IHaBiS commited on
Commit
2cd8487
·
verified ·
1 Parent(s): f5ae95e

Add files using upload-large-folder tool

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +8 -0
  2. classification_gemma_4b_test/checkpoint-132/README.md +205 -0
  3. classification_gemma_4b_test/checkpoint-66/adapter_config.json +8 -0
  4. classification_gemma_4b_test/checkpoint-66/chat_template.jinja +47 -0
  5. classification_gemma_4b_test/checkpoint-66/special_tokens_map.json +33 -0
  6. classification_gemma_4b_test/checkpoint-66/tokenizer_config.json +0 -0
  7. classification_gemma_4b_test/checkpoint-66/trainer_state.json +55 -0
  8. qwen_14b_rl_thinking_classification/checkpoint_epoch_0_batch_1000/adapter_model.safetensors +3 -0
  9. qwen_14b_rl_thinking_classification/checkpoint_epoch_0_batch_500/adapter_model.safetensors +3 -0
  10. qwen_14b_rl_thinking_classification/checkpoint_epoch_0_batch_final/adapter_model.safetensors +3 -0
  11. qwen_14b_test_b64_r16_alpha8_ct/adapter_model.safetensors +3 -0
  12. qwen_14b_test_b64_r16_alpha8_ct/checkpoint-132/adapter_model.safetensors +3 -0
  13. qwen_14b_test_b64_r16_alpha8_ct/checkpoint-132/optimizer.pt +3 -0
  14. qwen_14b_test_b64_r16_alpha8_ct/checkpoint-165/adapter_model.safetensors +3 -0
  15. qwen_14b_test_b64_r16_alpha8_ct/checkpoint-165/optimizer.pt +3 -0
  16. qwen_14b_test_b64_r16_alpha8_ct/checkpoint-198/adapter_model.safetensors +3 -0
  17. qwen_14b_test_b64_r16_alpha8_ct/checkpoint-198/optimizer.pt +3 -0
  18. qwen_14b_test_b64_r16_alpha8_ct/checkpoint-99/adapter_model.safetensors +3 -0
  19. qwen_14b_test_b64_r16_alpha8_ct_apply_chat_template/adapter_model.safetensors +3 -0
  20. qwen_14b_test_b64_r16_alpha8_ct_apply_chat_template/checkpoint-132/adapter_model.safetensors +3 -0
  21. qwen_14b_test_b64_r16_alpha8_ct_apply_chat_template/checkpoint-132/optimizer.pt +3 -0
  22. qwen_14b_test_b64_r16_alpha8_ct_apply_chat_template/checkpoint-165/adapter_model.safetensors +3 -0
  23. qwen_14b_test_b64_r16_alpha8_ct_apply_chat_template/checkpoint-165/optimizer.pt +3 -0
  24. qwen_14b_test_b64_r16_alpha8_ct_apply_chat_template/checkpoint-198/adapter_model.safetensors +3 -0
  25. qwen_14b_test_b64_r16_alpha8_ct_apply_chat_template/checkpoint-198/optimizer.pt +3 -0
  26. qwen_14b_test_b64_r16_alpha8_ct_apply_chat_template/checkpoint-33/adapter_model.safetensors +3 -0
  27. qwen_14b_test_b64_r16_alpha8_ct_apply_chat_template/checkpoint-33/optimizer.pt +3 -0
  28. qwen_14b_test_b64_r16_alpha8_ct_apply_chat_template/checkpoint-66/adapter_model.safetensors +3 -0
  29. qwen_14b_test_b64_r16_alpha8_ct_apply_chat_template/checkpoint-66/optimizer.pt +3 -0
  30. qwen_14b_test_b64_r16_alpha8_ct_apply_chat_template/checkpoint-99/adapter_model.safetensors +3 -0
  31. qwen_14b_test_b64_r16_alpha8_ct_apply_chat_template/checkpoint-99/optimizer.pt +3 -0
  32. qwen_14b_test_b64_r16_alpha8_ct_apply_chat_template_with_system_prompt/adapter_model.safetensors +3 -0
  33. qwen_14b_test_b64_r16_alpha8_ct_apply_chat_template_with_system_prompt/checkpoint-132/adapter_model.safetensors +3 -0
  34. qwen_14b_test_b64_r16_alpha8_ct_apply_chat_template_with_system_prompt/checkpoint-132/optimizer.pt +3 -0
  35. qwen_14b_test_b64_r16_alpha8_ct_apply_chat_template_with_system_prompt/checkpoint-132/rng_state.pth +3 -0
  36. qwen_14b_test_b64_r16_alpha8_ct_apply_chat_template_with_system_prompt/checkpoint-132/scheduler.pt +3 -0
  37. qwen_14b_test_b64_r16_alpha8_ct_apply_chat_template_with_system_prompt/checkpoint-132/tokenizer.json +3 -0
  38. qwen_14b_test_b64_r16_alpha8_ct_apply_chat_template_with_system_prompt/checkpoint-132/training_args.bin +3 -0
  39. qwen_14b_test_b64_r16_alpha8_ct_apply_chat_template_with_system_prompt/checkpoint-165/adapter_model.safetensors +3 -0
  40. qwen_14b_test_b64_r16_alpha8_ct_apply_chat_template_with_system_prompt/checkpoint-165/optimizer.pt +3 -0
  41. qwen_14b_test_b64_r16_alpha8_ct_apply_chat_template_with_system_prompt/checkpoint-165/tokenizer.json +3 -0
  42. qwen_14b_test_b64_r16_alpha8_ct_apply_chat_template_with_system_prompt/checkpoint-198/adapter_model.safetensors +3 -0
  43. qwen_14b_test_b64_r16_alpha8_ct_apply_chat_template_with_system_prompt/checkpoint-198/optimizer.pt +3 -0
  44. qwen_14b_test_b64_r16_alpha8_ct_apply_chat_template_with_system_prompt/checkpoint-33/adapter_model.safetensors +3 -0
  45. qwen_14b_test_b64_r16_alpha8_ct_apply_chat_template_with_system_prompt/checkpoint-33/optimizer.pt +3 -0
  46. qwen_14b_test_b64_r16_alpha8_ct_apply_chat_template_with_system_prompt/checkpoint-66/adapter_model.safetensors +3 -0
  47. qwen_14b_test_b64_r16_alpha8_ct_apply_chat_template_with_system_prompt/checkpoint-66/optimizer.pt +3 -0
  48. qwen_14b_test_b64_r16_alpha8_ct_apply_chat_template_with_system_prompt/checkpoint-99/adapter_model.safetensors +3 -0
  49. qwen_14b_test_b64_r16_alpha8_ct_apply_chat_template_with_system_prompt/checkpoint-99/optimizer.pt +3 -0
  50. qwen_14b_test_b64_r64_alpha32_ct/adapter_model.safetensors +3 -0
.gitattributes CHANGED
@@ -68,3 +68,11 @@ qwen_14b_rl_thinking_classification/checkpoint_epoch_0_batch_1000/tokenizer.json
68
  qwen_14b_rl_thinking_classification/checkpoint_epoch_0_batch_500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
69
  qwen_14b_test_b64_r16_alpha8_ct_apply_chat_template_with_system_prompt/cloudflared.deb filter=lfs diff=lfs merge=lfs -text
70
  qwen_14b_test_b64_r16_alpha8_ct_apply_chat_template_with_system_prompt/checkpoint-198/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
68
  qwen_14b_rl_thinking_classification/checkpoint_epoch_0_batch_500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
69
  qwen_14b_test_b64_r16_alpha8_ct_apply_chat_template_with_system_prompt/cloudflared.deb filter=lfs diff=lfs merge=lfs -text
70
  qwen_14b_test_b64_r16_alpha8_ct_apply_chat_template_with_system_prompt/checkpoint-198/tokenizer.json filter=lfs diff=lfs merge=lfs -text
71
+ qwen_14b_test_b64_r16_alpha8_ct_apply_chat_template_with_system_prompt/checkpoint-165/tokenizer.json filter=lfs diff=lfs merge=lfs -text
72
+ qwen_14b_test_b64_r16_alpha8_ct_apply_chat_template_with_system_prompt/checkpoint-132/tokenizer.json filter=lfs diff=lfs merge=lfs -text
73
+ qwen_4b_instruct_2507_test_b64_r16_alpha8_ct/checkpoint-66/tokenizer.json filter=lfs diff=lfs merge=lfs -text
74
+ qwen_4b_instruct_2507_test_b64_r16_alpha8_ct/checkpoint-33/tokenizer.json filter=lfs diff=lfs merge=lfs -text
75
+ qwen_4b_test_b16_r8_alpha8_ct_dtd80/checkpoint-954/tokenizer.json filter=lfs diff=lfs merge=lfs -text
76
+ qwen_4b_test_b16_r8_alpha8_ct_dtd80/checkpoint-848/tokenizer.json filter=lfs diff=lfs merge=lfs -text
77
+ qwen_4b_test_b16_r8_alpha8_ct_dtd80/checkpoint-742/tokenizer.json filter=lfs diff=lfs merge=lfs -text
78
+ qwen_4b_test_b16_r8_alpha8_ct_dtd80/checkpoint-636/tokenizer.json filter=lfs diff=lfs merge=lfs -text
classification_gemma_4b_test/checkpoint-132/README.md ADDED
@@ -0,0 +1,205 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: google/gemma-3-4b-it
3
+ library_name: peft
4
+ tags:
5
+ - base_model:adapter:google/gemma-3-4b-it
6
+ - lora
7
+ ---
8
+
9
+ # Model Card for Model ID
10
+
11
+ <!-- Provide a quick summary of what the model is/does. -->
12
+
13
+
14
+
15
+ ## Model Details
16
+
17
+ ### Model Description
18
+
19
+ <!-- Provide a longer summary of what this model is. -->
20
+
21
+
22
+
23
+ - **Developed by:** [More Information Needed]
24
+ - **Funded by [optional]:** [More Information Needed]
25
+ - **Shared by [optional]:** [More Information Needed]
26
+ - **Model type:** [More Information Needed]
27
+ - **Language(s) (NLP):** [More Information Needed]
28
+ - **License:** [More Information Needed]
29
+ - **Finetuned from model [optional]:** [More Information Needed]
30
+
31
+ ### Model Sources [optional]
32
+
33
+ <!-- Provide the basic links for the model. -->
34
+
35
+ - **Repository:** [More Information Needed]
36
+ - **Paper [optional]:** [More Information Needed]
37
+ - **Demo [optional]:** [More Information Needed]
38
+
39
+ ## Uses
40
+
41
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
42
+
43
+ ### Direct Use
44
+
45
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
46
+
47
+ [More Information Needed]
48
+
49
+ ### Downstream Use [optional]
50
+
51
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
52
+
53
+ [More Information Needed]
54
+
55
+ ### Out-of-Scope Use
56
+
57
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
58
+
59
+ [More Information Needed]
60
+
61
+ ## Bias, Risks, and Limitations
62
+
63
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
64
+
65
+ [More Information Needed]
66
+
67
+ ### Recommendations
68
+
69
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
70
+
71
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
72
+
73
+ ## How to Get Started with the Model
74
+
75
+ Use the code below to get started with the model.
76
+
77
+ [More Information Needed]
78
+
79
+ ## Training Details
80
+
81
+ ### Training Data
82
+
83
+ <!-- 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. -->
84
+
85
+ [More Information Needed]
86
+
87
+ ### Training Procedure
88
+
89
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
90
+
91
+ #### Preprocessing [optional]
92
+
93
+ [More Information Needed]
94
+
95
+
96
+ #### Training Hyperparameters
97
+
98
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
99
+
100
+ #### Speeds, Sizes, Times [optional]
101
+
102
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
103
+
104
+ [More Information Needed]
105
+
106
+ ## Evaluation
107
+
108
+ <!-- This section describes the evaluation protocols and provides the results. -->
109
+
110
+ ### Testing Data, Factors & Metrics
111
+
112
+ #### Testing Data
113
+
114
+ <!-- This should link to a Dataset Card if possible. -->
115
+
116
+ [More Information Needed]
117
+
118
+ #### Factors
119
+
120
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
121
+
122
+ [More Information Needed]
123
+
124
+ #### Metrics
125
+
126
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
127
+
128
+ [More Information Needed]
129
+
130
+ ### Results
131
+
132
+ [More Information Needed]
133
+
134
+ #### Summary
135
+
136
+
137
+
138
+ ## Model Examination [optional]
139
+
140
+ <!-- Relevant interpretability work for the model goes here -->
141
+
142
+ [More Information Needed]
143
+
144
+ ## Environmental Impact
145
+
146
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
147
+
148
+ 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).
149
+
150
+ - **Hardware Type:** [More Information Needed]
151
+ - **Hours used:** [More Information Needed]
152
+ - **Cloud Provider:** [More Information Needed]
153
+ - **Compute Region:** [More Information Needed]
154
+ - **Carbon Emitted:** [More Information Needed]
155
+
156
+ ## Technical Specifications [optional]
157
+
158
+ ### Model Architecture and Objective
159
+
160
+ [More Information Needed]
161
+
162
+ ### Compute Infrastructure
163
+
164
+ [More Information Needed]
165
+
166
+ #### Hardware
167
+
168
+ [More Information Needed]
169
+
170
+ #### Software
171
+
172
+ [More Information Needed]
173
+
174
+ ## Citation [optional]
175
+
176
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
177
+
178
+ **BibTeX:**
179
+
180
+ [More Information Needed]
181
+
182
+ **APA:**
183
+
184
+ [More Information Needed]
185
+
186
+ ## Glossary [optional]
187
+
188
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
189
+
190
+ [More Information Needed]
191
+
192
+ ## More Information [optional]
193
+
194
+ [More Information Needed]
195
+
196
+ ## Model Card Authors [optional]
197
+
198
+ [More Information Needed]
199
+
200
+ ## Model Card Contact
201
+
202
+ [More Information Needed]
203
+ ### Framework versions
204
+
205
+ - PEFT 0.17.1
classification_gemma_4b_test/checkpoint-66/adapter_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "google/gemma-3-4b-it",
4
+ "inference_mode": true,
5
+ "peft_type": "LORA",
6
+ "revision": null,
7
+ "task_type": "SEQ_CLS"
8
+ }
classification_gemma_4b_test/checkpoint-66/chat_template.jinja ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {{ bos_token }}
2
+ {%- if messages[0]['role'] == 'system' -%}
3
+ {%- if messages[0]['content'] is string -%}
4
+ {%- set first_user_prefix = messages[0]['content'] + '
5
+
6
+ ' -%}
7
+ {%- else -%}
8
+ {%- set first_user_prefix = messages[0]['content'][0]['text'] + '
9
+
10
+ ' -%}
11
+ {%- endif -%}
12
+ {%- set loop_messages = messages[1:] -%}
13
+ {%- else -%}
14
+ {%- set first_user_prefix = "" -%}
15
+ {%- set loop_messages = messages -%}
16
+ {%- endif -%}
17
+ {%- for message in loop_messages -%}
18
+ {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
19
+ {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
20
+ {%- endif -%}
21
+ {%- if (message['role'] == 'assistant') -%}
22
+ {%- set role = "model" -%}
23
+ {%- else -%}
24
+ {%- set role = message['role'] -%}
25
+ {%- endif -%}
26
+ {{ '<start_of_turn>' + role + '
27
+ ' + (first_user_prefix if loop.first else "") }}
28
+ {%- if message['content'] is string -%}
29
+ {{ message['content'] | trim }}
30
+ {%- elif message['content'] is iterable -%}
31
+ {%- for item in message['content'] -%}
32
+ {%- if item['type'] == 'image' -%}
33
+ {{ '<start_of_image>' }}
34
+ {%- elif item['type'] == 'text' -%}
35
+ {{ item['text'] | trim }}
36
+ {%- endif -%}
37
+ {%- endfor -%}
38
+ {%- else -%}
39
+ {{ raise_exception("Invalid content type") }}
40
+ {%- endif -%}
41
+ {{ '<end_of_turn>
42
+ ' }}
43
+ {%- endfor -%}
44
+ {%- if add_generation_prompt -%}
45
+ {{'<start_of_turn>model
46
+ '}}
47
+ {%- endif -%}
classification_gemma_4b_test/checkpoint-66/special_tokens_map.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "boi_token": "<start_of_image>",
3
+ "bos_token": {
4
+ "content": "<bos>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ "eoi_token": "<end_of_image>",
11
+ "eos_token": {
12
+ "content": "<eos>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false
17
+ },
18
+ "image_token": "<image_soft_token>",
19
+ "pad_token": {
20
+ "content": "<pad>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false
25
+ },
26
+ "unk_token": {
27
+ "content": "<unk>",
28
+ "lstrip": false,
29
+ "normalized": false,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ }
33
+ }
classification_gemma_4b_test/checkpoint-66/tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
classification_gemma_4b_test/checkpoint-66/trainer_state.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 66,
3
+ "best_metric": 0.3837648332118988,
4
+ "best_model_checkpoint": "classification_gemma_4b_test/checkpoint-66",
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 66,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 1.0,
14
+ "eval_accuracy": 0.8317073170731707,
15
+ "eval_f1": 0.8690702087286527,
16
+ "eval_loss": 0.3837648332118988,
17
+ "eval_precision": 0.89453125,
18
+ "eval_recall": 0.8450184501845018,
19
+ "eval_runtime": 3.9634,
20
+ "eval_samples_per_second": 103.447,
21
+ "eval_steps_per_second": 6.56,
22
+ "step": 66
23
+ }
24
+ ],
25
+ "logging_steps": 100,
26
+ "max_steps": 660,
27
+ "num_input_tokens_seen": 0,
28
+ "num_train_epochs": 10,
29
+ "save_steps": 500,
30
+ "stateful_callbacks": {
31
+ "EarlyStoppingCallback": {
32
+ "args": {
33
+ "early_stopping_patience": 5,
34
+ "early_stopping_threshold": 0.0005
35
+ },
36
+ "attributes": {
37
+ "early_stopping_patience_counter": 0
38
+ }
39
+ },
40
+ "TrainerControl": {
41
+ "args": {
42
+ "should_epoch_stop": false,
43
+ "should_evaluate": false,
44
+ "should_log": false,
45
+ "should_save": true,
46
+ "should_training_stop": false
47
+ },
48
+ "attributes": {}
49
+ }
50
+ },
51
+ "total_flos": 1.096257667820544e+16,
52
+ "train_batch_size": 8,
53
+ "trial_name": null,
54
+ "trial_params": null
55
+ }
qwen_14b_rl_thinking_classification/checkpoint_epoch_0_batch_1000/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7da48b5896f6f702e670ec30065de86bdba811ec1c24a06b925ea1c12a40b8e9
3
+ size 256976504
qwen_14b_rl_thinking_classification/checkpoint_epoch_0_batch_500/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7da48b5896f6f702e670ec30065de86bdba811ec1c24a06b925ea1c12a40b8e9
3
+ size 256976504
qwen_14b_rl_thinking_classification/checkpoint_epoch_0_batch_final/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7da48b5896f6f702e670ec30065de86bdba811ec1c24a06b925ea1c12a40b8e9
3
+ size 256976504
qwen_14b_test_b64_r16_alpha8_ct/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06e8013d8a9523659504f70c377afe12de3bc3b9bd27bff1f5993617321fc5b5
3
+ size 257006624
qwen_14b_test_b64_r16_alpha8_ct/checkpoint-132/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a415172f7183b0dba32076cbc6505c0b71f4ecc03df4af3c5643dcb0b31055d
3
+ size 257006624
qwen_14b_test_b64_r16_alpha8_ct/checkpoint-132/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40783c8604875d953ac8fd4afcbfb0fd3e6892a9d07f10e3e5fe1957eb0bdfe5
3
+ size 514325430
qwen_14b_test_b64_r16_alpha8_ct/checkpoint-165/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9f6130389f4ac14314d0b9fcf25c8c5d7e5fb0ef91215df4f75aad1b8583fdb
3
+ size 257006624
qwen_14b_test_b64_r16_alpha8_ct/checkpoint-165/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47ac462af4f580f5cb36972ed37e0e19099b04b7236d19afd4f387a1b838a0ac
3
+ size 514325430
qwen_14b_test_b64_r16_alpha8_ct/checkpoint-198/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a50e2f08621201f0be242732263c0402a7481817f7ade2bfe417b1cc17aef02
3
+ size 257006624
qwen_14b_test_b64_r16_alpha8_ct/checkpoint-198/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f980dcb0277514db805571b4d414182c5996987c7b4ef31bd567dd18ab2fe8c5
3
+ size 514325430
qwen_14b_test_b64_r16_alpha8_ct/checkpoint-99/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06e8013d8a9523659504f70c377afe12de3bc3b9bd27bff1f5993617321fc5b5
3
+ size 257006624
qwen_14b_test_b64_r16_alpha8_ct_apply_chat_template/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f20eeb4e951c82498c2f052428d5ffd1327c11ef737c4301e178ea335283f5c
3
+ size 257006624
qwen_14b_test_b64_r16_alpha8_ct_apply_chat_template/checkpoint-132/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82a6e9574743d40028cee61935bb84e4e4d3750ca7979515da4c20a01d3ac957
3
+ size 257006624
qwen_14b_test_b64_r16_alpha8_ct_apply_chat_template/checkpoint-132/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:423547d8739b2d03dd29c3686bee44b1e757077ee8b12fb095997afd13d96134
3
+ size 514325430
qwen_14b_test_b64_r16_alpha8_ct_apply_chat_template/checkpoint-165/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44254946c08a868c53426341c8b836c2dc838237c0adb6cf55ad1c89e33c8076
3
+ size 257006624
qwen_14b_test_b64_r16_alpha8_ct_apply_chat_template/checkpoint-165/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57335cd8c8995e6695a55812a8e74fab273158e98339aa84b1f053c88d18796a
3
+ size 514325430
qwen_14b_test_b64_r16_alpha8_ct_apply_chat_template/checkpoint-198/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9694ffb90e57810cfd3bbc0157ab1e1df4ab7c3e6084fee478d7e5d49f658bc1
3
+ size 257006624
qwen_14b_test_b64_r16_alpha8_ct_apply_chat_template/checkpoint-198/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80e1d60d308fb17aa2782cf1ef3dc788431c7e5c447bb242b92b2b529d4fa8cb
3
+ size 514325430
qwen_14b_test_b64_r16_alpha8_ct_apply_chat_template/checkpoint-33/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db0dc799a370f30315807a376e7d83c6ea9541144c60255339e1b5190086c53f
3
+ size 257006624
qwen_14b_test_b64_r16_alpha8_ct_apply_chat_template/checkpoint-33/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9b2731c79f742886c482337478ca829c03d4bfceebecea3fb7fa78bc2f2c081
3
+ size 514325430
qwen_14b_test_b64_r16_alpha8_ct_apply_chat_template/checkpoint-66/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e12255bb40bd8768b6b009f855c51229589a19098148b1b14c679b7486af839f
3
+ size 257006624
qwen_14b_test_b64_r16_alpha8_ct_apply_chat_template/checkpoint-66/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a85ffa8f5257bb416fa0a7b342d7049df11261b0acc505fa7dd99db4b9269851
3
+ size 514325430
qwen_14b_test_b64_r16_alpha8_ct_apply_chat_template/checkpoint-99/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f20eeb4e951c82498c2f052428d5ffd1327c11ef737c4301e178ea335283f5c
3
+ size 257006624
qwen_14b_test_b64_r16_alpha8_ct_apply_chat_template/checkpoint-99/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1071a01aff0f48da1dfa83461a26f2a237df3291f0e130c01debac35c91fbc35
3
+ size 514325430
qwen_14b_test_b64_r16_alpha8_ct_apply_chat_template_with_system_prompt/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b21d66344f3c76cac284a2b4db9dc903c08bc6240e885bd915c5b977ff3f7af
3
+ size 257006624
qwen_14b_test_b64_r16_alpha8_ct_apply_chat_template_with_system_prompt/checkpoint-132/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e35e73dc05bcc237a4ec36ac16c8c9eed4e2e50929181950de752f070f7eb0de
3
+ size 257006624
qwen_14b_test_b64_r16_alpha8_ct_apply_chat_template_with_system_prompt/checkpoint-132/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d3a74bb571b50b1fb78bfadc3fe7fddf706da88c6e49033ee2f7617793b558d
3
+ size 514325430
qwen_14b_test_b64_r16_alpha8_ct_apply_chat_template_with_system_prompt/checkpoint-132/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ecdc92a8a68d9b01b430b20655abafb23cc6a0c3404dd5b34dc971906715ac3
3
+ size 14581
qwen_14b_test_b64_r16_alpha8_ct_apply_chat_template_with_system_prompt/checkpoint-132/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25906b6d9cd287b02f3755613e0335dfbe2ccaee687581444ef59353042b97f0
3
+ size 1465
qwen_14b_test_b64_r16_alpha8_ct_apply_chat_template_with_system_prompt/checkpoint-132/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
+ size 11422654
qwen_14b_test_b64_r16_alpha8_ct_apply_chat_template_with_system_prompt/checkpoint-132/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43ced9cd2a26ff1759794abb2678d23126fb5f2869d6f976bc10d55b1d6bca50
3
+ size 5841
qwen_14b_test_b64_r16_alpha8_ct_apply_chat_template_with_system_prompt/checkpoint-165/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffa8a5903035a127e873681ed6a244ae6d93d9ce97e42526c044f2fadb19e8fe
3
+ size 257006624
qwen_14b_test_b64_r16_alpha8_ct_apply_chat_template_with_system_prompt/checkpoint-165/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae89d24b00183de0cf601af6e46274db4d8aeb490f292cdab264a4d22ffd9813
3
+ size 514325430
qwen_14b_test_b64_r16_alpha8_ct_apply_chat_template_with_system_prompt/checkpoint-165/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
+ size 11422654
qwen_14b_test_b64_r16_alpha8_ct_apply_chat_template_with_system_prompt/checkpoint-198/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0b5f501dc458b2ba6bfb1a739a57653f337b6800a102f78e85c946225f621c8
3
+ size 257006624
qwen_14b_test_b64_r16_alpha8_ct_apply_chat_template_with_system_prompt/checkpoint-198/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e00fbfc10ca13ade5a6ca6eb768959ae29fa97474476df9565d2dd38a9534c6
3
+ size 514325430
qwen_14b_test_b64_r16_alpha8_ct_apply_chat_template_with_system_prompt/checkpoint-33/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b39cd55efe0087055859cdce30d158d158107f12c430bec64ce1875407e3ba5e
3
+ size 257006624
qwen_14b_test_b64_r16_alpha8_ct_apply_chat_template_with_system_prompt/checkpoint-33/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a377c0b76f65f2de8a1d6f929c1e2d94b8a57ba19a151e6f38cfa6864da0a0b7
3
+ size 514325430
qwen_14b_test_b64_r16_alpha8_ct_apply_chat_template_with_system_prompt/checkpoint-66/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4730d9d7d8e2b00e4a9b50c5e202d4373f8a6d618640b263d188ff9c7acfb2c1
3
+ size 257006624
qwen_14b_test_b64_r16_alpha8_ct_apply_chat_template_with_system_prompt/checkpoint-66/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47b2e8ebe07a60e8a8aab487a0c1d2f84b6b8a94a9ae8aecb0eb0e9954c1357c
3
+ size 514325430
qwen_14b_test_b64_r16_alpha8_ct_apply_chat_template_with_system_prompt/checkpoint-99/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b21d66344f3c76cac284a2b4db9dc903c08bc6240e885bd915c5b977ff3f7af
3
+ size 257006624
qwen_14b_test_b64_r16_alpha8_ct_apply_chat_template_with_system_prompt/checkpoint-99/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39dc4c9ca1fa2846109c352ac832cc480d1ad74ae50658860df97ceb4e9101d1
3
+ size 514325430
qwen_14b_test_b64_r64_alpha32_ct/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd35458a3eda3e8373687187d0ae27453bddfc38a95a891e79c9e45c346f4c50
3
+ size 1027710368