Upload folder using huggingface_hub
Browse files- checkpoint-100/config.json +34 -0
- checkpoint-100/generation_config.json +10 -0
- checkpoint-100/model.safetensors +3 -0
- checkpoint-100/optimizer.pt +3 -0
- checkpoint-100/rng_state.pth +3 -0
- checkpoint-100/scheduler.pt +3 -0
- checkpoint-100/tokenizer.json +127 -0
- checkpoint-100/tokenizer_config.json +8 -0
- checkpoint-100/trainer_state.json +104 -0
- checkpoint-100/training_args.bin +3 -0
- checkpoint-150/config.json +34 -0
- checkpoint-150/generation_config.json +10 -0
- checkpoint-150/model.safetensors +3 -0
- checkpoint-150/optimizer.pt +3 -0
- checkpoint-150/rng_state.pth +3 -0
- checkpoint-150/scheduler.pt +3 -0
- checkpoint-150/tokenizer.json +127 -0
- checkpoint-150/tokenizer_config.json +8 -0
- checkpoint-150/trainer_state.json +139 -0
- checkpoint-150/training_args.bin +3 -0
- checkpoint-160/config.json +34 -0
- checkpoint-160/generation_config.json +10 -0
- checkpoint-160/model.safetensors +3 -0
- checkpoint-160/optimizer.pt +3 -0
- checkpoint-160/rng_state.pth +3 -0
- checkpoint-160/scheduler.pt +3 -0
- checkpoint-160/tokenizer.json +127 -0
- checkpoint-160/tokenizer_config.json +8 -0
- checkpoint-160/trainer_state.json +146 -0
- checkpoint-160/training_args.bin +3 -0
- checkpoint-50/config.json +34 -0
- checkpoint-50/generation_config.json +10 -0
- checkpoint-50/model.safetensors +3 -0
- checkpoint-50/optimizer.pt +3 -0
- checkpoint-50/rng_state.pth +3 -0
- checkpoint-50/scheduler.pt +3 -0
- checkpoint-50/tokenizer.json +127 -0
- checkpoint-50/tokenizer_config.json +8 -0
- checkpoint-50/trainer_state.json +69 -0
- checkpoint-50/training_args.bin +3 -0
- config.json +34 -0
- generation_config.json +10 -0
- model.safetensors +3 -0
- tokenizer.json +127 -0
- tokenizer_config.json +8 -0
- training_args.bin +3 -0
checkpoint-100/config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_function": "gelu",
|
| 3 |
+
"add_cross_attention": false,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"GPT2LMHeadModel"
|
| 6 |
+
],
|
| 7 |
+
"attn_pdrop": 0.0,
|
| 8 |
+
"bos_token_id": 0,
|
| 9 |
+
"dtype": "float32",
|
| 10 |
+
"embd_pdrop": 0.0,
|
| 11 |
+
"eos_token_id": 0,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"layer_norm_epsilon": 1e-05,
|
| 14 |
+
"model_type": "gpt2",
|
| 15 |
+
"n_embd": 4,
|
| 16 |
+
"n_head": 1,
|
| 17 |
+
"n_inner": 8,
|
| 18 |
+
"n_layer": 1,
|
| 19 |
+
"n_positions": 16,
|
| 20 |
+
"pad_token_id": 1,
|
| 21 |
+
"reorder_and_upcast_attn": false,
|
| 22 |
+
"resid_pdrop": 0.0,
|
| 23 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 24 |
+
"scale_attn_weights": true,
|
| 25 |
+
"summary_activation": null,
|
| 26 |
+
"summary_first_dropout": 0.1,
|
| 27 |
+
"summary_proj_to_labels": true,
|
| 28 |
+
"summary_type": "cls_index",
|
| 29 |
+
"summary_use_proj": true,
|
| 30 |
+
"tie_word_embeddings": true,
|
| 31 |
+
"transformers_version": "5.12.0",
|
| 32 |
+
"use_cache": false,
|
| 33 |
+
"vocab_size": 32
|
| 34 |
+
}
|
checkpoint-100/generation_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"eos_token_id": 0,
|
| 5 |
+
"output_attentions": false,
|
| 6 |
+
"output_hidden_states": false,
|
| 7 |
+
"pad_token_id": 1,
|
| 8 |
+
"transformers_version": "5.12.0",
|
| 9 |
+
"use_cache": true
|
| 10 |
+
}
|
checkpoint-100/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:97d58f75447644ab0a89da320bf0a643d89245888b0abc87d8ed748a356f6e44
|
| 3 |
+
size 2888
|
checkpoint-100/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:63c545cb06ad9230bb92b6516878010eec30cac152dfa2df4bdd3c87aae9312a
|
| 3 |
+
size 16383
|
checkpoint-100/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:799af21e8c98b5b33efb40e1806882d89f329486619fd8f7f6c267e08bc7954e
|
| 3 |
+
size 14455
|
checkpoint-100/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3a3ab3904598e966007e85c80038c56261c305f0a5532f93501e4eb1deb56b4a
|
| 3 |
+
size 1465
|
checkpoint-100/tokenizer.json
ADDED
|
@@ -0,0 +1,127 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"version": "1.0",
|
| 3 |
+
"truncation": {
|
| 4 |
+
"direction": "Right",
|
| 5 |
+
"max_length": 16,
|
| 6 |
+
"strategy": "LongestFirst",
|
| 7 |
+
"stride": 0
|
| 8 |
+
},
|
| 9 |
+
"padding": null,
|
| 10 |
+
"added_tokens": [
|
| 11 |
+
{
|
| 12 |
+
"id": 0,
|
| 13 |
+
"content": "<|endoftext|>",
|
| 14 |
+
"single_word": false,
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"id": 1,
|
| 22 |
+
"content": "<|pad|>",
|
| 23 |
+
"single_word": false,
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"special": true
|
| 28 |
+
}
|
| 29 |
+
],
|
| 30 |
+
"normalizer": null,
|
| 31 |
+
"pre_tokenizer": {
|
| 32 |
+
"type": "ByteLevel",
|
| 33 |
+
"add_prefix_space": true,
|
| 34 |
+
"trim_offsets": true,
|
| 35 |
+
"use_regex": true
|
| 36 |
+
},
|
| 37 |
+
"post_processor": {
|
| 38 |
+
"type": "TemplateProcessing",
|
| 39 |
+
"single": [
|
| 40 |
+
{
|
| 41 |
+
"Sequence": {
|
| 42 |
+
"id": "A",
|
| 43 |
+
"type_id": 0
|
| 44 |
+
}
|
| 45 |
+
}
|
| 46 |
+
],
|
| 47 |
+
"pair": [
|
| 48 |
+
{
|
| 49 |
+
"Sequence": {
|
| 50 |
+
"id": "A",
|
| 51 |
+
"type_id": 0
|
| 52 |
+
}
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"Sequence": {
|
| 56 |
+
"id": "B",
|
| 57 |
+
"type_id": 1
|
| 58 |
+
}
|
| 59 |
+
}
|
| 60 |
+
],
|
| 61 |
+
"special_tokens": {}
|
| 62 |
+
},
|
| 63 |
+
"decoder": {
|
| 64 |
+
"type": "ByteLevel",
|
| 65 |
+
"add_prefix_space": true,
|
| 66 |
+
"trim_offsets": true,
|
| 67 |
+
"use_regex": true
|
| 68 |
+
},
|
| 69 |
+
"model": {
|
| 70 |
+
"type": "BPE",
|
| 71 |
+
"dropout": null,
|
| 72 |
+
"unk_token": null,
|
| 73 |
+
"continuing_subword_prefix": null,
|
| 74 |
+
"end_of_word_suffix": null,
|
| 75 |
+
"fuse_unk": false,
|
| 76 |
+
"byte_fallback": false,
|
| 77 |
+
"ignore_merges": false,
|
| 78 |
+
"vocab": {
|
| 79 |
+
"<|endoftext|>": 0,
|
| 80 |
+
"<|pad|>": 1,
|
| 81 |
+
"a": 2,
|
| 82 |
+
"b": 3,
|
| 83 |
+
"c": 4,
|
| 84 |
+
"d": 5,
|
| 85 |
+
"e": 6,
|
| 86 |
+
"f": 7,
|
| 87 |
+
"g": 8,
|
| 88 |
+
"h": 9,
|
| 89 |
+
"i": 10,
|
| 90 |
+
"j": 11,
|
| 91 |
+
"k": 12,
|
| 92 |
+
"l": 13,
|
| 93 |
+
"m": 14,
|
| 94 |
+
"n": 15,
|
| 95 |
+
"o": 16,
|
| 96 |
+
"p": 17,
|
| 97 |
+
"q": 18,
|
| 98 |
+
"r": 19,
|
| 99 |
+
"s": 20,
|
| 100 |
+
"t": 21,
|
| 101 |
+
"u": 22,
|
| 102 |
+
"v": 23,
|
| 103 |
+
"w": 24,
|
| 104 |
+
"x": 25,
|
| 105 |
+
"y": 26,
|
| 106 |
+
"z": 27,
|
| 107 |
+
"Ġ": 28,
|
| 108 |
+
"Ġz": 29,
|
| 109 |
+
"Ġx": 30,
|
| 110 |
+
"Ġi": 31
|
| 111 |
+
},
|
| 112 |
+
"merges": [
|
| 113 |
+
[
|
| 114 |
+
"Ġ",
|
| 115 |
+
"z"
|
| 116 |
+
],
|
| 117 |
+
[
|
| 118 |
+
"Ġ",
|
| 119 |
+
"x"
|
| 120 |
+
],
|
| 121 |
+
[
|
| 122 |
+
"Ġ",
|
| 123 |
+
"i"
|
| 124 |
+
]
|
| 125 |
+
]
|
| 126 |
+
}
|
| 127 |
+
}
|
checkpoint-100/tokenizer_config.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"backend": "tokenizers",
|
| 3 |
+
"bos_token": "<|endoftext|>",
|
| 4 |
+
"eos_token": "<|endoftext|>",
|
| 5 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 6 |
+
"pad_token": "<|pad|>",
|
| 7 |
+
"tokenizer_class": "TokenizersBackend"
|
| 8 |
+
}
|
checkpoint-100/trainer_state.json
ADDED
|
@@ -0,0 +1,104 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 6.25,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 100,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.625,
|
| 14 |
+
"grad_norm": 0.13900995254516602,
|
| 15 |
+
"learning_rate": 0.009000000000000001,
|
| 16 |
+
"loss": 3.240981674194336,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 1.25,
|
| 21 |
+
"grad_norm": 0.10888686776161194,
|
| 22 |
+
"learning_rate": 0.0094,
|
| 23 |
+
"loss": 3.185182571411133,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 1.875,
|
| 28 |
+
"grad_norm": 0.10133716464042664,
|
| 29 |
+
"learning_rate": 0.008733333333333333,
|
| 30 |
+
"loss": 3.1393909454345703,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 2.5,
|
| 35 |
+
"grad_norm": 0.11951159685850143,
|
| 36 |
+
"learning_rate": 0.008066666666666666,
|
| 37 |
+
"loss": 3.1178558349609373,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 3.125,
|
| 42 |
+
"grad_norm": 0.07364343106746674,
|
| 43 |
+
"learning_rate": 0.0074,
|
| 44 |
+
"loss": 3.1153308868408205,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 3.75,
|
| 49 |
+
"grad_norm": 0.11443202942609787,
|
| 50 |
+
"learning_rate": 0.006733333333333333,
|
| 51 |
+
"loss": 3.111285591125488,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 4.375,
|
| 56 |
+
"grad_norm": 0.13409413397312164,
|
| 57 |
+
"learning_rate": 0.006066666666666667,
|
| 58 |
+
"loss": 3.107038116455078,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 5.0,
|
| 63 |
+
"grad_norm": 0.12714578211307526,
|
| 64 |
+
"learning_rate": 0.0054,
|
| 65 |
+
"loss": 3.1068656921386717,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 5.625,
|
| 70 |
+
"grad_norm": 0.11183512210845947,
|
| 71 |
+
"learning_rate": 0.004733333333333333,
|
| 72 |
+
"loss": 3.1074026107788084,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 6.25,
|
| 77 |
+
"grad_norm": 0.10536977648735046,
|
| 78 |
+
"learning_rate": 0.004066666666666667,
|
| 79 |
+
"loss": 3.1052799224853516,
|
| 80 |
+
"step": 100
|
| 81 |
+
}
|
| 82 |
+
],
|
| 83 |
+
"logging_steps": 10,
|
| 84 |
+
"max_steps": 160,
|
| 85 |
+
"num_input_tokens_seen": 0,
|
| 86 |
+
"num_train_epochs": 10,
|
| 87 |
+
"save_steps": 50,
|
| 88 |
+
"stateful_callbacks": {
|
| 89 |
+
"TrainerControl": {
|
| 90 |
+
"args": {
|
| 91 |
+
"should_epoch_stop": false,
|
| 92 |
+
"should_evaluate": false,
|
| 93 |
+
"should_log": false,
|
| 94 |
+
"should_save": true,
|
| 95 |
+
"should_training_stop": false
|
| 96 |
+
},
|
| 97 |
+
"attributes": {}
|
| 98 |
+
}
|
| 99 |
+
},
|
| 100 |
+
"total_flos": 108103680.0,
|
| 101 |
+
"train_batch_size": 64,
|
| 102 |
+
"trial_name": null,
|
| 103 |
+
"trial_params": null
|
| 104 |
+
}
|
checkpoint-100/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:850fcbfdd316ee92f254e09ea6a5d1c6e9cfa06bc4a892af59b8839023c9b6df
|
| 3 |
+
size 5137
|
checkpoint-150/config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_function": "gelu",
|
| 3 |
+
"add_cross_attention": false,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"GPT2LMHeadModel"
|
| 6 |
+
],
|
| 7 |
+
"attn_pdrop": 0.0,
|
| 8 |
+
"bos_token_id": 0,
|
| 9 |
+
"dtype": "float32",
|
| 10 |
+
"embd_pdrop": 0.0,
|
| 11 |
+
"eos_token_id": 0,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"layer_norm_epsilon": 1e-05,
|
| 14 |
+
"model_type": "gpt2",
|
| 15 |
+
"n_embd": 4,
|
| 16 |
+
"n_head": 1,
|
| 17 |
+
"n_inner": 8,
|
| 18 |
+
"n_layer": 1,
|
| 19 |
+
"n_positions": 16,
|
| 20 |
+
"pad_token_id": 1,
|
| 21 |
+
"reorder_and_upcast_attn": false,
|
| 22 |
+
"resid_pdrop": 0.0,
|
| 23 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 24 |
+
"scale_attn_weights": true,
|
| 25 |
+
"summary_activation": null,
|
| 26 |
+
"summary_first_dropout": 0.1,
|
| 27 |
+
"summary_proj_to_labels": true,
|
| 28 |
+
"summary_type": "cls_index",
|
| 29 |
+
"summary_use_proj": true,
|
| 30 |
+
"tie_word_embeddings": true,
|
| 31 |
+
"transformers_version": "5.12.0",
|
| 32 |
+
"use_cache": false,
|
| 33 |
+
"vocab_size": 32
|
| 34 |
+
}
|
checkpoint-150/generation_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"eos_token_id": 0,
|
| 5 |
+
"output_attentions": false,
|
| 6 |
+
"output_hidden_states": false,
|
| 7 |
+
"pad_token_id": 1,
|
| 8 |
+
"transformers_version": "5.12.0",
|
| 9 |
+
"use_cache": true
|
| 10 |
+
}
|
checkpoint-150/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:826df0510322619d1664ed9c1c42dbc13c223bd1b49121c6fe9c124888ee4912
|
| 3 |
+
size 2888
|
checkpoint-150/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:59c6abe18a203b57f07e4763bfa9a27de2d826ecb79afaca0a4c4f40e5b481b4
|
| 3 |
+
size 16383
|
checkpoint-150/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b165ddef80fcf82bb786dd6b314c9c2847995753023cc24d37410baab27063eb
|
| 3 |
+
size 14455
|
checkpoint-150/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a0ade3b36803b7eb7989cd2e17f2f522f1bfc618da5f81da2fa66c5b88e17432
|
| 3 |
+
size 1465
|
checkpoint-150/tokenizer.json
ADDED
|
@@ -0,0 +1,127 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"version": "1.0",
|
| 3 |
+
"truncation": {
|
| 4 |
+
"direction": "Right",
|
| 5 |
+
"max_length": 16,
|
| 6 |
+
"strategy": "LongestFirst",
|
| 7 |
+
"stride": 0
|
| 8 |
+
},
|
| 9 |
+
"padding": null,
|
| 10 |
+
"added_tokens": [
|
| 11 |
+
{
|
| 12 |
+
"id": 0,
|
| 13 |
+
"content": "<|endoftext|>",
|
| 14 |
+
"single_word": false,
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"id": 1,
|
| 22 |
+
"content": "<|pad|>",
|
| 23 |
+
"single_word": false,
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"special": true
|
| 28 |
+
}
|
| 29 |
+
],
|
| 30 |
+
"normalizer": null,
|
| 31 |
+
"pre_tokenizer": {
|
| 32 |
+
"type": "ByteLevel",
|
| 33 |
+
"add_prefix_space": true,
|
| 34 |
+
"trim_offsets": true,
|
| 35 |
+
"use_regex": true
|
| 36 |
+
},
|
| 37 |
+
"post_processor": {
|
| 38 |
+
"type": "TemplateProcessing",
|
| 39 |
+
"single": [
|
| 40 |
+
{
|
| 41 |
+
"Sequence": {
|
| 42 |
+
"id": "A",
|
| 43 |
+
"type_id": 0
|
| 44 |
+
}
|
| 45 |
+
}
|
| 46 |
+
],
|
| 47 |
+
"pair": [
|
| 48 |
+
{
|
| 49 |
+
"Sequence": {
|
| 50 |
+
"id": "A",
|
| 51 |
+
"type_id": 0
|
| 52 |
+
}
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"Sequence": {
|
| 56 |
+
"id": "B",
|
| 57 |
+
"type_id": 1
|
| 58 |
+
}
|
| 59 |
+
}
|
| 60 |
+
],
|
| 61 |
+
"special_tokens": {}
|
| 62 |
+
},
|
| 63 |
+
"decoder": {
|
| 64 |
+
"type": "ByteLevel",
|
| 65 |
+
"add_prefix_space": true,
|
| 66 |
+
"trim_offsets": true,
|
| 67 |
+
"use_regex": true
|
| 68 |
+
},
|
| 69 |
+
"model": {
|
| 70 |
+
"type": "BPE",
|
| 71 |
+
"dropout": null,
|
| 72 |
+
"unk_token": null,
|
| 73 |
+
"continuing_subword_prefix": null,
|
| 74 |
+
"end_of_word_suffix": null,
|
| 75 |
+
"fuse_unk": false,
|
| 76 |
+
"byte_fallback": false,
|
| 77 |
+
"ignore_merges": false,
|
| 78 |
+
"vocab": {
|
| 79 |
+
"<|endoftext|>": 0,
|
| 80 |
+
"<|pad|>": 1,
|
| 81 |
+
"a": 2,
|
| 82 |
+
"b": 3,
|
| 83 |
+
"c": 4,
|
| 84 |
+
"d": 5,
|
| 85 |
+
"e": 6,
|
| 86 |
+
"f": 7,
|
| 87 |
+
"g": 8,
|
| 88 |
+
"h": 9,
|
| 89 |
+
"i": 10,
|
| 90 |
+
"j": 11,
|
| 91 |
+
"k": 12,
|
| 92 |
+
"l": 13,
|
| 93 |
+
"m": 14,
|
| 94 |
+
"n": 15,
|
| 95 |
+
"o": 16,
|
| 96 |
+
"p": 17,
|
| 97 |
+
"q": 18,
|
| 98 |
+
"r": 19,
|
| 99 |
+
"s": 20,
|
| 100 |
+
"t": 21,
|
| 101 |
+
"u": 22,
|
| 102 |
+
"v": 23,
|
| 103 |
+
"w": 24,
|
| 104 |
+
"x": 25,
|
| 105 |
+
"y": 26,
|
| 106 |
+
"z": 27,
|
| 107 |
+
"Ġ": 28,
|
| 108 |
+
"Ġz": 29,
|
| 109 |
+
"Ġx": 30,
|
| 110 |
+
"Ġi": 31
|
| 111 |
+
},
|
| 112 |
+
"merges": [
|
| 113 |
+
[
|
| 114 |
+
"Ġ",
|
| 115 |
+
"z"
|
| 116 |
+
],
|
| 117 |
+
[
|
| 118 |
+
"Ġ",
|
| 119 |
+
"x"
|
| 120 |
+
],
|
| 121 |
+
[
|
| 122 |
+
"Ġ",
|
| 123 |
+
"i"
|
| 124 |
+
]
|
| 125 |
+
]
|
| 126 |
+
}
|
| 127 |
+
}
|
checkpoint-150/tokenizer_config.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"backend": "tokenizers",
|
| 3 |
+
"bos_token": "<|endoftext|>",
|
| 4 |
+
"eos_token": "<|endoftext|>",
|
| 5 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 6 |
+
"pad_token": "<|pad|>",
|
| 7 |
+
"tokenizer_class": "TokenizersBackend"
|
| 8 |
+
}
|
checkpoint-150/trainer_state.json
ADDED
|
@@ -0,0 +1,139 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 9.375,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 150,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.625,
|
| 14 |
+
"grad_norm": 0.13900995254516602,
|
| 15 |
+
"learning_rate": 0.009000000000000001,
|
| 16 |
+
"loss": 3.240981674194336,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 1.25,
|
| 21 |
+
"grad_norm": 0.10888686776161194,
|
| 22 |
+
"learning_rate": 0.0094,
|
| 23 |
+
"loss": 3.185182571411133,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 1.875,
|
| 28 |
+
"grad_norm": 0.10133716464042664,
|
| 29 |
+
"learning_rate": 0.008733333333333333,
|
| 30 |
+
"loss": 3.1393909454345703,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 2.5,
|
| 35 |
+
"grad_norm": 0.11951159685850143,
|
| 36 |
+
"learning_rate": 0.008066666666666666,
|
| 37 |
+
"loss": 3.1178558349609373,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 3.125,
|
| 42 |
+
"grad_norm": 0.07364343106746674,
|
| 43 |
+
"learning_rate": 0.0074,
|
| 44 |
+
"loss": 3.1153308868408205,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 3.75,
|
| 49 |
+
"grad_norm": 0.11443202942609787,
|
| 50 |
+
"learning_rate": 0.006733333333333333,
|
| 51 |
+
"loss": 3.111285591125488,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 4.375,
|
| 56 |
+
"grad_norm": 0.13409413397312164,
|
| 57 |
+
"learning_rate": 0.006066666666666667,
|
| 58 |
+
"loss": 3.107038116455078,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 5.0,
|
| 63 |
+
"grad_norm": 0.12714578211307526,
|
| 64 |
+
"learning_rate": 0.0054,
|
| 65 |
+
"loss": 3.1068656921386717,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 5.625,
|
| 70 |
+
"grad_norm": 0.11183512210845947,
|
| 71 |
+
"learning_rate": 0.004733333333333333,
|
| 72 |
+
"loss": 3.1074026107788084,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 6.25,
|
| 77 |
+
"grad_norm": 0.10536977648735046,
|
| 78 |
+
"learning_rate": 0.004066666666666667,
|
| 79 |
+
"loss": 3.1052799224853516,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 6.875,
|
| 84 |
+
"grad_norm": 0.13250383734703064,
|
| 85 |
+
"learning_rate": 0.0034000000000000002,
|
| 86 |
+
"loss": 3.108180809020996,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 7.5,
|
| 91 |
+
"grad_norm": 0.09257843345403671,
|
| 92 |
+
"learning_rate": 0.0027333333333333333,
|
| 93 |
+
"loss": 3.104732322692871,
|
| 94 |
+
"step": 120
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 8.125,
|
| 98 |
+
"grad_norm": 0.12099669873714447,
|
| 99 |
+
"learning_rate": 0.0020666666666666667,
|
| 100 |
+
"loss": 3.1070682525634767,
|
| 101 |
+
"step": 130
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 8.75,
|
| 105 |
+
"grad_norm": 0.11566343903541565,
|
| 106 |
+
"learning_rate": 0.0014000000000000002,
|
| 107 |
+
"loss": 3.102994918823242,
|
| 108 |
+
"step": 140
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 9.375,
|
| 112 |
+
"grad_norm": 0.12711389362812042,
|
| 113 |
+
"learning_rate": 0.0007333333333333333,
|
| 114 |
+
"loss": 3.106877899169922,
|
| 115 |
+
"step": 150
|
| 116 |
+
}
|
| 117 |
+
],
|
| 118 |
+
"logging_steps": 10,
|
| 119 |
+
"max_steps": 160,
|
| 120 |
+
"num_input_tokens_seen": 0,
|
| 121 |
+
"num_train_epochs": 10,
|
| 122 |
+
"save_steps": 50,
|
| 123 |
+
"stateful_callbacks": {
|
| 124 |
+
"TrainerControl": {
|
| 125 |
+
"args": {
|
| 126 |
+
"should_epoch_stop": false,
|
| 127 |
+
"should_evaluate": false,
|
| 128 |
+
"should_log": false,
|
| 129 |
+
"should_save": true,
|
| 130 |
+
"should_training_stop": false
|
| 131 |
+
},
|
| 132 |
+
"attributes": {}
|
| 133 |
+
}
|
| 134 |
+
},
|
| 135 |
+
"total_flos": 162155520.0,
|
| 136 |
+
"train_batch_size": 64,
|
| 137 |
+
"trial_name": null,
|
| 138 |
+
"trial_params": null
|
| 139 |
+
}
|
checkpoint-150/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:850fcbfdd316ee92f254e09ea6a5d1c6e9cfa06bc4a892af59b8839023c9b6df
|
| 3 |
+
size 5137
|
checkpoint-160/config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_function": "gelu",
|
| 3 |
+
"add_cross_attention": false,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"GPT2LMHeadModel"
|
| 6 |
+
],
|
| 7 |
+
"attn_pdrop": 0.0,
|
| 8 |
+
"bos_token_id": 0,
|
| 9 |
+
"dtype": "float32",
|
| 10 |
+
"embd_pdrop": 0.0,
|
| 11 |
+
"eos_token_id": 0,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"layer_norm_epsilon": 1e-05,
|
| 14 |
+
"model_type": "gpt2",
|
| 15 |
+
"n_embd": 4,
|
| 16 |
+
"n_head": 1,
|
| 17 |
+
"n_inner": 8,
|
| 18 |
+
"n_layer": 1,
|
| 19 |
+
"n_positions": 16,
|
| 20 |
+
"pad_token_id": 1,
|
| 21 |
+
"reorder_and_upcast_attn": false,
|
| 22 |
+
"resid_pdrop": 0.0,
|
| 23 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 24 |
+
"scale_attn_weights": true,
|
| 25 |
+
"summary_activation": null,
|
| 26 |
+
"summary_first_dropout": 0.1,
|
| 27 |
+
"summary_proj_to_labels": true,
|
| 28 |
+
"summary_type": "cls_index",
|
| 29 |
+
"summary_use_proj": true,
|
| 30 |
+
"tie_word_embeddings": true,
|
| 31 |
+
"transformers_version": "5.12.0",
|
| 32 |
+
"use_cache": false,
|
| 33 |
+
"vocab_size": 32
|
| 34 |
+
}
|
checkpoint-160/generation_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"eos_token_id": 0,
|
| 5 |
+
"output_attentions": false,
|
| 6 |
+
"output_hidden_states": false,
|
| 7 |
+
"pad_token_id": 1,
|
| 8 |
+
"transformers_version": "5.12.0",
|
| 9 |
+
"use_cache": true
|
| 10 |
+
}
|
checkpoint-160/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b275c4b6b9893c68cf5c229198490453d6627086b27be0cab53a40e45649f898
|
| 3 |
+
size 2888
|
checkpoint-160/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b08a8e68515c6564eb0f98eed1aa5b744c045c05736ea3c8bd040b9a460f2744
|
| 3 |
+
size 16383
|
checkpoint-160/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b165ddef80fcf82bb786dd6b314c9c2847995753023cc24d37410baab27063eb
|
| 3 |
+
size 14455
|
checkpoint-160/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7e7076f6c0041df8743b9bd07c79ad80deb069c88919ccd807b7d7f8d794201b
|
| 3 |
+
size 1465
|
checkpoint-160/tokenizer.json
ADDED
|
@@ -0,0 +1,127 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"version": "1.0",
|
| 3 |
+
"truncation": {
|
| 4 |
+
"direction": "Right",
|
| 5 |
+
"max_length": 16,
|
| 6 |
+
"strategy": "LongestFirst",
|
| 7 |
+
"stride": 0
|
| 8 |
+
},
|
| 9 |
+
"padding": null,
|
| 10 |
+
"added_tokens": [
|
| 11 |
+
{
|
| 12 |
+
"id": 0,
|
| 13 |
+
"content": "<|endoftext|>",
|
| 14 |
+
"single_word": false,
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"id": 1,
|
| 22 |
+
"content": "<|pad|>",
|
| 23 |
+
"single_word": false,
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"special": true
|
| 28 |
+
}
|
| 29 |
+
],
|
| 30 |
+
"normalizer": null,
|
| 31 |
+
"pre_tokenizer": {
|
| 32 |
+
"type": "ByteLevel",
|
| 33 |
+
"add_prefix_space": true,
|
| 34 |
+
"trim_offsets": true,
|
| 35 |
+
"use_regex": true
|
| 36 |
+
},
|
| 37 |
+
"post_processor": {
|
| 38 |
+
"type": "TemplateProcessing",
|
| 39 |
+
"single": [
|
| 40 |
+
{
|
| 41 |
+
"Sequence": {
|
| 42 |
+
"id": "A",
|
| 43 |
+
"type_id": 0
|
| 44 |
+
}
|
| 45 |
+
}
|
| 46 |
+
],
|
| 47 |
+
"pair": [
|
| 48 |
+
{
|
| 49 |
+
"Sequence": {
|
| 50 |
+
"id": "A",
|
| 51 |
+
"type_id": 0
|
| 52 |
+
}
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"Sequence": {
|
| 56 |
+
"id": "B",
|
| 57 |
+
"type_id": 1
|
| 58 |
+
}
|
| 59 |
+
}
|
| 60 |
+
],
|
| 61 |
+
"special_tokens": {}
|
| 62 |
+
},
|
| 63 |
+
"decoder": {
|
| 64 |
+
"type": "ByteLevel",
|
| 65 |
+
"add_prefix_space": true,
|
| 66 |
+
"trim_offsets": true,
|
| 67 |
+
"use_regex": true
|
| 68 |
+
},
|
| 69 |
+
"model": {
|
| 70 |
+
"type": "BPE",
|
| 71 |
+
"dropout": null,
|
| 72 |
+
"unk_token": null,
|
| 73 |
+
"continuing_subword_prefix": null,
|
| 74 |
+
"end_of_word_suffix": null,
|
| 75 |
+
"fuse_unk": false,
|
| 76 |
+
"byte_fallback": false,
|
| 77 |
+
"ignore_merges": false,
|
| 78 |
+
"vocab": {
|
| 79 |
+
"<|endoftext|>": 0,
|
| 80 |
+
"<|pad|>": 1,
|
| 81 |
+
"a": 2,
|
| 82 |
+
"b": 3,
|
| 83 |
+
"c": 4,
|
| 84 |
+
"d": 5,
|
| 85 |
+
"e": 6,
|
| 86 |
+
"f": 7,
|
| 87 |
+
"g": 8,
|
| 88 |
+
"h": 9,
|
| 89 |
+
"i": 10,
|
| 90 |
+
"j": 11,
|
| 91 |
+
"k": 12,
|
| 92 |
+
"l": 13,
|
| 93 |
+
"m": 14,
|
| 94 |
+
"n": 15,
|
| 95 |
+
"o": 16,
|
| 96 |
+
"p": 17,
|
| 97 |
+
"q": 18,
|
| 98 |
+
"r": 19,
|
| 99 |
+
"s": 20,
|
| 100 |
+
"t": 21,
|
| 101 |
+
"u": 22,
|
| 102 |
+
"v": 23,
|
| 103 |
+
"w": 24,
|
| 104 |
+
"x": 25,
|
| 105 |
+
"y": 26,
|
| 106 |
+
"z": 27,
|
| 107 |
+
"Ġ": 28,
|
| 108 |
+
"Ġz": 29,
|
| 109 |
+
"Ġx": 30,
|
| 110 |
+
"Ġi": 31
|
| 111 |
+
},
|
| 112 |
+
"merges": [
|
| 113 |
+
[
|
| 114 |
+
"Ġ",
|
| 115 |
+
"z"
|
| 116 |
+
],
|
| 117 |
+
[
|
| 118 |
+
"Ġ",
|
| 119 |
+
"x"
|
| 120 |
+
],
|
| 121 |
+
[
|
| 122 |
+
"Ġ",
|
| 123 |
+
"i"
|
| 124 |
+
]
|
| 125 |
+
]
|
| 126 |
+
}
|
| 127 |
+
}
|
checkpoint-160/tokenizer_config.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"backend": "tokenizers",
|
| 3 |
+
"bos_token": "<|endoftext|>",
|
| 4 |
+
"eos_token": "<|endoftext|>",
|
| 5 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 6 |
+
"pad_token": "<|pad|>",
|
| 7 |
+
"tokenizer_class": "TokenizersBackend"
|
| 8 |
+
}
|
checkpoint-160/trainer_state.json
ADDED
|
@@ -0,0 +1,146 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 10.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 160,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.625,
|
| 14 |
+
"grad_norm": 0.13900995254516602,
|
| 15 |
+
"learning_rate": 0.009000000000000001,
|
| 16 |
+
"loss": 3.240981674194336,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 1.25,
|
| 21 |
+
"grad_norm": 0.10888686776161194,
|
| 22 |
+
"learning_rate": 0.0094,
|
| 23 |
+
"loss": 3.185182571411133,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 1.875,
|
| 28 |
+
"grad_norm": 0.10133716464042664,
|
| 29 |
+
"learning_rate": 0.008733333333333333,
|
| 30 |
+
"loss": 3.1393909454345703,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 2.5,
|
| 35 |
+
"grad_norm": 0.11951159685850143,
|
| 36 |
+
"learning_rate": 0.008066666666666666,
|
| 37 |
+
"loss": 3.1178558349609373,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 3.125,
|
| 42 |
+
"grad_norm": 0.07364343106746674,
|
| 43 |
+
"learning_rate": 0.0074,
|
| 44 |
+
"loss": 3.1153308868408205,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 3.75,
|
| 49 |
+
"grad_norm": 0.11443202942609787,
|
| 50 |
+
"learning_rate": 0.006733333333333333,
|
| 51 |
+
"loss": 3.111285591125488,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 4.375,
|
| 56 |
+
"grad_norm": 0.13409413397312164,
|
| 57 |
+
"learning_rate": 0.006066666666666667,
|
| 58 |
+
"loss": 3.107038116455078,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 5.0,
|
| 63 |
+
"grad_norm": 0.12714578211307526,
|
| 64 |
+
"learning_rate": 0.0054,
|
| 65 |
+
"loss": 3.1068656921386717,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 5.625,
|
| 70 |
+
"grad_norm": 0.11183512210845947,
|
| 71 |
+
"learning_rate": 0.004733333333333333,
|
| 72 |
+
"loss": 3.1074026107788084,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 6.25,
|
| 77 |
+
"grad_norm": 0.10536977648735046,
|
| 78 |
+
"learning_rate": 0.004066666666666667,
|
| 79 |
+
"loss": 3.1052799224853516,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 6.875,
|
| 84 |
+
"grad_norm": 0.13250383734703064,
|
| 85 |
+
"learning_rate": 0.0034000000000000002,
|
| 86 |
+
"loss": 3.108180809020996,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 7.5,
|
| 91 |
+
"grad_norm": 0.09257843345403671,
|
| 92 |
+
"learning_rate": 0.0027333333333333333,
|
| 93 |
+
"loss": 3.104732322692871,
|
| 94 |
+
"step": 120
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 8.125,
|
| 98 |
+
"grad_norm": 0.12099669873714447,
|
| 99 |
+
"learning_rate": 0.0020666666666666667,
|
| 100 |
+
"loss": 3.1070682525634767,
|
| 101 |
+
"step": 130
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 8.75,
|
| 105 |
+
"grad_norm": 0.11566343903541565,
|
| 106 |
+
"learning_rate": 0.0014000000000000002,
|
| 107 |
+
"loss": 3.102994918823242,
|
| 108 |
+
"step": 140
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 9.375,
|
| 112 |
+
"grad_norm": 0.12711389362812042,
|
| 113 |
+
"learning_rate": 0.0007333333333333333,
|
| 114 |
+
"loss": 3.106877899169922,
|
| 115 |
+
"step": 150
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 10.0,
|
| 119 |
+
"grad_norm": 0.17492446303367615,
|
| 120 |
+
"learning_rate": 6.666666666666667e-05,
|
| 121 |
+
"loss": 3.1029436111450197,
|
| 122 |
+
"step": 160
|
| 123 |
+
}
|
| 124 |
+
],
|
| 125 |
+
"logging_steps": 10,
|
| 126 |
+
"max_steps": 160,
|
| 127 |
+
"num_input_tokens_seen": 0,
|
| 128 |
+
"num_train_epochs": 10,
|
| 129 |
+
"save_steps": 50,
|
| 130 |
+
"stateful_callbacks": {
|
| 131 |
+
"TrainerControl": {
|
| 132 |
+
"args": {
|
| 133 |
+
"should_epoch_stop": false,
|
| 134 |
+
"should_evaluate": false,
|
| 135 |
+
"should_log": false,
|
| 136 |
+
"should_save": true,
|
| 137 |
+
"should_training_stop": true
|
| 138 |
+
},
|
| 139 |
+
"attributes": {}
|
| 140 |
+
}
|
| 141 |
+
},
|
| 142 |
+
"total_flos": 172800000.0,
|
| 143 |
+
"train_batch_size": 64,
|
| 144 |
+
"trial_name": null,
|
| 145 |
+
"trial_params": null
|
| 146 |
+
}
|
checkpoint-160/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:850fcbfdd316ee92f254e09ea6a5d1c6e9cfa06bc4a892af59b8839023c9b6df
|
| 3 |
+
size 5137
|
checkpoint-50/config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_function": "gelu",
|
| 3 |
+
"add_cross_attention": false,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"GPT2LMHeadModel"
|
| 6 |
+
],
|
| 7 |
+
"attn_pdrop": 0.0,
|
| 8 |
+
"bos_token_id": 0,
|
| 9 |
+
"dtype": "float32",
|
| 10 |
+
"embd_pdrop": 0.0,
|
| 11 |
+
"eos_token_id": 0,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"layer_norm_epsilon": 1e-05,
|
| 14 |
+
"model_type": "gpt2",
|
| 15 |
+
"n_embd": 4,
|
| 16 |
+
"n_head": 1,
|
| 17 |
+
"n_inner": 8,
|
| 18 |
+
"n_layer": 1,
|
| 19 |
+
"n_positions": 16,
|
| 20 |
+
"pad_token_id": 1,
|
| 21 |
+
"reorder_and_upcast_attn": false,
|
| 22 |
+
"resid_pdrop": 0.0,
|
| 23 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 24 |
+
"scale_attn_weights": true,
|
| 25 |
+
"summary_activation": null,
|
| 26 |
+
"summary_first_dropout": 0.1,
|
| 27 |
+
"summary_proj_to_labels": true,
|
| 28 |
+
"summary_type": "cls_index",
|
| 29 |
+
"summary_use_proj": true,
|
| 30 |
+
"tie_word_embeddings": true,
|
| 31 |
+
"transformers_version": "5.12.0",
|
| 32 |
+
"use_cache": false,
|
| 33 |
+
"vocab_size": 32
|
| 34 |
+
}
|
checkpoint-50/generation_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"eos_token_id": 0,
|
| 5 |
+
"output_attentions": false,
|
| 6 |
+
"output_hidden_states": false,
|
| 7 |
+
"pad_token_id": 1,
|
| 8 |
+
"transformers_version": "5.12.0",
|
| 9 |
+
"use_cache": true
|
| 10 |
+
}
|
checkpoint-50/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ec47d8be45fad2bf07ce647662a7e522b65a7295a7dddb60d9593d68a2a9846e
|
| 3 |
+
size 2888
|
checkpoint-50/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f2c426c9f3da8f4ba55bea03896108ff5cd0e5747f6811a8621f7d6ddf0fb0c2
|
| 3 |
+
size 16383
|
checkpoint-50/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b2330b4937d58a8245fa41d049d3bd387d1682b81a005499f0f0cc3ef70f148a
|
| 3 |
+
size 14455
|
checkpoint-50/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:786631d18fbfa04a10d9202d8b218f9287b704d3d70853911e019c92a25963dd
|
| 3 |
+
size 1465
|
checkpoint-50/tokenizer.json
ADDED
|
@@ -0,0 +1,127 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"version": "1.0",
|
| 3 |
+
"truncation": {
|
| 4 |
+
"direction": "Right",
|
| 5 |
+
"max_length": 16,
|
| 6 |
+
"strategy": "LongestFirst",
|
| 7 |
+
"stride": 0
|
| 8 |
+
},
|
| 9 |
+
"padding": null,
|
| 10 |
+
"added_tokens": [
|
| 11 |
+
{
|
| 12 |
+
"id": 0,
|
| 13 |
+
"content": "<|endoftext|>",
|
| 14 |
+
"single_word": false,
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"id": 1,
|
| 22 |
+
"content": "<|pad|>",
|
| 23 |
+
"single_word": false,
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"special": true
|
| 28 |
+
}
|
| 29 |
+
],
|
| 30 |
+
"normalizer": null,
|
| 31 |
+
"pre_tokenizer": {
|
| 32 |
+
"type": "ByteLevel",
|
| 33 |
+
"add_prefix_space": true,
|
| 34 |
+
"trim_offsets": true,
|
| 35 |
+
"use_regex": true
|
| 36 |
+
},
|
| 37 |
+
"post_processor": {
|
| 38 |
+
"type": "TemplateProcessing",
|
| 39 |
+
"single": [
|
| 40 |
+
{
|
| 41 |
+
"Sequence": {
|
| 42 |
+
"id": "A",
|
| 43 |
+
"type_id": 0
|
| 44 |
+
}
|
| 45 |
+
}
|
| 46 |
+
],
|
| 47 |
+
"pair": [
|
| 48 |
+
{
|
| 49 |
+
"Sequence": {
|
| 50 |
+
"id": "A",
|
| 51 |
+
"type_id": 0
|
| 52 |
+
}
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"Sequence": {
|
| 56 |
+
"id": "B",
|
| 57 |
+
"type_id": 1
|
| 58 |
+
}
|
| 59 |
+
}
|
| 60 |
+
],
|
| 61 |
+
"special_tokens": {}
|
| 62 |
+
},
|
| 63 |
+
"decoder": {
|
| 64 |
+
"type": "ByteLevel",
|
| 65 |
+
"add_prefix_space": true,
|
| 66 |
+
"trim_offsets": true,
|
| 67 |
+
"use_regex": true
|
| 68 |
+
},
|
| 69 |
+
"model": {
|
| 70 |
+
"type": "BPE",
|
| 71 |
+
"dropout": null,
|
| 72 |
+
"unk_token": null,
|
| 73 |
+
"continuing_subword_prefix": null,
|
| 74 |
+
"end_of_word_suffix": null,
|
| 75 |
+
"fuse_unk": false,
|
| 76 |
+
"byte_fallback": false,
|
| 77 |
+
"ignore_merges": false,
|
| 78 |
+
"vocab": {
|
| 79 |
+
"<|endoftext|>": 0,
|
| 80 |
+
"<|pad|>": 1,
|
| 81 |
+
"a": 2,
|
| 82 |
+
"b": 3,
|
| 83 |
+
"c": 4,
|
| 84 |
+
"d": 5,
|
| 85 |
+
"e": 6,
|
| 86 |
+
"f": 7,
|
| 87 |
+
"g": 8,
|
| 88 |
+
"h": 9,
|
| 89 |
+
"i": 10,
|
| 90 |
+
"j": 11,
|
| 91 |
+
"k": 12,
|
| 92 |
+
"l": 13,
|
| 93 |
+
"m": 14,
|
| 94 |
+
"n": 15,
|
| 95 |
+
"o": 16,
|
| 96 |
+
"p": 17,
|
| 97 |
+
"q": 18,
|
| 98 |
+
"r": 19,
|
| 99 |
+
"s": 20,
|
| 100 |
+
"t": 21,
|
| 101 |
+
"u": 22,
|
| 102 |
+
"v": 23,
|
| 103 |
+
"w": 24,
|
| 104 |
+
"x": 25,
|
| 105 |
+
"y": 26,
|
| 106 |
+
"z": 27,
|
| 107 |
+
"Ġ": 28,
|
| 108 |
+
"Ġz": 29,
|
| 109 |
+
"Ġx": 30,
|
| 110 |
+
"Ġi": 31
|
| 111 |
+
},
|
| 112 |
+
"merges": [
|
| 113 |
+
[
|
| 114 |
+
"Ġ",
|
| 115 |
+
"z"
|
| 116 |
+
],
|
| 117 |
+
[
|
| 118 |
+
"Ġ",
|
| 119 |
+
"x"
|
| 120 |
+
],
|
| 121 |
+
[
|
| 122 |
+
"Ġ",
|
| 123 |
+
"i"
|
| 124 |
+
]
|
| 125 |
+
]
|
| 126 |
+
}
|
| 127 |
+
}
|
checkpoint-50/tokenizer_config.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"backend": "tokenizers",
|
| 3 |
+
"bos_token": "<|endoftext|>",
|
| 4 |
+
"eos_token": "<|endoftext|>",
|
| 5 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 6 |
+
"pad_token": "<|pad|>",
|
| 7 |
+
"tokenizer_class": "TokenizersBackend"
|
| 8 |
+
}
|
checkpoint-50/trainer_state.json
ADDED
|
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 3.125,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 50,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.625,
|
| 14 |
+
"grad_norm": 0.13900995254516602,
|
| 15 |
+
"learning_rate": 0.009000000000000001,
|
| 16 |
+
"loss": 3.240981674194336,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 1.25,
|
| 21 |
+
"grad_norm": 0.10888686776161194,
|
| 22 |
+
"learning_rate": 0.0094,
|
| 23 |
+
"loss": 3.185182571411133,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 1.875,
|
| 28 |
+
"grad_norm": 0.10133716464042664,
|
| 29 |
+
"learning_rate": 0.008733333333333333,
|
| 30 |
+
"loss": 3.1393909454345703,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 2.5,
|
| 35 |
+
"grad_norm": 0.11951159685850143,
|
| 36 |
+
"learning_rate": 0.008066666666666666,
|
| 37 |
+
"loss": 3.1178558349609373,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 3.125,
|
| 42 |
+
"grad_norm": 0.07364343106746674,
|
| 43 |
+
"learning_rate": 0.0074,
|
| 44 |
+
"loss": 3.1153308868408205,
|
| 45 |
+
"step": 50
|
| 46 |
+
}
|
| 47 |
+
],
|
| 48 |
+
"logging_steps": 10,
|
| 49 |
+
"max_steps": 160,
|
| 50 |
+
"num_input_tokens_seen": 0,
|
| 51 |
+
"num_train_epochs": 10,
|
| 52 |
+
"save_steps": 50,
|
| 53 |
+
"stateful_callbacks": {
|
| 54 |
+
"TrainerControl": {
|
| 55 |
+
"args": {
|
| 56 |
+
"should_epoch_stop": false,
|
| 57 |
+
"should_evaluate": false,
|
| 58 |
+
"should_log": false,
|
| 59 |
+
"should_save": true,
|
| 60 |
+
"should_training_stop": false
|
| 61 |
+
},
|
| 62 |
+
"attributes": {}
|
| 63 |
+
}
|
| 64 |
+
},
|
| 65 |
+
"total_flos": 54051840.0,
|
| 66 |
+
"train_batch_size": 64,
|
| 67 |
+
"trial_name": null,
|
| 68 |
+
"trial_params": null
|
| 69 |
+
}
|
checkpoint-50/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:850fcbfdd316ee92f254e09ea6a5d1c6e9cfa06bc4a892af59b8839023c9b6df
|
| 3 |
+
size 5137
|
config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_function": "gelu",
|
| 3 |
+
"add_cross_attention": false,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"GPT2LMHeadModel"
|
| 6 |
+
],
|
| 7 |
+
"attn_pdrop": 0.0,
|
| 8 |
+
"bos_token_id": 0,
|
| 9 |
+
"dtype": "float32",
|
| 10 |
+
"embd_pdrop": 0.0,
|
| 11 |
+
"eos_token_id": 0,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"layer_norm_epsilon": 1e-05,
|
| 14 |
+
"model_type": "gpt2",
|
| 15 |
+
"n_embd": 4,
|
| 16 |
+
"n_head": 1,
|
| 17 |
+
"n_inner": 8,
|
| 18 |
+
"n_layer": 1,
|
| 19 |
+
"n_positions": 16,
|
| 20 |
+
"pad_token_id": 1,
|
| 21 |
+
"reorder_and_upcast_attn": false,
|
| 22 |
+
"resid_pdrop": 0.0,
|
| 23 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 24 |
+
"scale_attn_weights": true,
|
| 25 |
+
"summary_activation": null,
|
| 26 |
+
"summary_first_dropout": 0.1,
|
| 27 |
+
"summary_proj_to_labels": true,
|
| 28 |
+
"summary_type": "cls_index",
|
| 29 |
+
"summary_use_proj": true,
|
| 30 |
+
"tie_word_embeddings": true,
|
| 31 |
+
"transformers_version": "5.12.0",
|
| 32 |
+
"use_cache": false,
|
| 33 |
+
"vocab_size": 32
|
| 34 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"eos_token_id": 0,
|
| 5 |
+
"output_attentions": false,
|
| 6 |
+
"output_hidden_states": false,
|
| 7 |
+
"pad_token_id": 1,
|
| 8 |
+
"transformers_version": "5.12.0",
|
| 9 |
+
"use_cache": true
|
| 10 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b275c4b6b9893c68cf5c229198490453d6627086b27be0cab53a40e45649f898
|
| 3 |
+
size 2888
|
tokenizer.json
ADDED
|
@@ -0,0 +1,127 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"version": "1.0",
|
| 3 |
+
"truncation": {
|
| 4 |
+
"direction": "Right",
|
| 5 |
+
"max_length": 16,
|
| 6 |
+
"strategy": "LongestFirst",
|
| 7 |
+
"stride": 0
|
| 8 |
+
},
|
| 9 |
+
"padding": null,
|
| 10 |
+
"added_tokens": [
|
| 11 |
+
{
|
| 12 |
+
"id": 0,
|
| 13 |
+
"content": "<|endoftext|>",
|
| 14 |
+
"single_word": false,
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"id": 1,
|
| 22 |
+
"content": "<|pad|>",
|
| 23 |
+
"single_word": false,
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"special": true
|
| 28 |
+
}
|
| 29 |
+
],
|
| 30 |
+
"normalizer": null,
|
| 31 |
+
"pre_tokenizer": {
|
| 32 |
+
"type": "ByteLevel",
|
| 33 |
+
"add_prefix_space": true,
|
| 34 |
+
"trim_offsets": true,
|
| 35 |
+
"use_regex": true
|
| 36 |
+
},
|
| 37 |
+
"post_processor": {
|
| 38 |
+
"type": "TemplateProcessing",
|
| 39 |
+
"single": [
|
| 40 |
+
{
|
| 41 |
+
"Sequence": {
|
| 42 |
+
"id": "A",
|
| 43 |
+
"type_id": 0
|
| 44 |
+
}
|
| 45 |
+
}
|
| 46 |
+
],
|
| 47 |
+
"pair": [
|
| 48 |
+
{
|
| 49 |
+
"Sequence": {
|
| 50 |
+
"id": "A",
|
| 51 |
+
"type_id": 0
|
| 52 |
+
}
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"Sequence": {
|
| 56 |
+
"id": "B",
|
| 57 |
+
"type_id": 1
|
| 58 |
+
}
|
| 59 |
+
}
|
| 60 |
+
],
|
| 61 |
+
"special_tokens": {}
|
| 62 |
+
},
|
| 63 |
+
"decoder": {
|
| 64 |
+
"type": "ByteLevel",
|
| 65 |
+
"add_prefix_space": true,
|
| 66 |
+
"trim_offsets": true,
|
| 67 |
+
"use_regex": true
|
| 68 |
+
},
|
| 69 |
+
"model": {
|
| 70 |
+
"type": "BPE",
|
| 71 |
+
"dropout": null,
|
| 72 |
+
"unk_token": null,
|
| 73 |
+
"continuing_subword_prefix": null,
|
| 74 |
+
"end_of_word_suffix": null,
|
| 75 |
+
"fuse_unk": false,
|
| 76 |
+
"byte_fallback": false,
|
| 77 |
+
"ignore_merges": false,
|
| 78 |
+
"vocab": {
|
| 79 |
+
"<|endoftext|>": 0,
|
| 80 |
+
"<|pad|>": 1,
|
| 81 |
+
"a": 2,
|
| 82 |
+
"b": 3,
|
| 83 |
+
"c": 4,
|
| 84 |
+
"d": 5,
|
| 85 |
+
"e": 6,
|
| 86 |
+
"f": 7,
|
| 87 |
+
"g": 8,
|
| 88 |
+
"h": 9,
|
| 89 |
+
"i": 10,
|
| 90 |
+
"j": 11,
|
| 91 |
+
"k": 12,
|
| 92 |
+
"l": 13,
|
| 93 |
+
"m": 14,
|
| 94 |
+
"n": 15,
|
| 95 |
+
"o": 16,
|
| 96 |
+
"p": 17,
|
| 97 |
+
"q": 18,
|
| 98 |
+
"r": 19,
|
| 99 |
+
"s": 20,
|
| 100 |
+
"t": 21,
|
| 101 |
+
"u": 22,
|
| 102 |
+
"v": 23,
|
| 103 |
+
"w": 24,
|
| 104 |
+
"x": 25,
|
| 105 |
+
"y": 26,
|
| 106 |
+
"z": 27,
|
| 107 |
+
"Ġ": 28,
|
| 108 |
+
"Ġz": 29,
|
| 109 |
+
"Ġx": 30,
|
| 110 |
+
"Ġi": 31
|
| 111 |
+
},
|
| 112 |
+
"merges": [
|
| 113 |
+
[
|
| 114 |
+
"Ġ",
|
| 115 |
+
"z"
|
| 116 |
+
],
|
| 117 |
+
[
|
| 118 |
+
"Ġ",
|
| 119 |
+
"x"
|
| 120 |
+
],
|
| 121 |
+
[
|
| 122 |
+
"Ġ",
|
| 123 |
+
"i"
|
| 124 |
+
]
|
| 125 |
+
]
|
| 126 |
+
}
|
| 127 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"backend": "tokenizers",
|
| 3 |
+
"bos_token": "<|endoftext|>",
|
| 4 |
+
"eos_token": "<|endoftext|>",
|
| 5 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 6 |
+
"pad_token": "<|pad|>",
|
| 7 |
+
"tokenizer_class": "TokenizersBackend"
|
| 8 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:850fcbfdd316ee92f254e09ea6a5d1c6e9cfa06bc4a892af59b8839023c9b6df
|
| 3 |
+
size 5137
|