Training in progress, step 50
Browse files- adapter_config.json +31 -0
- adapter_model.safetensors +3 -0
- config.json +139 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer_config.json +137 -0
- training_args.bin +3 -0
adapter_config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "numind/NuExtract-v1.5",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": null,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 128,
|
| 14 |
+
"lora_dropout": 0.05,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 64,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"gate_up_proj",
|
| 24 |
+
"o_proj",
|
| 25 |
+
"down_proj",
|
| 26 |
+
"qkv_proj"
|
| 27 |
+
],
|
| 28 |
+
"task_type": "CAUSAL_LM",
|
| 29 |
+
"use_dora": false,
|
| 30 |
+
"use_rslora": false
|
| 31 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:84c00ebe10d33e8f6e512b5ba1d4418f821592e16c7dfd7a8b40a4fabfe4729a
|
| 3 |
+
size 402688040
|
config.json
ADDED
|
@@ -0,0 +1,139 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_attn_implementation_autoset": true,
|
| 3 |
+
"_name_or_path": "numind/NuExtract-v1.5",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"Phi3ForCausalLM"
|
| 6 |
+
],
|
| 7 |
+
"attention_bias": false,
|
| 8 |
+
"attention_dropout": 0.0,
|
| 9 |
+
"auto_map": {
|
| 10 |
+
"AutoConfig": "microsoft/Phi-3.5-mini-instruct--configuration_phi3.Phi3Config",
|
| 11 |
+
"AutoModelForCausalLM": "microsoft/Phi-3.5-mini-instruct--modeling_phi3.Phi3ForCausalLM"
|
| 12 |
+
},
|
| 13 |
+
"bos_token_id": 1,
|
| 14 |
+
"embd_pdrop": 0.0,
|
| 15 |
+
"eos_token_id": 32000,
|
| 16 |
+
"hidden_act": "silu",
|
| 17 |
+
"hidden_size": 3072,
|
| 18 |
+
"initializer_range": 0.02,
|
| 19 |
+
"intermediate_size": 8192,
|
| 20 |
+
"max_position_embeddings": 131072,
|
| 21 |
+
"model_type": "phi3",
|
| 22 |
+
"num_attention_heads": 32,
|
| 23 |
+
"num_hidden_layers": 32,
|
| 24 |
+
"num_key_value_heads": 32,
|
| 25 |
+
"original_max_position_embeddings": 4096,
|
| 26 |
+
"pad_token_id": 32000,
|
| 27 |
+
"resid_pdrop": 0.0,
|
| 28 |
+
"rms_norm_eps": 1e-05,
|
| 29 |
+
"rope_scaling": {
|
| 30 |
+
"long_factor": [
|
| 31 |
+
1.0800000429153442,
|
| 32 |
+
1.1100000143051147,
|
| 33 |
+
1.1399999856948853,
|
| 34 |
+
1.340000033378601,
|
| 35 |
+
1.5899999141693115,
|
| 36 |
+
1.600000023841858,
|
| 37 |
+
1.6200000047683716,
|
| 38 |
+
2.620000123977661,
|
| 39 |
+
3.2300000190734863,
|
| 40 |
+
3.2300000190734863,
|
| 41 |
+
4.789999961853027,
|
| 42 |
+
7.400000095367432,
|
| 43 |
+
7.700000286102295,
|
| 44 |
+
9.09000015258789,
|
| 45 |
+
12.199999809265137,
|
| 46 |
+
17.670000076293945,
|
| 47 |
+
24.46000099182129,
|
| 48 |
+
28.57000160217285,
|
| 49 |
+
30.420001983642578,
|
| 50 |
+
30.840002059936523,
|
| 51 |
+
32.590003967285156,
|
| 52 |
+
32.93000411987305,
|
| 53 |
+
42.320003509521484,
|
| 54 |
+
44.96000289916992,
|
| 55 |
+
50.340003967285156,
|
| 56 |
+
50.45000457763672,
|
| 57 |
+
57.55000305175781,
|
| 58 |
+
57.93000411987305,
|
| 59 |
+
58.21000289916992,
|
| 60 |
+
60.1400032043457,
|
| 61 |
+
62.61000442504883,
|
| 62 |
+
62.62000274658203,
|
| 63 |
+
62.71000289916992,
|
| 64 |
+
63.1400032043457,
|
| 65 |
+
63.1400032043457,
|
| 66 |
+
63.77000427246094,
|
| 67 |
+
63.93000411987305,
|
| 68 |
+
63.96000289916992,
|
| 69 |
+
63.970001220703125,
|
| 70 |
+
64.02999877929688,
|
| 71 |
+
64.06999969482422,
|
| 72 |
+
64.08000183105469,
|
| 73 |
+
64.12000274658203,
|
| 74 |
+
64.41000366210938,
|
| 75 |
+
64.4800033569336,
|
| 76 |
+
64.51000213623047,
|
| 77 |
+
64.52999877929688,
|
| 78 |
+
64.83999633789062
|
| 79 |
+
],
|
| 80 |
+
"short_factor": [
|
| 81 |
+
1.0,
|
| 82 |
+
1.0199999809265137,
|
| 83 |
+
1.0299999713897705,
|
| 84 |
+
1.0299999713897705,
|
| 85 |
+
1.0499999523162842,
|
| 86 |
+
1.0499999523162842,
|
| 87 |
+
1.0499999523162842,
|
| 88 |
+
1.0499999523162842,
|
| 89 |
+
1.0499999523162842,
|
| 90 |
+
1.0699999332427979,
|
| 91 |
+
1.0999999046325684,
|
| 92 |
+
1.1099998950958252,
|
| 93 |
+
1.1599998474121094,
|
| 94 |
+
1.1599998474121094,
|
| 95 |
+
1.1699998378753662,
|
| 96 |
+
1.2899998426437378,
|
| 97 |
+
1.339999794960022,
|
| 98 |
+
1.679999828338623,
|
| 99 |
+
1.7899998426437378,
|
| 100 |
+
1.8199998140335083,
|
| 101 |
+
1.8499997854232788,
|
| 102 |
+
1.8799997568130493,
|
| 103 |
+
1.9099997282028198,
|
| 104 |
+
1.9399996995925903,
|
| 105 |
+
1.9899996519088745,
|
| 106 |
+
2.0199997425079346,
|
| 107 |
+
2.0199997425079346,
|
| 108 |
+
2.0199997425079346,
|
| 109 |
+
2.0199997425079346,
|
| 110 |
+
2.0199997425079346,
|
| 111 |
+
2.0199997425079346,
|
| 112 |
+
2.0299997329711914,
|
| 113 |
+
2.0299997329711914,
|
| 114 |
+
2.0299997329711914,
|
| 115 |
+
2.0299997329711914,
|
| 116 |
+
2.0299997329711914,
|
| 117 |
+
2.0299997329711914,
|
| 118 |
+
2.0299997329711914,
|
| 119 |
+
2.0299997329711914,
|
| 120 |
+
2.0299997329711914,
|
| 121 |
+
2.0799996852874756,
|
| 122 |
+
2.0899996757507324,
|
| 123 |
+
2.189999580383301,
|
| 124 |
+
2.2199995517730713,
|
| 125 |
+
2.5899994373321533,
|
| 126 |
+
2.729999542236328,
|
| 127 |
+
2.749999523162842,
|
| 128 |
+
2.8399994373321533
|
| 129 |
+
],
|
| 130 |
+
"type": "longrope"
|
| 131 |
+
},
|
| 132 |
+
"rope_theta": 10000.0,
|
| 133 |
+
"sliding_window": 262144,
|
| 134 |
+
"tie_word_embeddings": false,
|
| 135 |
+
"torch_dtype": "bfloat16",
|
| 136 |
+
"transformers_version": "4.46.0",
|
| 137 |
+
"use_cache": false,
|
| 138 |
+
"vocab_size": 32064
|
| 139 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 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": {
|
| 17 |
+
"content": "<|endoftext|>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "<unk>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,137 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": null,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<unk>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"2": {
|
| 23 |
+
"content": "</s>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": true,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": false
|
| 29 |
+
},
|
| 30 |
+
"32000": {
|
| 31 |
+
"content": "<|endoftext|>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": true
|
| 37 |
+
},
|
| 38 |
+
"32001": {
|
| 39 |
+
"content": "<|assistant|>",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": false,
|
| 42 |
+
"rstrip": true,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": true
|
| 45 |
+
},
|
| 46 |
+
"32002": {
|
| 47 |
+
"content": "<|placeholder1|>",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": false,
|
| 50 |
+
"rstrip": true,
|
| 51 |
+
"single_word": false,
|
| 52 |
+
"special": true
|
| 53 |
+
},
|
| 54 |
+
"32003": {
|
| 55 |
+
"content": "<|placeholder2|>",
|
| 56 |
+
"lstrip": false,
|
| 57 |
+
"normalized": false,
|
| 58 |
+
"rstrip": true,
|
| 59 |
+
"single_word": false,
|
| 60 |
+
"special": true
|
| 61 |
+
},
|
| 62 |
+
"32004": {
|
| 63 |
+
"content": "<|placeholder3|>",
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"normalized": false,
|
| 66 |
+
"rstrip": true,
|
| 67 |
+
"single_word": false,
|
| 68 |
+
"special": true
|
| 69 |
+
},
|
| 70 |
+
"32005": {
|
| 71 |
+
"content": "<|placeholder4|>",
|
| 72 |
+
"lstrip": false,
|
| 73 |
+
"normalized": false,
|
| 74 |
+
"rstrip": true,
|
| 75 |
+
"single_word": false,
|
| 76 |
+
"special": true
|
| 77 |
+
},
|
| 78 |
+
"32006": {
|
| 79 |
+
"content": "<|system|>",
|
| 80 |
+
"lstrip": false,
|
| 81 |
+
"normalized": false,
|
| 82 |
+
"rstrip": true,
|
| 83 |
+
"single_word": false,
|
| 84 |
+
"special": true
|
| 85 |
+
},
|
| 86 |
+
"32007": {
|
| 87 |
+
"content": "<|end|>",
|
| 88 |
+
"lstrip": false,
|
| 89 |
+
"normalized": false,
|
| 90 |
+
"rstrip": true,
|
| 91 |
+
"single_word": false,
|
| 92 |
+
"special": true
|
| 93 |
+
},
|
| 94 |
+
"32008": {
|
| 95 |
+
"content": "<|placeholder5|>",
|
| 96 |
+
"lstrip": false,
|
| 97 |
+
"normalized": false,
|
| 98 |
+
"rstrip": true,
|
| 99 |
+
"single_word": false,
|
| 100 |
+
"special": true
|
| 101 |
+
},
|
| 102 |
+
"32009": {
|
| 103 |
+
"content": "<|placeholder6|>",
|
| 104 |
+
"lstrip": false,
|
| 105 |
+
"normalized": false,
|
| 106 |
+
"rstrip": true,
|
| 107 |
+
"single_word": false,
|
| 108 |
+
"special": true
|
| 109 |
+
},
|
| 110 |
+
"32010": {
|
| 111 |
+
"content": "<|user|>",
|
| 112 |
+
"lstrip": false,
|
| 113 |
+
"normalized": false,
|
| 114 |
+
"rstrip": true,
|
| 115 |
+
"single_word": false,
|
| 116 |
+
"special": true
|
| 117 |
+
}
|
| 118 |
+
},
|
| 119 |
+
"bos_token": "<s>",
|
| 120 |
+
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
|
| 121 |
+
"clean_up_tokenization_spaces": false,
|
| 122 |
+
"eos_token": "<|endoftext|>",
|
| 123 |
+
"legacy": false,
|
| 124 |
+
"max_length": 4000,
|
| 125 |
+
"model_max_length": 131072,
|
| 126 |
+
"pad_to_multiple_of": null,
|
| 127 |
+
"pad_token": "<|endoftext|>",
|
| 128 |
+
"pad_token_type_id": 0,
|
| 129 |
+
"padding_side": "left",
|
| 130 |
+
"sp_model_kwargs": {},
|
| 131 |
+
"stride": 0,
|
| 132 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 133 |
+
"truncation_side": "right",
|
| 134 |
+
"truncation_strategy": "longest_first",
|
| 135 |
+
"unk_token": "<unk>",
|
| 136 |
+
"use_default_system_prompt": false
|
| 137 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a1d4931a82c0a2f8ca3b80d1e51bc95da54e038842f68f19e2db2e8def1e4019
|
| 3 |
+
size 6840
|