
|
| 166 |
+
"50272": {
|
| 167 |
+
"content": " ",
|
| 168 |
+
"lstrip": false,
|
| 169 |
+
"normalized": true,
|
| 170 |
+
"rstrip": false,
|
| 171 |
+
"single_word": false,
|
| 172 |
+
"special": false
|
| 173 |
+
},
|
| 174 |
+
"50273": {
|
| 175 |
+
"content": " ",
|
| 176 |
+
"lstrip": false,
|
| 177 |
+
"normalized": true,
|
| 178 |
+
"rstrip": false,
|
| 179 |
+
"single_word": false,
|
| 180 |
+
"special": false
|
| 181 |
+
},
|
| 182 |
+
"50274": {
|
| 183 |
+
"content": " ",
|
| 184 |
+
"lstrip": false,
|
| 185 |
+
"normalized": true,
|
| 186 |
+
"rstrip": false,
|
| 187 |
+
"single_word": false,
|
| 188 |
+
"special": false
|
| 189 |
+
},
|
| 190 |
+
"50275": {
|
| 191 |
+
"content": " ",
|
| 192 |
+
"lstrip": false,
|
| 193 |
+
"normalized": true,
|
| 194 |
+
"rstrip": false,
|
| 195 |
+
"single_word": false,
|
| 196 |
+
"special": false
|
| 197 |
+
},
|
| 198 |
+
"50276": {
|
| 199 |
+
"content": " ",
|
| 200 |
+
"lstrip": false,
|
| 201 |
+
"normalized": true,
|
| 202 |
+
"rstrip": false,
|
| 203 |
+
"single_word": false,
|
| 204 |
+
"special": false
|
| 205 |
+
},
|
| 206 |
+
"50277": {
|
| 207 |
+
"content": "<PAD>",
|
| 208 |
+
"lstrip": false,
|
| 209 |
+
"normalized": false,
|
| 210 |
+
"rstrip": false,
|
| 211 |
+
"single_word": false,
|
| 212 |
+
"special": true
|
| 213 |
+
}
|
| 214 |
+
},
|
| 215 |
+
"bos_token": "<|endoftext|>",
|
| 216 |
+
"clean_up_tokenization_spaces": true,
|
| 217 |
+
"eos_token": "<|endoftext|>",
|
| 218 |
+
"model_max_length": 2048,
|
| 219 |
+
"pad_token": "<|endoftext|>",
|
| 220 |
+
"tokenizer_class": "GPTNeoXTokenizer",
|
| 221 |
+
"unk_token": "<|endoftext|>"
|
| 222 |
+
}
|
training.yaml
ADDED
|
@@ -0,0 +1,140 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
output_dir: checkpoints/EleutherAI/pythia-14m
|
| 2 |
+
overwrite_output_dir: 'False'
|
| 3 |
+
do_train: 'False'
|
| 4 |
+
do_eval: 'False'
|
| 5 |
+
do_predict: 'False'
|
| 6 |
+
eval_strategy: IntervalStrategy.NO
|
| 7 |
+
prediction_loss_only: 'False'
|
| 8 |
+
per_device_train_batch_size: '8'
|
| 9 |
+
per_device_eval_batch_size: '8'
|
| 10 |
+
per_gpu_train_batch_size: None
|
| 11 |
+
per_gpu_eval_batch_size: None
|
| 12 |
+
gradient_accumulation_steps: '8'
|
| 13 |
+
eval_accumulation_steps: None
|
| 14 |
+
eval_delay: '0'
|
| 15 |
+
torch_empty_cache_steps: None
|
| 16 |
+
learning_rate: '0.001'
|
| 17 |
+
weight_decay: '0.0'
|
| 18 |
+
adam_beta1: '0.9'
|
| 19 |
+
adam_beta2: '0.999'
|
| 20 |
+
adam_epsilon: 1e-08
|
| 21 |
+
max_grad_norm: '1.0'
|
| 22 |
+
num_train_epochs: '3.0'
|
| 23 |
+
max_steps: '-1'
|
| 24 |
+
lr_scheduler_type: SchedulerType.LINEAR
|
| 25 |
+
lr_scheduler_kwargs: '{}'
|
| 26 |
+
warmup_ratio: '0.0'
|
| 27 |
+
warmup_steps: '0'
|
| 28 |
+
log_level: warning
|
| 29 |
+
log_level_replica: warning
|
| 30 |
+
log_on_each_node: 'True'
|
| 31 |
+
logging_dir: checkpoints/EleutherAI/pythia-14m/runs/Jul16_19-19-58_0082549b2b6f
|
| 32 |
+
logging_strategy: IntervalStrategy.STEPS
|
| 33 |
+
logging_first_step: 'True'
|
| 34 |
+
logging_steps: '250'
|
| 35 |
+
logging_nan_inf_filter: 'True'
|
| 36 |
+
save_strategy: IntervalStrategy.STEPS
|
| 37 |
+
save_steps: '300'
|
| 38 |
+
save_total_limit: None
|
| 39 |
+
save_safetensors: 'True'
|
| 40 |
+
save_on_each_node: 'False'
|
| 41 |
+
save_only_model: 'False'
|
| 42 |
+
restore_callback_states_from_checkpoint: 'False'
|
| 43 |
+
no_cuda: 'False'
|
| 44 |
+
use_cpu: 'False'
|
| 45 |
+
use_mps_device: 'False'
|
| 46 |
+
seed: '42'
|
| 47 |
+
data_seed: None
|
| 48 |
+
jit_mode_eval: 'False'
|
| 49 |
+
use_ipex: 'False'
|
| 50 |
+
bf16: 'False'
|
| 51 |
+
fp16: 'False'
|
| 52 |
+
fp16_opt_level: O1
|
| 53 |
+
half_precision_backend: auto
|
| 54 |
+
bf16_full_eval: 'False'
|
| 55 |
+
fp16_full_eval: 'False'
|
| 56 |
+
tf32: None
|
| 57 |
+
local_rank: '0'
|
| 58 |
+
ddp_backend: None
|
| 59 |
+
tpu_num_cores: None
|
| 60 |
+
tpu_metrics_debug: 'False'
|
| 61 |
+
debug: '[]'
|
| 62 |
+
dataloader_drop_last: 'False'
|
| 63 |
+
eval_steps: None
|
| 64 |
+
dataloader_num_workers: '0'
|
| 65 |
+
dataloader_prefetch_factor: None
|
| 66 |
+
past_index: '-1'
|
| 67 |
+
run_name: EleutherAI/pythia-14m_distilled_from_pythia-14m
|
| 68 |
+
disable_tqdm: 'False'
|
| 69 |
+
remove_unused_columns: 'False'
|
| 70 |
+
label_names: '[''input_ids'']'
|
| 71 |
+
load_best_model_at_end: 'False'
|
| 72 |
+
metric_for_best_model: None
|
| 73 |
+
greater_is_better: None
|
| 74 |
+
ignore_data_skip: 'False'
|
| 75 |
+
fsdp: '[]'
|
| 76 |
+
fsdp_min_num_params: '0'
|
| 77 |
+
fsdp_config: '{''min_num_params'': 0, ''xla'': False, ''xla_fsdp_v2'': False, ''xla_fsdp_grad_ckpt'':
|
| 78 |
+
False}'
|
| 79 |
+
fsdp_transformer_layer_cls_to_wrap: None
|
| 80 |
+
accelerator_config: '{''split_batches'': False, ''dispatch_batches'': None, ''even_batches'':
|
| 81 |
+
True, ''use_seedable_sampler'': True, ''non_blocking'': False, ''gradient_accumulation_kwargs'':
|
| 82 |
+
None, ''use_configured_state'': False}'
|
| 83 |
+
deepspeed: None
|
| 84 |
+
label_smoothing_factor: '0.0'
|
| 85 |
+
optim: OptimizerNames.ADAMW_TORCH
|
| 86 |
+
optim_args: None
|
| 87 |
+
adafactor: 'False'
|
| 88 |
+
group_by_length: 'False'
|
| 89 |
+
length_column_name: length
|
| 90 |
+
report_to: '[''wandb'']'
|
| 91 |
+
ddp_find_unused_parameters: None
|
| 92 |
+
ddp_bucket_cap_mb: None
|
| 93 |
+
ddp_broadcast_buffers: None
|
| 94 |
+
dataloader_pin_memory: 'True'
|
| 95 |
+
dataloader_persistent_workers: 'False'
|
| 96 |
+
skip_memory_metrics: 'True'
|
| 97 |
+
use_legacy_prediction_loop: 'False'
|
| 98 |
+
push_to_hub: 'True'
|
| 99 |
+
resume_from_checkpoint: None
|
| 100 |
+
hub_model_id: test-distillation
|
| 101 |
+
hub_strategy: HubStrategy.EVERY_SAVE
|
| 102 |
+
hub_token: None
|
| 103 |
+
hub_private_repo: 'False'
|
| 104 |
+
hub_always_push: 'False'
|
| 105 |
+
gradient_checkpointing: 'False'
|
| 106 |
+
gradient_checkpointing_kwargs: None
|
| 107 |
+
include_inputs_for_metrics: 'False'
|
| 108 |
+
eval_do_concat_batches: 'True'
|
| 109 |
+
fp16_backend: auto
|
| 110 |
+
evaluation_strategy: None
|
| 111 |
+
push_to_hub_model_id: None
|
| 112 |
+
push_to_hub_organization: None
|
| 113 |
+
push_to_hub_token: None
|
| 114 |
+
_n_gpu: '1'
|
| 115 |
+
mp_parameters: ''
|
| 116 |
+
auto_find_batch_size: 'False'
|
| 117 |
+
full_determinism: 'False'
|
| 118 |
+
torchdynamo: None
|
| 119 |
+
ray_scope: last
|
| 120 |
+
ddp_timeout: '1800'
|
| 121 |
+
torch_compile: 'False'
|
| 122 |
+
torch_compile_backend: None
|
| 123 |
+
torch_compile_mode: None
|
| 124 |
+
dispatch_batches: None
|
| 125 |
+
split_batches: None
|
| 126 |
+
include_tokens_per_second: 'False'
|
| 127 |
+
include_num_input_tokens_seen: 'False'
|
| 128 |
+
neftune_noise_alpha: None
|
| 129 |
+
optim_target_modules: None
|
| 130 |
+
batch_eval_metrics: 'False'
|
| 131 |
+
eval_on_start: 'False'
|
| 132 |
+
use_liger_kernel: 'False'
|
| 133 |
+
eval_use_gather_object: 'False'
|
| 134 |
+
checkpoints_dir: .//checkpoints/
|
| 135 |
+
init_step: '0'
|
| 136 |
+
save_log_steps: '250'
|
| 137 |
+
bucket_name: devinterp-language
|
| 138 |
+
s3_folder: checkpoints/tetrahedron-3m
|
| 139 |
+
delete_after_upload: 'False'
|
| 140 |
+
push_to_aws: 'False'
|