Training in progress, step 500
Browse files- added_tokens.json +5 -0
- config.json +43 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- runs/Aug06_17-06-27_232a0f8c3879/events.out.tfevents.1722964283.232a0f8c3879 +3 -0
- runs/Aug07_00-28-27_232a0f8c3879/events.out.tfevents.1722990837.232a0f8c3879 +3 -0
- runs/Aug07_01-01-58_232a0f8c3879/events.out.tfevents.1722992940.232a0f8c3879 +3 -0
- runs/Aug07_01-27-45_232a0f8c3879/events.out.tfevents.1722994589.232a0f8c3879 +3 -0
- runs/Aug07_02-08-04_232a0f8c3879/events.out.tfevents.1722997019.232a0f8c3879 +3 -0
- runs/Aug08_00-42-29_232a0f8c3879/events.out.tfevents.1723078179.232a0f8c3879 +3 -0
- special_tokens_map.json +20 -0
- tokenizer.json +0 -0
- tokenizer_config.json +43 -0
- training_args.bin +3 -0
- vocab.json +0 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<|endoftext|>": 151643,
|
| 3 |
+
"<|im_end|>": 151645,
|
| 4 |
+
"<|im_start|>": 151644
|
| 5 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "Qwen/Qwen2-0.5B-Instruct",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"Qwen2ForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 151643,
|
| 8 |
+
"eos_token_id": 151645,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 896,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 4864,
|
| 13 |
+
"max_position_embeddings": 32768,
|
| 14 |
+
"max_window_layers": 24,
|
| 15 |
+
"model_type": "qwen2",
|
| 16 |
+
"num_attention_heads": 14,
|
| 17 |
+
"num_hidden_layers": 24,
|
| 18 |
+
"num_key_value_heads": 2,
|
| 19 |
+
"quantization_config": {
|
| 20 |
+
"_load_in_4bit": false,
|
| 21 |
+
"_load_in_8bit": true,
|
| 22 |
+
"bnb_4bit_compute_dtype": "float32",
|
| 23 |
+
"bnb_4bit_quant_storage": "uint8",
|
| 24 |
+
"bnb_4bit_quant_type": "fp4",
|
| 25 |
+
"bnb_4bit_use_double_quant": false,
|
| 26 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
| 27 |
+
"llm_int8_has_fp16_weight": false,
|
| 28 |
+
"llm_int8_skip_modules": null,
|
| 29 |
+
"llm_int8_threshold": 6.0,
|
| 30 |
+
"load_in_4bit": false,
|
| 31 |
+
"load_in_8bit": true,
|
| 32 |
+
"quant_method": "bitsandbytes"
|
| 33 |
+
},
|
| 34 |
+
"rms_norm_eps": 1e-06,
|
| 35 |
+
"rope_theta": 1000000.0,
|
| 36 |
+
"sliding_window": null,
|
| 37 |
+
"tie_word_embeddings": true,
|
| 38 |
+
"torch_dtype": "bfloat16",
|
| 39 |
+
"transformers_version": "4.43.3",
|
| 40 |
+
"use_cache": true,
|
| 41 |
+
"use_sliding_window": false,
|
| 42 |
+
"vocab_size": 151936
|
| 43 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b41db1697da1880dd3a5bd205335ac9d935483e95dd73dec3cee8fac6e793758
|
| 3 |
+
size 988097824
|
runs/Aug06_17-06-27_232a0f8c3879/events.out.tfevents.1722964283.232a0f8c3879
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7960660bf4b1fb26ab022f99c77d5650051f3e9d34c4af22f8b0d2dab48b192b
|
| 3 |
+
size 5816
|
runs/Aug07_00-28-27_232a0f8c3879/events.out.tfevents.1722990837.232a0f8c3879
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0ddd6c7219fb407e517bc72c46ba7c66fb7c2f6a877b5c3228858f7956a5e885
|
| 3 |
+
size 5816
|
runs/Aug07_01-01-58_232a0f8c3879/events.out.tfevents.1722992940.232a0f8c3879
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ac9c810e307c682aaed9f27e30dae559a550906d94fb0643f9529c52a7398680
|
| 3 |
+
size 6072
|
runs/Aug07_01-27-45_232a0f8c3879/events.out.tfevents.1722994589.232a0f8c3879
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a4ee90c9796fc8419752b076a0a8d7a668048881f9056f35418744a291308658
|
| 3 |
+
size 93762
|
runs/Aug07_02-08-04_232a0f8c3879/events.out.tfevents.1722997019.232a0f8c3879
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e1d83033d77b910029363020ea62858c8956bb369dc8c05d9b699e767aba2699
|
| 3 |
+
size 79836
|
runs/Aug08_00-42-29_232a0f8c3879/events.out.tfevents.1723078179.232a0f8c3879
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9d2896adba5a8fe76b65d91a502754e73fe3ed7a6034e06a235cddb2db99984f
|
| 3 |
+
size 111273
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>"
|
| 5 |
+
],
|
| 6 |
+
"eos_token": {
|
| 7 |
+
"content": "<|im_end|>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false
|
| 12 |
+
},
|
| 13 |
+
"pad_token": {
|
| 14 |
+
"content": "<|endoftext|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false
|
| 19 |
+
}
|
| 20 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"151643": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"151644": {
|
| 13 |
+
"content": "<|im_start|>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"151645": {
|
| 21 |
+
"content": "<|im_end|>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
}
|
| 28 |
+
},
|
| 29 |
+
"additional_special_tokens": [
|
| 30 |
+
"<|im_start|>",
|
| 31 |
+
"<|im_end|>"
|
| 32 |
+
],
|
| 33 |
+
"bos_token": null,
|
| 34 |
+
"chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
| 35 |
+
"clean_up_tokenization_spaces": false,
|
| 36 |
+
"eos_token": "<|im_end|>",
|
| 37 |
+
"errors": "replace",
|
| 38 |
+
"model_max_length": 32768,
|
| 39 |
+
"pad_token": "<|endoftext|>",
|
| 40 |
+
"split_special_tokens": false,
|
| 41 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 42 |
+
"unk_token": null
|
| 43 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:53571aa830e0386660d62ccb4361a18dda5a80a0218aeeda4a01df462d2820ab
|
| 3 |
+
size 630222980
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|