Upload folder using huggingface_hub
Browse files- saves/composition-10B/op_level/id2-10_0.2easy_0.3medium_0.5hard/cpt0.2-uniform_0.8-11-14_plus/checkpoint-6579/chat_template.jinja +1 -0
- saves/composition-10B/op_level/id2-10_0.2easy_0.3medium_0.5hard/cpt0.2-uniform_0.8-11-14_plus/checkpoint-6579/config.json +43 -0
- saves/composition-10B/op_level/id2-10_0.2easy_0.3medium_0.5hard/cpt0.2-uniform_0.8-11-14_plus/checkpoint-6579/generation_config.json +7 -0
- saves/composition-10B/op_level/id2-10_0.2easy_0.3medium_0.5hard/cpt0.2-uniform_0.8-11-14_plus/checkpoint-6579/model.safetensors +3 -0
- saves/composition-10B/op_level/id2-10_0.2easy_0.3medium_0.5hard/cpt0.2-uniform_0.8-11-14_plus/checkpoint-6579/rng_state_0.pth +3 -0
- saves/composition-10B/op_level/id2-10_0.2easy_0.3medium_0.5hard/cpt0.2-uniform_0.8-11-14_plus/checkpoint-6579/rng_state_1.pth +3 -0
- saves/composition-10B/op_level/id2-10_0.2easy_0.3medium_0.5hard/cpt0.2-uniform_0.8-11-14_plus/checkpoint-6579/rng_state_2.pth +3 -0
- saves/composition-10B/op_level/id2-10_0.2easy_0.3medium_0.5hard/cpt0.2-uniform_0.8-11-14_plus/checkpoint-6579/rng_state_3.pth +3 -0
- saves/composition-10B/op_level/id2-10_0.2easy_0.3medium_0.5hard/cpt0.2-uniform_0.8-11-14_plus/checkpoint-6579/scheduler.pt +3 -0
- saves/composition-10B/op_level/id2-10_0.2easy_0.3medium_0.5hard/cpt0.2-uniform_0.8-11-14_plus/checkpoint-6579/special_tokens_map.json +38 -0
- saves/composition-10B/op_level/id2-10_0.2easy_0.3medium_0.5hard/cpt0.2-uniform_0.8-11-14_plus/checkpoint-6579/tokenizer.json +0 -0
- saves/composition-10B/op_level/id2-10_0.2easy_0.3medium_0.5hard/cpt0.2-uniform_0.8-11-14_plus/checkpoint-6579/tokenizer_config.json +143 -0
- saves/composition-10B/op_level/id2-10_0.2easy_0.3medium_0.5hard/cpt0.2-uniform_0.8-11-14_plus/checkpoint-6579/trainer_state.json +0 -0
- saves/composition-10B/op_level/id2-10_0.2easy_0.3medium_0.5hard/cpt0.2-uniform_0.8-11-14_plus/checkpoint-6579/training_args.bin +3 -0
saves/composition-10B/op_level/id2-10_0.2easy_0.3medium_0.5hard/cpt0.2-uniform_0.8-11-14_plus/checkpoint-6579/chat_template.jinja
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ content }}{% elif message['role'] == 'assistant' %}{{ content }}{% endif %}{% endfor %}
|
saves/composition-10B/op_level/id2-10_0.2easy_0.3medium_0.5hard/cpt0.2-uniform_0.8-11-14_plus/checkpoint-6579/config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen2ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"bos_token_id": 2,
|
| 7 |
+
"eos_token_id": 3,
|
| 8 |
+
"hidden_act": "silu",
|
| 9 |
+
"hidden_size": 768,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 3072,
|
| 12 |
+
"layer_types": [
|
| 13 |
+
"full_attention",
|
| 14 |
+
"full_attention",
|
| 15 |
+
"full_attention",
|
| 16 |
+
"full_attention",
|
| 17 |
+
"full_attention",
|
| 18 |
+
"full_attention",
|
| 19 |
+
"full_attention",
|
| 20 |
+
"full_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention"
|
| 25 |
+
],
|
| 26 |
+
"max_position_embeddings": 2048,
|
| 27 |
+
"max_window_layers": 24,
|
| 28 |
+
"model_type": "qwen2",
|
| 29 |
+
"num_attention_heads": 12,
|
| 30 |
+
"num_hidden_layers": 12,
|
| 31 |
+
"num_key_value_heads": 2,
|
| 32 |
+
"rms_norm_eps": 1e-06,
|
| 33 |
+
"rope_scaling": null,
|
| 34 |
+
"rope_theta": 1000000.0,
|
| 35 |
+
"sliding_window": null,
|
| 36 |
+
"tie_word_embeddings": true,
|
| 37 |
+
"torch_dtype": "float32",
|
| 38 |
+
"transformers_version": "4.55.0",
|
| 39 |
+
"use_cache": false,
|
| 40 |
+
"use_mrope": false,
|
| 41 |
+
"use_sliding_window": false,
|
| 42 |
+
"vocab_size": 2200
|
| 43 |
+
}
|
saves/composition-10B/op_level/id2-10_0.2easy_0.3medium_0.5hard/cpt0.2-uniform_0.8-11-14_plus/checkpoint-6579/generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 2,
|
| 4 |
+
"eos_token_id": 3,
|
| 5 |
+
"transformers_version": "4.55.0",
|
| 6 |
+
"use_cache": false
|
| 7 |
+
}
|
saves/composition-10B/op_level/id2-10_0.2easy_0.3medium_0.5hard/cpt0.2-uniform_0.8-11-14_plus/checkpoint-6579/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:188ab29ca91c153ded8a85724fb684bfcfa12cc442c8a06a36440aa0982e207a
|
| 3 |
+
size 412699256
|
saves/composition-10B/op_level/id2-10_0.2easy_0.3medium_0.5hard/cpt0.2-uniform_0.8-11-14_plus/checkpoint-6579/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7f91f87bd9a92e8739289f46162ef308559319763234c64c5b77db9ec569f87f
|
| 3 |
+
size 15429
|
saves/composition-10B/op_level/id2-10_0.2easy_0.3medium_0.5hard/cpt0.2-uniform_0.8-11-14_plus/checkpoint-6579/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d7d39b8b541e3fd455fdaac992f8e531a8b6ecbd342d84bd34ce103caf8c4829
|
| 3 |
+
size 15429
|
saves/composition-10B/op_level/id2-10_0.2easy_0.3medium_0.5hard/cpt0.2-uniform_0.8-11-14_plus/checkpoint-6579/rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0ff092a382271ec0416bca1eaebe1589a5c027148f661f515a99be89a41550e9
|
| 3 |
+
size 15429
|
saves/composition-10B/op_level/id2-10_0.2easy_0.3medium_0.5hard/cpt0.2-uniform_0.8-11-14_plus/checkpoint-6579/rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5ee31a8654359133d1c40cfb2da8b7350b44cc7eec9bf923c997643420f7061d
|
| 3 |
+
size 15429
|
saves/composition-10B/op_level/id2-10_0.2easy_0.3medium_0.5hard/cpt0.2-uniform_0.8-11-14_plus/checkpoint-6579/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aad47d3731c397fe3b0aace6c3ab576ee85e030520d42054baf6cdba4ac9bc8e
|
| 3 |
+
size 1465
|
saves/composition-10B/op_level/id2-10_0.2easy_0.3medium_0.5hard/cpt0.2-uniform_0.8-11-14_plus/checkpoint-6579/special_tokens_map.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<question>",
|
| 4 |
+
"</question>",
|
| 5 |
+
"<solution>",
|
| 6 |
+
"</solution>",
|
| 7 |
+
"<answer>",
|
| 8 |
+
"</answer>"
|
| 9 |
+
],
|
| 10 |
+
"bos_token": {
|
| 11 |
+
"content": "[BOS]",
|
| 12 |
+
"lstrip": false,
|
| 13 |
+
"normalized": false,
|
| 14 |
+
"rstrip": false,
|
| 15 |
+
"single_word": false
|
| 16 |
+
},
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "[EOS]",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "[PAD]",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
},
|
| 31 |
+
"unk_token": {
|
| 32 |
+
"content": "[UNK]",
|
| 33 |
+
"lstrip": false,
|
| 34 |
+
"normalized": false,
|
| 35 |
+
"rstrip": false,
|
| 36 |
+
"single_word": false
|
| 37 |
+
}
|
| 38 |
+
}
|
saves/composition-10B/op_level/id2-10_0.2easy_0.3medium_0.5hard/cpt0.2-uniform_0.8-11-14_plus/checkpoint-6579/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
saves/composition-10B/op_level/id2-10_0.2easy_0.3medium_0.5hard/cpt0.2-uniform_0.8-11-14_plus/checkpoint-6579/tokenizer_config.json
ADDED
|
@@ -0,0 +1,143 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "[UNK]",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "[PAD]",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "[BOS]",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "[EOS]",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"4": {
|
| 37 |
+
"content": "<question>",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
},
|
| 44 |
+
"5": {
|
| 45 |
+
"content": "</question>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": true
|
| 51 |
+
},
|
| 52 |
+
"6": {
|
| 53 |
+
"content": "<solution>",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": true
|
| 59 |
+
},
|
| 60 |
+
"7": {
|
| 61 |
+
"content": "</solution>",
|
| 62 |
+
"lstrip": false,
|
| 63 |
+
"normalized": false,
|
| 64 |
+
"rstrip": false,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": true
|
| 67 |
+
},
|
| 68 |
+
"8": {
|
| 69 |
+
"content": "<answer>",
|
| 70 |
+
"lstrip": false,
|
| 71 |
+
"normalized": false,
|
| 72 |
+
"rstrip": false,
|
| 73 |
+
"single_word": false,
|
| 74 |
+
"special": true
|
| 75 |
+
},
|
| 76 |
+
"9": {
|
| 77 |
+
"content": "</answer>",
|
| 78 |
+
"lstrip": false,
|
| 79 |
+
"normalized": false,
|
| 80 |
+
"rstrip": false,
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"special": true
|
| 83 |
+
},
|
| 84 |
+
"2196": {
|
| 85 |
+
"content": "<special_token_0>",
|
| 86 |
+
"lstrip": false,
|
| 87 |
+
"normalized": false,
|
| 88 |
+
"rstrip": false,
|
| 89 |
+
"single_word": false,
|
| 90 |
+
"special": true
|
| 91 |
+
},
|
| 92 |
+
"2197": {
|
| 93 |
+
"content": "<special_token_1>",
|
| 94 |
+
"lstrip": false,
|
| 95 |
+
"normalized": false,
|
| 96 |
+
"rstrip": false,
|
| 97 |
+
"single_word": false,
|
| 98 |
+
"special": true
|
| 99 |
+
},
|
| 100 |
+
"2198": {
|
| 101 |
+
"content": "<special_token_2>",
|
| 102 |
+
"lstrip": false,
|
| 103 |
+
"normalized": false,
|
| 104 |
+
"rstrip": false,
|
| 105 |
+
"single_word": false,
|
| 106 |
+
"special": true
|
| 107 |
+
},
|
| 108 |
+
"2199": {
|
| 109 |
+
"content": "<special_token_3>",
|
| 110 |
+
"lstrip": false,
|
| 111 |
+
"normalized": false,
|
| 112 |
+
"rstrip": false,
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"special": true
|
| 115 |
+
},
|
| 116 |
+
"2200": {
|
| 117 |
+
"content": "<special_token_4>",
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"normalized": false,
|
| 120 |
+
"rstrip": false,
|
| 121 |
+
"single_word": false,
|
| 122 |
+
"special": true
|
| 123 |
+
}
|
| 124 |
+
},
|
| 125 |
+
"additional_special_tokens": [
|
| 126 |
+
"<question>",
|
| 127 |
+
"</question>",
|
| 128 |
+
"<solution>",
|
| 129 |
+
"</solution>",
|
| 130 |
+
"<answer>",
|
| 131 |
+
"</answer>"
|
| 132 |
+
],
|
| 133 |
+
"bos_token": "[BOS]",
|
| 134 |
+
"clean_up_tokenization_spaces": false,
|
| 135 |
+
"eos_token": "[EOS]",
|
| 136 |
+
"extra_special_tokens": {},
|
| 137 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 138 |
+
"pad_token": "[PAD]",
|
| 139 |
+
"padding_side": "right",
|
| 140 |
+
"split_special_tokens": false,
|
| 141 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 142 |
+
"unk_token": "[UNK]"
|
| 143 |
+
}
|
saves/composition-10B/op_level/id2-10_0.2easy_0.3medium_0.5hard/cpt0.2-uniform_0.8-11-14_plus/checkpoint-6579/trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
saves/composition-10B/op_level/id2-10_0.2easy_0.3medium_0.5hard/cpt0.2-uniform_0.8-11-14_plus/checkpoint-6579/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:25e3a78494c56d71516c49e12d8a074314e5088114a26358e11ffa123915451a
|
| 3 |
+
size 6353
|