cutelemonlili commited on
Commit
90ce9b5
·
verified ·
1 Parent(s): e0f6bc5

Add files using upload-large-folder tool

Browse files
README.md CHANGED
@@ -1,7 +1,7 @@
1
  ---
2
  library_name: transformers
3
  license: other
4
- base_model: Qwen/Qwen2.5-7B-Instruct
5
  tags:
6
  - llama-factory
7
  - full
@@ -16,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  # 2and3_apps_30k_v6
18
 
19
- This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the 2and3_apps_30k_v6 dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.1715
22
 
23
  ## Model description
24
 
@@ -53,79 +53,79 @@ The following hyperparameters were used during training:
53
 
54
  | Training Loss | Epoch | Step | Validation Loss |
55
  |:-------------:|:------:|:----:|:---------------:|
56
- | 0.2684 | 0.0137 | 100 | 0.2567 |
57
- | 0.2402 | 0.0274 | 200 | 0.2422 |
58
- | 0.2016 | 0.0410 | 300 | 0.2344 |
59
- | 0.2508 | 0.0547 | 400 | 0.2289 |
60
- | 0.2277 | 0.0684 | 500 | 0.2274 |
61
- | 0.2448 | 0.0821 | 600 | 0.2225 |
62
- | 0.2281 | 0.0958 | 700 | 0.2245 |
63
- | 0.1926 | 0.1094 | 800 | 0.2221 |
64
- | 0.2274 | 0.1231 | 900 | 0.2196 |
65
- | 0.2124 | 0.1368 | 1000 | 0.2187 |
66
- | 0.1941 | 0.1505 | 1100 | 0.2171 |
67
- | 0.2056 | 0.1642 | 1200 | 0.2130 |
68
- | 0.2045 | 0.1778 | 1300 | 0.2146 |
69
- | 0.2526 | 0.1915 | 1400 | 0.2156 |
70
- | 0.2603 | 0.2052 | 1500 | 0.2127 |
71
- | 0.2054 | 0.2189 | 1600 | 0.2096 |
72
- | 0.2339 | 0.2326 | 1700 | 0.2102 |
73
- | 0.2152 | 0.2462 | 1800 | 0.2100 |
74
- | 0.2183 | 0.2599 | 1900 | 0.2020 |
75
- | 0.2139 | 0.2736 | 2000 | 0.2043 |
76
- | 0.2003 | 0.2873 | 2100 | 0.2009 |
77
- | 0.2205 | 0.3010 | 2200 | 0.2030 |
78
- | 0.2279 | 0.3146 | 2300 | 0.2024 |
79
- | 0.2143 | 0.3283 | 2400 | 0.2000 |
80
- | 0.2095 | 0.3420 | 2500 | 0.1964 |
81
- | 0.261 | 0.3557 | 2600 | 0.1976 |
82
- | 0.193 | 0.3694 | 2700 | 0.1942 |
83
- | 0.2 | 0.3830 | 2800 | 0.1944 |
84
- | 0.2057 | 0.3967 | 2900 | 0.1957 |
85
- | 0.2125 | 0.4104 | 3000 | 0.1936 |
86
- | 0.2202 | 0.4241 | 3100 | 0.1931 |
87
- | 0.1829 | 0.4378 | 3200 | 0.1910 |
88
- | 0.1676 | 0.4514 | 3300 | 0.1883 |
89
- | 0.2089 | 0.4651 | 3400 | 0.1909 |
90
- | 0.2321 | 0.4788 | 3500 | 0.1905 |
91
- | 0.1843 | 0.4925 | 3600 | 0.1870 |
92
- | 0.1601 | 0.5062 | 3700 | 0.1868 |
93
- | 0.2017 | 0.5198 | 3800 | 0.1860 |
94
- | 0.1762 | 0.5335 | 3900 | 0.1843 |
95
- | 0.1871 | 0.5472 | 4000 | 0.1836 |
96
- | 0.1568 | 0.5609 | 4100 | 0.1833 |
97
- | 0.1769 | 0.5746 | 4200 | 0.1816 |
98
- | 0.2005 | 0.5882 | 4300 | 0.1822 |
99
- | 0.1805 | 0.6019 | 4400 | 0.1823 |
100
- | 0.1904 | 0.6156 | 4500 | 0.1810 |
101
- | 0.1836 | 0.6293 | 4600 | 0.1789 |
102
- | 0.2285 | 0.6430 | 4700 | 0.1792 |
103
- | 0.1814 | 0.6566 | 4800 | 0.1777 |
104
- | 0.2276 | 0.6703 | 4900 | 0.1781 |
105
- | 0.1474 | 0.6840 | 5000 | 0.1771 |
106
- | 0.1894 | 0.6977 | 5100 | 0.1769 |
107
- | 0.2278 | 0.7114 | 5200 | 0.1762 |
108
- | 0.2075 | 0.7250 | 5300 | 0.1753 |
109
- | 0.192 | 0.7387 | 5400 | 0.1760 |
110
- | 0.1713 | 0.7524 | 5500 | 0.1752 |
111
- | 0.1733 | 0.7661 | 5600 | 0.1735 |
112
- | 0.1405 | 0.7798 | 5700 | 0.1736 |
113
- | 0.1841 | 0.7934 | 5800 | 0.1731 |
114
- | 0.1441 | 0.8071 | 5900 | 0.1727 |
115
- | 0.1628 | 0.8208 | 6000 | 0.1728 |
116
- | 0.2095 | 0.8345 | 6100 | 0.1728 |
117
- | 0.1821 | 0.8482 | 6200 | 0.1722 |
118
- | 0.1827 | 0.8618 | 6300 | 0.1719 |
119
- | 0.198 | 0.8755 | 6400 | 0.1722 |
120
- | 0.1494 | 0.8892 | 6500 | 0.1720 |
121
- | 0.1831 | 0.9029 | 6600 | 0.1718 |
122
- | 0.1776 | 0.9166 | 6700 | 0.1716 |
123
- | 0.1518 | 0.9302 | 6800 | 0.1718 |
124
- | 0.1747 | 0.9439 | 6900 | 0.1716 |
125
- | 0.1843 | 0.9576 | 7000 | 0.1715 |
126
- | 0.1725 | 0.9713 | 7100 | 0.1716 |
127
- | 0.174 | 0.9850 | 7200 | 0.1715 |
128
- | 0.2098 | 0.9986 | 7300 | 0.1716 |
129
 
130
 
131
  ### Framework versions
 
1
  ---
2
  library_name: transformers
3
  license: other
4
+ base_model: Qwen/Qwen2.5-7B
5
  tags:
6
  - llama-factory
7
  - full
 
16
 
17
  # 2and3_apps_30k_v6
18
 
19
+ This model is a fine-tuned version of [Qwen/Qwen2.5-7B](https://huggingface.co/Qwen/Qwen2.5-7B) on the 2and3_apps_30k_v6 dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.1718
22
 
23
  ## Model description
24
 
 
53
 
54
  | Training Loss | Epoch | Step | Validation Loss |
55
  |:-------------:|:------:|:----:|:---------------:|
56
+ | 0.2769 | 0.0137 | 100 | 0.2641 |
57
+ | 0.2417 | 0.0274 | 200 | 0.2440 |
58
+ | 0.191 | 0.0410 | 300 | 0.2346 |
59
+ | 0.2466 | 0.0547 | 400 | 0.2327 |
60
+ | 0.2261 | 0.0684 | 500 | 0.2279 |
61
+ | 0.2394 | 0.0821 | 600 | 0.2231 |
62
+ | 0.228 | 0.0958 | 700 | 0.2237 |
63
+ | 0.1909 | 0.1094 | 800 | 0.2225 |
64
+ | 0.2277 | 0.1231 | 900 | 0.2201 |
65
+ | 0.2108 | 0.1368 | 1000 | 0.2182 |
66
+ | 0.1904 | 0.1505 | 1100 | 0.2172 |
67
+ | 0.2012 | 0.1642 | 1200 | 0.2130 |
68
+ | 0.2042 | 0.1778 | 1300 | 0.2143 |
69
+ | 0.2516 | 0.1915 | 1400 | 0.2161 |
70
+ | 0.2591 | 0.2052 | 1500 | 0.2122 |
71
+ | 0.2037 | 0.2189 | 1600 | 0.2097 |
72
+ | 0.2319 | 0.2326 | 1700 | 0.2108 |
73
+ | 0.2162 | 0.2462 | 1800 | 0.2093 |
74
+ | 0.2157 | 0.2599 | 1900 | 0.2022 |
75
+ | 0.2117 | 0.2736 | 2000 | 0.2046 |
76
+ | 0.2004 | 0.2873 | 2100 | 0.2018 |
77
+ | 0.2174 | 0.3010 | 2200 | 0.2039 |
78
+ | 0.2266 | 0.3146 | 2300 | 0.2030 |
79
+ | 0.2164 | 0.3283 | 2400 | 0.2006 |
80
+ | 0.211 | 0.3420 | 2500 | 0.1958 |
81
+ | 0.2614 | 0.3557 | 2600 | 0.1964 |
82
+ | 0.193 | 0.3694 | 2700 | 0.1935 |
83
+ | 0.1974 | 0.3830 | 2800 | 0.1949 |
84
+ | 0.206 | 0.3967 | 2900 | 0.1953 |
85
+ | 0.2133 | 0.4104 | 3000 | 0.1925 |
86
+ | 0.2151 | 0.4241 | 3100 | 0.1928 |
87
+ | 0.1837 | 0.4378 | 3200 | 0.1912 |
88
+ | 0.1663 | 0.4514 | 3300 | 0.1882 |
89
+ | 0.2099 | 0.4651 | 3400 | 0.1903 |
90
+ | 0.2328 | 0.4788 | 3500 | 0.1898 |
91
+ | 0.1812 | 0.4925 | 3600 | 0.1867 |
92
+ | 0.1645 | 0.5062 | 3700 | 0.1866 |
93
+ | 0.2001 | 0.5198 | 3800 | 0.1859 |
94
+ | 0.1751 | 0.5335 | 3900 | 0.1841 |
95
+ | 0.1873 | 0.5472 | 4000 | 0.1833 |
96
+ | 0.1578 | 0.5609 | 4100 | 0.1833 |
97
+ | 0.1765 | 0.5746 | 4200 | 0.1814 |
98
+ | 0.2 | 0.5882 | 4300 | 0.1819 |
99
+ | 0.1796 | 0.6019 | 4400 | 0.1820 |
100
+ | 0.1925 | 0.6156 | 4500 | 0.1808 |
101
+ | 0.183 | 0.6293 | 4600 | 0.1786 |
102
+ | 0.2281 | 0.6430 | 4700 | 0.1792 |
103
+ | 0.1815 | 0.6566 | 4800 | 0.1780 |
104
+ | 0.2287 | 0.6703 | 4900 | 0.1781 |
105
+ | 0.1469 | 0.6840 | 5000 | 0.1774 |
106
+ | 0.19 | 0.6977 | 5100 | 0.1769 |
107
+ | 0.2257 | 0.7114 | 5200 | 0.1765 |
108
+ | 0.2059 | 0.7250 | 5300 | 0.1757 |
109
+ | 0.1917 | 0.7387 | 5400 | 0.1759 |
110
+ | 0.1715 | 0.7524 | 5500 | 0.1753 |
111
+ | 0.173 | 0.7661 | 5600 | 0.1738 |
112
+ | 0.1404 | 0.7798 | 5700 | 0.1741 |
113
+ | 0.1819 | 0.7934 | 5800 | 0.1735 |
114
+ | 0.144 | 0.8071 | 5900 | 0.1731 |
115
+ | 0.1597 | 0.8208 | 6000 | 0.1729 |
116
+ | 0.2092 | 0.8345 | 6100 | 0.1731 |
117
+ | 0.1837 | 0.8482 | 6200 | 0.1726 |
118
+ | 0.1839 | 0.8618 | 6300 | 0.1723 |
119
+ | 0.1997 | 0.8755 | 6400 | 0.1725 |
120
+ | 0.1485 | 0.8892 | 6500 | 0.1723 |
121
+ | 0.1837 | 0.9029 | 6600 | 0.1721 |
122
+ | 0.1809 | 0.9166 | 6700 | 0.1720 |
123
+ | 0.1512 | 0.9302 | 6800 | 0.1720 |
124
+ | 0.1755 | 0.9439 | 6900 | 0.1721 |
125
+ | 0.183 | 0.9576 | 7000 | 0.1720 |
126
+ | 0.1727 | 0.9713 | 7100 | 0.1719 |
127
+ | 0.1811 | 0.9850 | 7200 | 0.1718 |
128
+ | 0.2091 | 0.9986 | 7300 | 0.1718 |
129
 
130
 
131
  ### Framework versions
all_results.json CHANGED
@@ -1,12 +1,12 @@
1
  {
2
  "epoch": 1.0,
3
- "eval_loss": 0.17149809002876282,
4
- "eval_runtime": 5.8964,
5
- "eval_samples_per_second": 5.088,
6
- "eval_steps_per_second": 1.357,
7
  "total_flos": 176832585990144.0,
8
- "train_loss": 0.1979428825846449,
9
- "train_runtime": 18695.1866,
10
- "train_samples_per_second": 1.564,
11
- "train_steps_per_second": 0.391
12
  }
 
1
  {
2
  "epoch": 1.0,
3
+ "eval_loss": 0.17183586955070496,
4
+ "eval_runtime": 5.8976,
5
+ "eval_samples_per_second": 5.087,
6
+ "eval_steps_per_second": 1.356,
7
  "total_flos": 176832585990144.0,
8
+ "train_loss": 0.19812894271515952,
9
+ "train_runtime": 18578.2586,
10
+ "train_samples_per_second": 1.574,
11
+ "train_steps_per_second": 0.393
12
  }
config.json CHANGED
@@ -1,16 +1,16 @@
1
  {
2
- "_name_or_path": "Qwen/Qwen2.5-7B-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": 3584,
11
  "initializer_range": 0.02,
12
  "intermediate_size": 18944,
13
- "max_position_embeddings": 32768,
14
  "max_window_layers": 28,
15
  "model_type": "qwen2",
16
  "num_attention_heads": 28,
@@ -24,6 +24,7 @@
24
  "torch_dtype": "bfloat16",
25
  "transformers_version": "4.46.1",
26
  "use_cache": false,
 
27
  "use_sliding_window": false,
28
  "vocab_size": 152064
29
  }
 
1
  {
2
+ "_name_or_path": "Qwen/Qwen2.5-7B",
3
  "architectures": [
4
  "Qwen2ForCausalLM"
5
  ],
6
  "attention_dropout": 0.0,
7
  "bos_token_id": 151643,
8
+ "eos_token_id": 151643,
9
  "hidden_act": "silu",
10
  "hidden_size": 3584,
11
  "initializer_range": 0.02,
12
  "intermediate_size": 18944,
13
+ "max_position_embeddings": 131072,
14
  "max_window_layers": 28,
15
  "model_type": "qwen2",
16
  "num_attention_heads": 28,
 
24
  "torch_dtype": "bfloat16",
25
  "transformers_version": "4.46.1",
26
  "use_cache": false,
27
+ "use_mrope": false,
28
  "use_sliding_window": false,
29
  "vocab_size": 152064
30
  }
eval_results.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "epoch": 1.0,
3
- "eval_loss": 0.17149809002876282,
4
- "eval_runtime": 5.8964,
5
- "eval_samples_per_second": 5.088,
6
- "eval_steps_per_second": 1.357
7
  }
 
1
  {
2
  "epoch": 1.0,
3
+ "eval_loss": 0.17183586955070496,
4
+ "eval_runtime": 5.8976,
5
+ "eval_samples_per_second": 5.087,
6
+ "eval_steps_per_second": 1.356
7
  }
generation_config.json CHANGED
@@ -1,14 +1,6 @@
1
  {
2
  "bos_token_id": 151643,
3
- "do_sample": true,
4
- "eos_token_id": [
5
- 151645,
6
- 151643
7
- ],
8
- "pad_token_id": 151643,
9
- "repetition_penalty": 1.05,
10
- "temperature": 0.7,
11
- "top_k": 20,
12
- "top_p": 0.8,
13
  "transformers_version": "4.46.1"
14
  }
 
1
  {
2
  "bos_token_id": 151643,
3
+ "eos_token_id": 151643,
4
+ "max_new_tokens": 2048,
 
 
 
 
 
 
 
 
5
  "transformers_version": "4.46.1"
6
  }
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c64e391ee3dd9b2861abaee4fdde78d6a8270313a4d217f0702482987eeddf4
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d486a05a66342e8fb6b2907d05fcc241afa4f9ead14de004f6a526c37364e02
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:07b9fbf55348d70818483f2285190cb36ff4721bb86fd351d0738ee43b4b4816
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:303e8a06261b468f50ef50b08ff22d673f690e63b6121cc21a93f2010fa3347c
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:858d1cc1931e4c695815ed1b7c84f2d72544bc4001e01b8c7a7bf3cc68990f20
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6aa2af3bf2a66764ecf52ff17a31530e3a1f7f71891773322f99e48413e01f6d
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:470cedfc46d985fa5a54c2f3c9b701e47399f34ced57e0cfee93a849bce7ce57
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34cc2401502164f54b8e7d08cf3f5bc3dd8f6cdcb43a7931674b7e18f3226740
3
  size 1089994880
tokenizer_config.json CHANGED
@@ -195,7 +195,7 @@
195
  "<|video_pad|>"
196
  ],
197
  "bos_token": null,
198
- "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
199
  "clean_up_tokenization_spaces": false,
200
  "eos_token": "<|im_end|>",
201
  "errors": "replace",
 
195
  "<|video_pad|>"
196
  ],
197
  "bos_token": null,
198
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
199
  "clean_up_tokenization_spaces": false,
200
  "eos_token": "<|im_end|>",
201
  "errors": "replace",
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 1.0,
3
  "total_flos": 176832585990144.0,
4
- "train_loss": 0.1979428825846449,
5
- "train_runtime": 18695.1866,
6
- "train_samples_per_second": 1.564,
7
- "train_steps_per_second": 0.391
8
  }
 
1
  {
2
  "epoch": 1.0,
3
  "total_flos": 176832585990144.0,
4
+ "train_loss": 0.19812894271515952,
5
+ "train_runtime": 18578.2586,
6
+ "train_samples_per_second": 1.574,
7
+ "train_steps_per_second": 0.393
8
  }
trainer_log.jsonl CHANGED
The diff for this file is too large to render. See raw diff
 
trainer_state.json CHANGED
The diff for this file is too large to render. See raw diff
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c97c43f02e82105781bc79b1e7ae678304754376166d8771a5c0deb503994a4e
3
  size 7160
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7972a14ab69d9589b003318f87301a88ecd5d44a70cc8918466251449573425
3
  size 7160
training_eval_loss.png CHANGED
training_loss.png CHANGED