BhurchandiMandar commited on
Commit
4693c6d
·
verified ·
1 Parent(s): 61a2084

Delete checkpoint-50

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. checkpoint-50/README.md +0 -202
  2. checkpoint-50/adapter_config.json +0 -39
  3. checkpoint-50/adapter_model.safetensors +0 -3
  4. checkpoint-50/added_tokens.json +0 -28
  5. checkpoint-50/chat_template.jinja +0 -89
  6. checkpoint-50/global_step44/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0 -3
  7. checkpoint-50/global_step44/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0 -3
  8. checkpoint-50/global_step44/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0 -3
  9. checkpoint-50/global_step44/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0 -3
  10. checkpoint-50/global_step44/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0 -3
  11. checkpoint-50/global_step44/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0 -3
  12. checkpoint-50/global_step44/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0 -3
  13. checkpoint-50/global_step44/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0 -3
  14. checkpoint-50/global_step44/zero_pp_rank_0_mp_rank_00_model_states.pt +0 -3
  15. checkpoint-50/global_step44/zero_pp_rank_1_mp_rank_00_model_states.pt +0 -3
  16. checkpoint-50/global_step44/zero_pp_rank_2_mp_rank_00_model_states.pt +0 -3
  17. checkpoint-50/global_step44/zero_pp_rank_3_mp_rank_00_model_states.pt +0 -3
  18. checkpoint-50/global_step44/zero_pp_rank_4_mp_rank_00_model_states.pt +0 -3
  19. checkpoint-50/global_step44/zero_pp_rank_5_mp_rank_00_model_states.pt +0 -3
  20. checkpoint-50/global_step44/zero_pp_rank_6_mp_rank_00_model_states.pt +0 -3
  21. checkpoint-50/global_step44/zero_pp_rank_7_mp_rank_00_model_states.pt +0 -3
  22. checkpoint-50/global_step50/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0 -3
  23. checkpoint-50/global_step50/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0 -3
  24. checkpoint-50/global_step50/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0 -3
  25. checkpoint-50/global_step50/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0 -3
  26. checkpoint-50/global_step50/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0 -3
  27. checkpoint-50/global_step50/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0 -3
  28. checkpoint-50/global_step50/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0 -3
  29. checkpoint-50/global_step50/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0 -3
  30. checkpoint-50/global_step50/zero_pp_rank_0_mp_rank_00_model_states.pt +0 -3
  31. checkpoint-50/global_step50/zero_pp_rank_1_mp_rank_00_model_states.pt +0 -3
  32. checkpoint-50/global_step50/zero_pp_rank_2_mp_rank_00_model_states.pt +0 -3
  33. checkpoint-50/global_step50/zero_pp_rank_3_mp_rank_00_model_states.pt +0 -3
  34. checkpoint-50/global_step50/zero_pp_rank_4_mp_rank_00_model_states.pt +0 -3
  35. checkpoint-50/global_step50/zero_pp_rank_5_mp_rank_00_model_states.pt +0 -3
  36. checkpoint-50/global_step50/zero_pp_rank_6_mp_rank_00_model_states.pt +0 -3
  37. checkpoint-50/global_step50/zero_pp_rank_7_mp_rank_00_model_states.pt +0 -3
  38. checkpoint-50/latest +0 -1
  39. checkpoint-50/merges.txt +0 -0
  40. checkpoint-50/rng_state_0.pth +0 -3
  41. checkpoint-50/rng_state_1.pth +0 -3
  42. checkpoint-50/rng_state_2.pth +0 -3
  43. checkpoint-50/rng_state_3.pth +0 -3
  44. checkpoint-50/rng_state_4.pth +0 -3
  45. checkpoint-50/rng_state_5.pth +0 -3
  46. checkpoint-50/rng_state_6.pth +0 -3
  47. checkpoint-50/rng_state_7.pth +0 -3
  48. checkpoint-50/scheduler.pt +0 -3
  49. checkpoint-50/special_tokens_map.json +0 -31
  50. checkpoint-50/tokenizer.json +0 -3
checkpoint-50/README.md DELETED
@@ -1,202 +0,0 @@
1
- ---
2
- base_model: Qwen/Qwen3-8B
3
- library_name: peft
4
- ---
5
-
6
- # Model Card for Model ID
7
-
8
- <!-- Provide a quick summary of what the model is/does. -->
9
-
10
-
11
-
12
- ## Model Details
13
-
14
- ### Model Description
15
-
16
- <!-- Provide a longer summary of what this model is. -->
17
-
18
-
19
-
20
- - **Developed by:** [More Information Needed]
21
- - **Funded by [optional]:** [More Information Needed]
22
- - **Shared by [optional]:** [More Information Needed]
23
- - **Model type:** [More Information Needed]
24
- - **Language(s) (NLP):** [More Information Needed]
25
- - **License:** [More Information Needed]
26
- - **Finetuned from model [optional]:** [More Information Needed]
27
-
28
- ### Model Sources [optional]
29
-
30
- <!-- Provide the basic links for the model. -->
31
-
32
- - **Repository:** [More Information Needed]
33
- - **Paper [optional]:** [More Information Needed]
34
- - **Demo [optional]:** [More Information Needed]
35
-
36
- ## Uses
37
-
38
- <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
-
40
- ### Direct Use
41
-
42
- <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
-
44
- [More Information Needed]
45
-
46
- ### Downstream Use [optional]
47
-
48
- <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
-
50
- [More Information Needed]
51
-
52
- ### Out-of-Scope Use
53
-
54
- <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
-
56
- [More Information Needed]
57
-
58
- ## Bias, Risks, and Limitations
59
-
60
- <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
-
62
- [More Information Needed]
63
-
64
- ### Recommendations
65
-
66
- <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
-
68
- Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
-
70
- ## How to Get Started with the Model
71
-
72
- Use the code below to get started with the model.
73
-
74
- [More Information Needed]
75
-
76
- ## Training Details
77
-
78
- ### Training Data
79
-
80
- <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
-
82
- [More Information Needed]
83
-
84
- ### Training Procedure
85
-
86
- <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
-
88
- #### Preprocessing [optional]
89
-
90
- [More Information Needed]
91
-
92
-
93
- #### Training Hyperparameters
94
-
95
- - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
-
97
- #### Speeds, Sizes, Times [optional]
98
-
99
- <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
-
101
- [More Information Needed]
102
-
103
- ## Evaluation
104
-
105
- <!-- This section describes the evaluation protocols and provides the results. -->
106
-
107
- ### Testing Data, Factors & Metrics
108
-
109
- #### Testing Data
110
-
111
- <!-- This should link to a Dataset Card if possible. -->
112
-
113
- [More Information Needed]
114
-
115
- #### Factors
116
-
117
- <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
-
119
- [More Information Needed]
120
-
121
- #### Metrics
122
-
123
- <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
-
125
- [More Information Needed]
126
-
127
- ### Results
128
-
129
- [More Information Needed]
130
-
131
- #### Summary
132
-
133
-
134
-
135
- ## Model Examination [optional]
136
-
137
- <!-- Relevant interpretability work for the model goes here -->
138
-
139
- [More Information Needed]
140
-
141
- ## Environmental Impact
142
-
143
- <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
-
145
- Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
-
147
- - **Hardware Type:** [More Information Needed]
148
- - **Hours used:** [More Information Needed]
149
- - **Cloud Provider:** [More Information Needed]
150
- - **Compute Region:** [More Information Needed]
151
- - **Carbon Emitted:** [More Information Needed]
152
-
153
- ## Technical Specifications [optional]
154
-
155
- ### Model Architecture and Objective
156
-
157
- [More Information Needed]
158
-
159
- ### Compute Infrastructure
160
-
161
- [More Information Needed]
162
-
163
- #### Hardware
164
-
165
- [More Information Needed]
166
-
167
- #### Software
168
-
169
- [More Information Needed]
170
-
171
- ## Citation [optional]
172
-
173
- <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
-
175
- **BibTeX:**
176
-
177
- [More Information Needed]
178
-
179
- **APA:**
180
-
181
- [More Information Needed]
182
-
183
- ## Glossary [optional]
184
-
185
- <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
-
187
- [More Information Needed]
188
-
189
- ## More Information [optional]
190
-
191
- [More Information Needed]
192
-
193
- ## Model Card Authors [optional]
194
-
195
- [More Information Needed]
196
-
197
- ## Model Card Contact
198
-
199
- [More Information Needed]
200
- ### Framework versions
201
-
202
- - PEFT 0.15.2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-50/adapter_config.json DELETED
@@ -1,39 +0,0 @@
1
- {
2
- "alpha_pattern": {},
3
- "auto_mapping": null,
4
- "base_model_name_or_path": "Qwen/Qwen3-8B",
5
- "bias": "none",
6
- "corda_config": null,
7
- "eva_config": null,
8
- "exclude_modules": null,
9
- "fan_in_fan_out": false,
10
- "inference_mode": true,
11
- "init_lora_weights": true,
12
- "layer_replication": null,
13
- "layers_pattern": null,
14
- "layers_to_transform": null,
15
- "loftq_config": {},
16
- "lora_alpha": 16,
17
- "lora_bias": false,
18
- "lora_dropout": 0.05,
19
- "megatron_config": null,
20
- "megatron_core": "megatron.core",
21
- "modules_to_save": null,
22
- "peft_type": "LORA",
23
- "r": 8,
24
- "rank_pattern": {},
25
- "revision": null,
26
- "target_modules": [
27
- "v_proj",
28
- "up_proj",
29
- "down_proj",
30
- "o_proj",
31
- "gate_proj",
32
- "k_proj",
33
- "q_proj"
34
- ],
35
- "task_type": "CAUSAL_LM",
36
- "trainable_token_indices": null,
37
- "use_dora": false,
38
- "use_rslora": false
39
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-50/adapter_model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:79c0f0c6711730284cfc8c2a01daafd1ce46570f5a69dcd429c85d0adc13ac16
3
- size 43713984
 
 
 
 
checkpoint-50/added_tokens.json DELETED
@@ -1,28 +0,0 @@
1
- {
2
- "</think>": 151668,
3
- "</tool_call>": 151658,
4
- "</tool_response>": 151666,
5
- "<think>": 151667,
6
- "<tool_call>": 151657,
7
- "<tool_response>": 151665,
8
- "<|box_end|>": 151649,
9
- "<|box_start|>": 151648,
10
- "<|endoftext|>": 151643,
11
- "<|file_sep|>": 151664,
12
- "<|fim_middle|>": 151660,
13
- "<|fim_pad|>": 151662,
14
- "<|fim_prefix|>": 151659,
15
- "<|fim_suffix|>": 151661,
16
- "<|im_end|>": 151645,
17
- "<|im_start|>": 151644,
18
- "<|image_pad|>": 151655,
19
- "<|object_ref_end|>": 151647,
20
- "<|object_ref_start|>": 151646,
21
- "<|quad_end|>": 151651,
22
- "<|quad_start|>": 151650,
23
- "<|repo_name|>": 151663,
24
- "<|video_pad|>": 151656,
25
- "<|vision_end|>": 151653,
26
- "<|vision_pad|>": 151654,
27
- "<|vision_start|>": 151652
28
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-50/chat_template.jinja DELETED
@@ -1,89 +0,0 @@
1
- {%- if tools %}
2
- {{- '<|im_start|>system\n' }}
3
- {%- if messages[0].role == 'system' %}
4
- {{- messages[0].content + '\n\n' }}
5
- {%- endif %}
6
- {{- "# 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>" }}
7
- {%- for tool in tools %}
8
- {{- "\n" }}
9
- {{- tool | tojson }}
10
- {%- endfor %}
11
- {{- "\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" }}
12
- {%- else %}
13
- {%- if messages[0].role == 'system' %}
14
- {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
15
- {%- endif %}
16
- {%- endif %}
17
- {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
18
- {%- for message in messages[::-1] %}
19
- {%- set index = (messages|length - 1) - loop.index0 %}
20
- {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
21
- {%- set ns.multi_step_tool = false %}
22
- {%- set ns.last_query_index = index %}
23
- {%- endif %}
24
- {%- endfor %}
25
- {%- for message in messages %}
26
- {%- if message.content is string %}
27
- {%- set content = message.content %}
28
- {%- else %}
29
- {%- set content = '' %}
30
- {%- endif %}
31
- {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
32
- {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
33
- {%- elif message.role == "assistant" %}
34
- {%- set reasoning_content = '' %}
35
- {%- if message.reasoning_content is string %}
36
- {%- set reasoning_content = message.reasoning_content %}
37
- {%- else %}
38
- {%- if '</think>' in content %}
39
- {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
40
- {%- set content = content.split('</think>')[-1].lstrip('\n') %}
41
- {%- endif %}
42
- {%- endif %}
43
- {%- if loop.index0 > ns.last_query_index %}
44
- {%- if loop.last or (not loop.last and reasoning_content) %}
45
- {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
46
- {%- else %}
47
- {{- '<|im_start|>' + message.role + '\n' + content }}
48
- {%- endif %}
49
- {%- else %}
50
- {{- '<|im_start|>' + message.role + '\n' + content }}
51
- {%- endif %}
52
- {%- if message.tool_calls %}
53
- {%- for tool_call in message.tool_calls %}
54
- {%- if (loop.first and content) or (not loop.first) %}
55
- {{- '\n' }}
56
- {%- endif %}
57
- {%- if tool_call.function %}
58
- {%- set tool_call = tool_call.function %}
59
- {%- endif %}
60
- {{- '<tool_call>\n{"name": "' }}
61
- {{- tool_call.name }}
62
- {{- '", "arguments": ' }}
63
- {%- if tool_call.arguments is string %}
64
- {{- tool_call.arguments }}
65
- {%- else %}
66
- {{- tool_call.arguments | tojson }}
67
- {%- endif %}
68
- {{- '}\n</tool_call>' }}
69
- {%- endfor %}
70
- {%- endif %}
71
- {{- '<|im_end|>\n' }}
72
- {%- elif message.role == "tool" %}
73
- {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
74
- {{- '<|im_start|>user' }}
75
- {%- endif %}
76
- {{- '\n<tool_response>\n' }}
77
- {{- content }}
78
- {{- '\n</tool_response>' }}
79
- {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
80
- {{- '<|im_end|>\n' }}
81
- {%- endif %}
82
- {%- endif %}
83
- {%- endfor %}
84
- {%- if add_generation_prompt %}
85
- {{- '<|im_start|>assistant\n' }}
86
- {%- if enable_thinking is defined and enable_thinking is false %}
87
- {{- '<think>\n\n</think>\n\n' }}
88
- {%- endif %}
89
- {%- endif %}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-50/global_step44/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:a9de36fe4d5bcea143cac9d6c10df60648c387213936d0d79d7fda4d251abc0f
3
- size 32739589
 
 
 
 
checkpoint-50/global_step44/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:5b0732c53b076adc1100b2a70493aa0c75c1937fbd62dc4ef3c7bc268a1bafd8
3
- size 32739589
 
 
 
 
checkpoint-50/global_step44/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:5d6a809ba92d4bf901d77ad7d334d988765ba17cdd51cb25b43d59608de4b46d
3
- size 32739589
 
 
 
 
checkpoint-50/global_step44/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:2a67bff855608b804ad3623e6afe3e413a56e27791a4d443c7a80ea3b0ad0081
3
- size 32739589
 
 
 
 
checkpoint-50/global_step44/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:352207d4cffd1ec3eac2844b287eb27ff47b0dad349a7c50cb42c8218377915c
3
- size 32739589
 
 
 
 
checkpoint-50/global_step44/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:4aa163426b44d8986649c2173b1b2407bacc789896ad51dab813fa217a74e4d1
3
- size 32739589
 
 
 
 
checkpoint-50/global_step44/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:edc251cb7e94e454255d6a8fcc3b93e4ccf96a139b3586e37ed384c6381b26ce
3
- size 32739589
 
 
 
 
checkpoint-50/global_step44/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:522cc928155eca7288e4c77eaef9cfe2c051d4dec3180bb8652a8441e18bff5d
3
- size 32739589
 
 
 
 
checkpoint-50/global_step44/zero_pp_rank_0_mp_rank_00_model_states.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:372befffe03989dbdf4d378ff65b1822c6960e896481e6905bbafe72aba4a148
3
- size 504529
 
 
 
 
checkpoint-50/global_step44/zero_pp_rank_1_mp_rank_00_model_states.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:d55e5f34caa9fffb786489ae7ea7c404bac2759f6ef858ae426bf9f6585d2780
3
- size 504529
 
 
 
 
checkpoint-50/global_step44/zero_pp_rank_2_mp_rank_00_model_states.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:0a5b606de7b5beda42dbd0ca4172e6a7c578eb9c839fc9e31dd28b017c18b09d
3
- size 504529
 
 
 
 
checkpoint-50/global_step44/zero_pp_rank_3_mp_rank_00_model_states.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:fe36de82e6915098c4b20165d6458703640987a0b94b80103e6499047378cdeb
3
- size 504529
 
 
 
 
checkpoint-50/global_step44/zero_pp_rank_4_mp_rank_00_model_states.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:8973e5b60d1f4a8baddb88dd82158c90e377ea341397d8d4c9796f096526b1c2
3
- size 504529
 
 
 
 
checkpoint-50/global_step44/zero_pp_rank_5_mp_rank_00_model_states.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:b5a565b461f68a48a83fcf8b43b62165cb2db9404b7edfecf4ace2310109c5fe
3
- size 504529
 
 
 
 
checkpoint-50/global_step44/zero_pp_rank_6_mp_rank_00_model_states.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:2b1381fdc9460c3f5cbcf6b7fa3e8dbdf572c95ae6749de86b0e782a64448b33
3
- size 504529
 
 
 
 
checkpoint-50/global_step44/zero_pp_rank_7_mp_rank_00_model_states.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:13d42064f99b710ebd2d6222050d94593a0d7808fae98085e9263aa20b2b9008
3
- size 504529
 
 
 
 
checkpoint-50/global_step50/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:4f4d72a1737209c0b8e72fe13570baaba4a1c3055bb2b05d089e5333fd91d55a
3
- size 261886213
 
 
 
 
checkpoint-50/global_step50/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:ed2d08ce3db0e511a88c576a99a0d1da12d357c07481a05fd4b451aa8f845340
3
- size 261886213
 
 
 
 
checkpoint-50/global_step50/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:2be85d7801d57683658e759384e437063da074113cfff86785620a5961c033b3
3
- size 261886213
 
 
 
 
checkpoint-50/global_step50/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:c695ed726ba293243b46d082ead16d286c1bdcc596e1438f642beb293220ea24
3
- size 261886213
 
 
 
 
checkpoint-50/global_step50/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:4b78cf28d8c9fb9cefca4520938bb3b2ca5718e95dbce4eda2e4a2c027fd98c9
3
- size 261886213
 
 
 
 
checkpoint-50/global_step50/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:d04adb6bbdfce6d7a8d9636f41a95839f464274bf555274d95e92b1111544bc2
3
- size 261886213
 
 
 
 
checkpoint-50/global_step50/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:b6494495fbdfb2ca804879a2511f137d20d9359f90437f193cfc71131c4b3d43
3
- size 261886213
 
 
 
 
checkpoint-50/global_step50/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:d3eb73c09639ebf76e6d2d4f15073e17264aaff026471f30596106657dedbdbc
3
- size 261886213
 
 
 
 
checkpoint-50/global_step50/zero_pp_rank_0_mp_rank_00_model_states.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:7c01f8c0fa03f1d7befad2eb63031c91b9f5209cdd72a8c3b84187a007f19288
3
- size 504529
 
 
 
 
checkpoint-50/global_step50/zero_pp_rank_1_mp_rank_00_model_states.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:1407d5600bbb62c8fdee7903421f5f95101723dcf31f6eefc34ade6ad1ca949d
3
- size 504529
 
 
 
 
checkpoint-50/global_step50/zero_pp_rank_2_mp_rank_00_model_states.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:f6c4141b6fea5086e602ee16ca835a4abaaba189dd20ec863001b4363373acae
3
- size 504529
 
 
 
 
checkpoint-50/global_step50/zero_pp_rank_3_mp_rank_00_model_states.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:58b4d6e57ec646377961cfcdc6267fb433d24779950ec15dd43e53efcdf891dc
3
- size 504529
 
 
 
 
checkpoint-50/global_step50/zero_pp_rank_4_mp_rank_00_model_states.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:f43ca1dd28cc70a6711980ca193ac641efbe919aefe298114c8093293b6739db
3
- size 504529
 
 
 
 
checkpoint-50/global_step50/zero_pp_rank_5_mp_rank_00_model_states.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:258cbb29f6c827e929d627d012ced023ca4497f586dd581b394c69022daa0b3c
3
- size 504529
 
 
 
 
checkpoint-50/global_step50/zero_pp_rank_6_mp_rank_00_model_states.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:58c72ad0dee2e25386289b1a498d0efa5ebfa20fb19140f728a6fd1ea2ab30c4
3
- size 504529
 
 
 
 
checkpoint-50/global_step50/zero_pp_rank_7_mp_rank_00_model_states.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:b530209e28d101f43f9456112e8f36500558a2c6e653f90f2445772c4c95dc27
3
- size 504529
 
 
 
 
checkpoint-50/latest DELETED
@@ -1 +0,0 @@
1
- global_step44
 
 
checkpoint-50/merges.txt DELETED
The diff for this file is too large to render. See raw diff
 
checkpoint-50/rng_state_0.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:8f083214d6e54ffa40ba7c89a0b8ceb60d9a743f4a02eb5fce0f4a9f9b61934b
3
- size 16389
 
 
 
 
checkpoint-50/rng_state_1.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:85b629acd710a60eaf73732dc4205f6b24be2e0fc11b426ee424516aed5f72cd
3
- size 16389
 
 
 
 
checkpoint-50/rng_state_2.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:dfba5cff1fab0d5a4a59e9d26d73b86d8680c089ba3427d3f700fba6cf47f8bd
3
- size 16389
 
 
 
 
checkpoint-50/rng_state_3.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:cd1708a2da57906a954edb626e700e5d0e430574a92e540144aa5fa0dd292254
3
- size 16389
 
 
 
 
checkpoint-50/rng_state_4.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:32378442f326246f7297bea3283fe469a5fd67f2eb6cc5f15960a96d660727a2
3
- size 16389
 
 
 
 
checkpoint-50/rng_state_5.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:3374ddd16a0f504dcf5427e9f025684db5821c8077bfa4cf630e53749193de5b
3
- size 16389
 
 
 
 
checkpoint-50/rng_state_6.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:374a336911b22c295a8e9c974e056d18bc0b56d3e10e25d5ee0476ad78c607da
3
- size 16389
 
 
 
 
checkpoint-50/rng_state_7.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:17f3bd6ab1ca7dc6ca2a9ebbdb9b694ea511330e6ebcdc3004c9b216d4ab91ce
3
- size 16389
 
 
 
 
checkpoint-50/scheduler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:03c7bda8d6f35b03629d916e81eb3e59c5cf1cef30e8cc48bbdd17025b136e17
3
- size 1401
 
 
 
 
checkpoint-50/special_tokens_map.json DELETED
@@ -1,31 +0,0 @@
1
- {
2
- "additional_special_tokens": [
3
- "<|im_start|>",
4
- "<|im_end|>",
5
- "<|object_ref_start|>",
6
- "<|object_ref_end|>",
7
- "<|box_start|>",
8
- "<|box_end|>",
9
- "<|quad_start|>",
10
- "<|quad_end|>",
11
- "<|vision_start|>",
12
- "<|vision_end|>",
13
- "<|vision_pad|>",
14
- "<|image_pad|>",
15
- "<|video_pad|>"
16
- ],
17
- "eos_token": {
18
- "content": "<|im_end|>",
19
- "lstrip": false,
20
- "normalized": false,
21
- "rstrip": false,
22
- "single_word": false
23
- },
24
- "pad_token": {
25
- "content": "<|endoftext|>",
26
- "lstrip": false,
27
- "normalized": false,
28
- "rstrip": false,
29
- "single_word": false
30
- }
31
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-50/tokenizer.json DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
- size 11422654