theoracle commited on
Commit
769cfa4
1 Parent(s): ec0d9cb

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ checkpoint-1510/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - autotrain
4
+ - text-generation-inference
5
+ - text-generation
6
+ - peft
7
+ library_name: transformers
8
+ widget:
9
+ - messages:
10
+ - role: user
11
+ content: What is your favorite condiment?
12
+ license: other
13
+ ---
14
+
15
+ # Model Trained Using AutoTrain
16
+
17
+ This model was trained using AutoTrain. For more information, please visit [AutoTrain](https://hf.co/docs/autotrain).
18
+
19
+ # Usage
20
+
21
+ ```python
22
+
23
+ from transformers import AutoModelForCausalLM, AutoTokenizer
24
+
25
+ model_path = "PATH_TO_THIS_REPO"
26
+
27
+ tokenizer = AutoTokenizer.from_pretrained(model_path)
28
+ model = AutoModelForCausalLM.from_pretrained(
29
+ model_path,
30
+ device_map="auto",
31
+ torch_dtype='auto'
32
+ ).eval()
33
+
34
+ # Prompt content: "hi"
35
+ messages = [
36
+ {"role": "user", "content": "hi"}
37
+ ]
38
+
39
+ input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt')
40
+ output_ids = model.generate(input_ids.to('cuda'))
41
+ response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)
42
+
43
+ # Model response: "Hello! How can I assist you today?"
44
+ print(response)
45
+ ```
adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "google/gemma-2b",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
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": 32,
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": 16,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "q_proj",
24
+ "v_proj",
25
+ "o_proj",
26
+ "k_proj",
27
+ "down_proj",
28
+ "up_proj",
29
+ "gate_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d30b056b88583915b8d59ca195abb7317059378fcd8e04920267b67337ab9bc
3
+ size 78480072
checkpoint-1510/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: google/gemma-2b
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 0.10.0
checkpoint-1510/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "google/gemma-2b",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
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": 32,
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": 16,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "q_proj",
24
+ "v_proj",
25
+ "o_proj",
26
+ "k_proj",
27
+ "down_proj",
28
+ "up_proj",
29
+ "gate_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
checkpoint-1510/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d30b056b88583915b8d59ca195abb7317059378fcd8e04920267b67337ab9bc
3
+ size 78480072
checkpoint-1510/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:641ee65c2a67bedabc6674748052376f59a07498d3c900e405259fe192cd1907
3
+ size 157104826
checkpoint-1510/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:049c26b844b79121ddd8379f7f69194e63f6fbf6aa007eeac0c66f17eebb8893
3
+ size 888
checkpoint-1510/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:acd9e64418b18a213e330b76e3ffade700175d3764a4cda1ccfa4eadd7d9801c
3
+ size 14244
checkpoint-1510/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27983f2cce091d0023355d993bc1dc7ab95e04a7ace916fd95418c8f92b6bc1c
3
+ size 1064
checkpoint-1510/special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<bos>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<eos>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<pad>",
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
+ }
checkpoint-1510/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0d908b4f9326e0998815690e325b6abbd378978553e10627924dd825db7e243
3
+ size 17477553
checkpoint-1510/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
3
+ size 4241003
checkpoint-1510/tokenizer_config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<pad>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<eos>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "<bos>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "3": {
30
+ "content": "<unk>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ }
37
+ },
38
+ "bos_token": "<bos>",
39
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
40
+ "clean_up_tokenization_spaces": false,
41
+ "eos_token": "<eos>",
42
+ "legacy": null,
43
+ "model_max_length": 2048,
44
+ "pad_token": "<pad>",
45
+ "sp_model_kwargs": {},
46
+ "spaces_between_special_tokens": false,
47
+ "tokenizer_class": "GemmaTokenizer",
48
+ "unk_token": "<unk>",
49
+ "use_default_system_prompt": false
50
+ }
checkpoint-1510/trainer_state.json ADDED
@@ -0,0 +1,441 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 4.987613542526837,
5
+ "eval_steps": 500,
6
+ "global_step": 1510,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.08,
13
+ "grad_norm": 6.482018947601318,
14
+ "learning_rate": 4.768211920529802e-06,
15
+ "loss": 5.8299,
16
+ "step": 25
17
+ },
18
+ {
19
+ "epoch": 0.17,
20
+ "grad_norm": 4.826422691345215,
21
+ "learning_rate": 9.735099337748345e-06,
22
+ "loss": 5.1849,
23
+ "step": 50
24
+ },
25
+ {
26
+ "epoch": 0.25,
27
+ "grad_norm": 5.315689563751221,
28
+ "learning_rate": 1.4701986754966887e-05,
29
+ "loss": 4.4164,
30
+ "step": 75
31
+ },
32
+ {
33
+ "epoch": 0.33,
34
+ "grad_norm": 2.3576250076293945,
35
+ "learning_rate": 1.9668874172185433e-05,
36
+ "loss": 3.5949,
37
+ "step": 100
38
+ },
39
+ {
40
+ "epoch": 0.41,
41
+ "grad_norm": 1.602609634399414,
42
+ "learning_rate": 2.4635761589403972e-05,
43
+ "loss": 2.9948,
44
+ "step": 125
45
+ },
46
+ {
47
+ "epoch": 0.5,
48
+ "grad_norm": 1.4007989168167114,
49
+ "learning_rate": 2.9602649006622518e-05,
50
+ "loss": 2.6452,
51
+ "step": 150
52
+ },
53
+ {
54
+ "epoch": 0.58,
55
+ "grad_norm": 2.107353687286377,
56
+ "learning_rate": 2.9492273730684327e-05,
57
+ "loss": 2.4714,
58
+ "step": 175
59
+ },
60
+ {
61
+ "epoch": 0.66,
62
+ "grad_norm": 1.3134864568710327,
63
+ "learning_rate": 2.894039735099338e-05,
64
+ "loss": 2.3634,
65
+ "step": 200
66
+ },
67
+ {
68
+ "epoch": 0.74,
69
+ "grad_norm": 1.580680251121521,
70
+ "learning_rate": 2.838852097130243e-05,
71
+ "loss": 2.3032,
72
+ "step": 225
73
+ },
74
+ {
75
+ "epoch": 0.83,
76
+ "grad_norm": 1.3618550300598145,
77
+ "learning_rate": 2.783664459161148e-05,
78
+ "loss": 2.2501,
79
+ "step": 250
80
+ },
81
+ {
82
+ "epoch": 0.91,
83
+ "grad_norm": 1.531614899635315,
84
+ "learning_rate": 2.728476821192053e-05,
85
+ "loss": 2.2265,
86
+ "step": 275
87
+ },
88
+ {
89
+ "epoch": 0.99,
90
+ "grad_norm": 1.4849926233291626,
91
+ "learning_rate": 2.673289183222958e-05,
92
+ "loss": 2.1844,
93
+ "step": 300
94
+ },
95
+ {
96
+ "epoch": 1.07,
97
+ "grad_norm": 1.6642751693725586,
98
+ "learning_rate": 2.6181015452538634e-05,
99
+ "loss": 2.1166,
100
+ "step": 325
101
+ },
102
+ {
103
+ "epoch": 1.16,
104
+ "grad_norm": 1.7284085750579834,
105
+ "learning_rate": 2.5629139072847685e-05,
106
+ "loss": 2.1233,
107
+ "step": 350
108
+ },
109
+ {
110
+ "epoch": 1.24,
111
+ "grad_norm": 1.6671867370605469,
112
+ "learning_rate": 2.5077262693156735e-05,
113
+ "loss": 2.1212,
114
+ "step": 375
115
+ },
116
+ {
117
+ "epoch": 1.32,
118
+ "grad_norm": 1.756274938583374,
119
+ "learning_rate": 2.4525386313465785e-05,
120
+ "loss": 2.0726,
121
+ "step": 400
122
+ },
123
+ {
124
+ "epoch": 1.4,
125
+ "grad_norm": 1.8096344470977783,
126
+ "learning_rate": 2.3973509933774835e-05,
127
+ "loss": 2.0875,
128
+ "step": 425
129
+ },
130
+ {
131
+ "epoch": 1.49,
132
+ "grad_norm": 1.7899348735809326,
133
+ "learning_rate": 2.3421633554083885e-05,
134
+ "loss": 2.0833,
135
+ "step": 450
136
+ },
137
+ {
138
+ "epoch": 1.57,
139
+ "grad_norm": 1.917384386062622,
140
+ "learning_rate": 2.286975717439294e-05,
141
+ "loss": 2.0743,
142
+ "step": 475
143
+ },
144
+ {
145
+ "epoch": 1.65,
146
+ "grad_norm": 1.8895052671432495,
147
+ "learning_rate": 2.231788079470199e-05,
148
+ "loss": 2.0609,
149
+ "step": 500
150
+ },
151
+ {
152
+ "epoch": 1.73,
153
+ "grad_norm": 1.9963146448135376,
154
+ "learning_rate": 2.176600441501104e-05,
155
+ "loss": 2.0656,
156
+ "step": 525
157
+ },
158
+ {
159
+ "epoch": 1.82,
160
+ "grad_norm": 1.9002119302749634,
161
+ "learning_rate": 2.121412803532009e-05,
162
+ "loss": 2.0541,
163
+ "step": 550
164
+ },
165
+ {
166
+ "epoch": 1.9,
167
+ "grad_norm": 1.874874472618103,
168
+ "learning_rate": 2.066225165562914e-05,
169
+ "loss": 2.0416,
170
+ "step": 575
171
+ },
172
+ {
173
+ "epoch": 1.98,
174
+ "grad_norm": 1.7960671186447144,
175
+ "learning_rate": 2.011037527593819e-05,
176
+ "loss": 2.0311,
177
+ "step": 600
178
+ },
179
+ {
180
+ "epoch": 2.06,
181
+ "grad_norm": 2.1183598041534424,
182
+ "learning_rate": 1.9558498896247242e-05,
183
+ "loss": 2.0009,
184
+ "step": 625
185
+ },
186
+ {
187
+ "epoch": 2.15,
188
+ "grad_norm": 1.9861488342285156,
189
+ "learning_rate": 1.9006622516556292e-05,
190
+ "loss": 1.9688,
191
+ "step": 650
192
+ },
193
+ {
194
+ "epoch": 2.23,
195
+ "grad_norm": 2.235743284225464,
196
+ "learning_rate": 1.8454746136865343e-05,
197
+ "loss": 1.9989,
198
+ "step": 675
199
+ },
200
+ {
201
+ "epoch": 2.31,
202
+ "grad_norm": 1.955734133720398,
203
+ "learning_rate": 1.7902869757174393e-05,
204
+ "loss": 1.9733,
205
+ "step": 700
206
+ },
207
+ {
208
+ "epoch": 2.39,
209
+ "grad_norm": 2.044551372528076,
210
+ "learning_rate": 1.7350993377483443e-05,
211
+ "loss": 1.9574,
212
+ "step": 725
213
+ },
214
+ {
215
+ "epoch": 2.48,
216
+ "grad_norm": 2.117047071456909,
217
+ "learning_rate": 1.6799116997792496e-05,
218
+ "loss": 1.9654,
219
+ "step": 750
220
+ },
221
+ {
222
+ "epoch": 2.56,
223
+ "grad_norm": 2.02316951751709,
224
+ "learning_rate": 1.6247240618101546e-05,
225
+ "loss": 1.9498,
226
+ "step": 775
227
+ },
228
+ {
229
+ "epoch": 2.64,
230
+ "grad_norm": 2.2580747604370117,
231
+ "learning_rate": 1.5695364238410596e-05,
232
+ "loss": 1.9748,
233
+ "step": 800
234
+ },
235
+ {
236
+ "epoch": 2.73,
237
+ "grad_norm": 2.0818331241607666,
238
+ "learning_rate": 1.5143487858719647e-05,
239
+ "loss": 1.984,
240
+ "step": 825
241
+ },
242
+ {
243
+ "epoch": 2.81,
244
+ "grad_norm": 2.1940929889678955,
245
+ "learning_rate": 1.4591611479028698e-05,
246
+ "loss": 1.9646,
247
+ "step": 850
248
+ },
249
+ {
250
+ "epoch": 2.89,
251
+ "grad_norm": 2.1697773933410645,
252
+ "learning_rate": 1.4039735099337748e-05,
253
+ "loss": 1.958,
254
+ "step": 875
255
+ },
256
+ {
257
+ "epoch": 2.97,
258
+ "grad_norm": 2.0976200103759766,
259
+ "learning_rate": 1.3487858719646799e-05,
260
+ "loss": 1.946,
261
+ "step": 900
262
+ },
263
+ {
264
+ "epoch": 3.06,
265
+ "grad_norm": 2.160543441772461,
266
+ "learning_rate": 1.293598233995585e-05,
267
+ "loss": 1.9398,
268
+ "step": 925
269
+ },
270
+ {
271
+ "epoch": 3.14,
272
+ "grad_norm": 2.161280393600464,
273
+ "learning_rate": 1.23841059602649e-05,
274
+ "loss": 1.9008,
275
+ "step": 950
276
+ },
277
+ {
278
+ "epoch": 3.22,
279
+ "grad_norm": 2.2662644386291504,
280
+ "learning_rate": 1.183222958057395e-05,
281
+ "loss": 1.9111,
282
+ "step": 975
283
+ },
284
+ {
285
+ "epoch": 3.3,
286
+ "grad_norm": 2.374934673309326,
287
+ "learning_rate": 1.1280353200883002e-05,
288
+ "loss": 1.9087,
289
+ "step": 1000
290
+ },
291
+ {
292
+ "epoch": 3.39,
293
+ "grad_norm": 2.3813648223876953,
294
+ "learning_rate": 1.0728476821192052e-05,
295
+ "loss": 1.9116,
296
+ "step": 1025
297
+ },
298
+ {
299
+ "epoch": 3.47,
300
+ "grad_norm": 2.115699529647827,
301
+ "learning_rate": 1.0176600441501102e-05,
302
+ "loss": 1.92,
303
+ "step": 1050
304
+ },
305
+ {
306
+ "epoch": 3.55,
307
+ "grad_norm": 2.41668963432312,
308
+ "learning_rate": 9.624724061810154e-06,
309
+ "loss": 1.9452,
310
+ "step": 1075
311
+ },
312
+ {
313
+ "epoch": 3.63,
314
+ "grad_norm": 2.383557081222534,
315
+ "learning_rate": 9.072847682119206e-06,
316
+ "loss": 1.9209,
317
+ "step": 1100
318
+ },
319
+ {
320
+ "epoch": 3.72,
321
+ "grad_norm": 2.2272610664367676,
322
+ "learning_rate": 8.520971302428258e-06,
323
+ "loss": 1.9057,
324
+ "step": 1125
325
+ },
326
+ {
327
+ "epoch": 3.8,
328
+ "grad_norm": 2.5420844554901123,
329
+ "learning_rate": 7.969094922737308e-06,
330
+ "loss": 1.9025,
331
+ "step": 1150
332
+ },
333
+ {
334
+ "epoch": 3.88,
335
+ "grad_norm": 2.2384705543518066,
336
+ "learning_rate": 7.417218543046358e-06,
337
+ "loss": 1.9072,
338
+ "step": 1175
339
+ },
340
+ {
341
+ "epoch": 3.96,
342
+ "grad_norm": 2.2767913341522217,
343
+ "learning_rate": 6.865342163355408e-06,
344
+ "loss": 1.8947,
345
+ "step": 1200
346
+ },
347
+ {
348
+ "epoch": 4.05,
349
+ "grad_norm": 2.2728919982910156,
350
+ "learning_rate": 6.313465783664459e-06,
351
+ "loss": 1.8819,
352
+ "step": 1225
353
+ },
354
+ {
355
+ "epoch": 4.13,
356
+ "grad_norm": 2.4492197036743164,
357
+ "learning_rate": 5.76158940397351e-06,
358
+ "loss": 1.8914,
359
+ "step": 1250
360
+ },
361
+ {
362
+ "epoch": 4.21,
363
+ "grad_norm": 2.238704204559326,
364
+ "learning_rate": 5.20971302428256e-06,
365
+ "loss": 1.8723,
366
+ "step": 1275
367
+ },
368
+ {
369
+ "epoch": 4.29,
370
+ "grad_norm": 2.341646194458008,
371
+ "learning_rate": 4.657836644591612e-06,
372
+ "loss": 1.8808,
373
+ "step": 1300
374
+ },
375
+ {
376
+ "epoch": 4.38,
377
+ "grad_norm": 2.2996695041656494,
378
+ "learning_rate": 4.105960264900663e-06,
379
+ "loss": 1.88,
380
+ "step": 1325
381
+ },
382
+ {
383
+ "epoch": 4.46,
384
+ "grad_norm": 2.213731050491333,
385
+ "learning_rate": 3.554083885209713e-06,
386
+ "loss": 1.8597,
387
+ "step": 1350
388
+ },
389
+ {
390
+ "epoch": 4.54,
391
+ "grad_norm": 2.0925798416137695,
392
+ "learning_rate": 3.002207505518764e-06,
393
+ "loss": 1.853,
394
+ "step": 1375
395
+ },
396
+ {
397
+ "epoch": 4.62,
398
+ "grad_norm": 2.3262617588043213,
399
+ "learning_rate": 2.450331125827815e-06,
400
+ "loss": 1.8795,
401
+ "step": 1400
402
+ },
403
+ {
404
+ "epoch": 4.71,
405
+ "grad_norm": 2.3422157764434814,
406
+ "learning_rate": 1.8984547461368651e-06,
407
+ "loss": 1.865,
408
+ "step": 1425
409
+ },
410
+ {
411
+ "epoch": 4.79,
412
+ "grad_norm": 2.6429784297943115,
413
+ "learning_rate": 1.3465783664459163e-06,
414
+ "loss": 1.8871,
415
+ "step": 1450
416
+ },
417
+ {
418
+ "epoch": 4.87,
419
+ "grad_norm": 2.334404945373535,
420
+ "learning_rate": 7.947019867549669e-07,
421
+ "loss": 1.8886,
422
+ "step": 1475
423
+ },
424
+ {
425
+ "epoch": 4.95,
426
+ "grad_norm": 2.4886159896850586,
427
+ "learning_rate": 2.428256070640177e-07,
428
+ "loss": 1.8998,
429
+ "step": 1500
430
+ }
431
+ ],
432
+ "logging_steps": 25,
433
+ "max_steps": 1510,
434
+ "num_input_tokens_seen": 0,
435
+ "num_train_epochs": 5,
436
+ "save_steps": 500,
437
+ "total_flos": 7.427503857598464e+16,
438
+ "train_batch_size": 1,
439
+ "trial_name": null,
440
+ "trial_params": null
441
+ }
checkpoint-1510/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9dd7dc4eb8c9290178577870024a0e08d059c556c3752949322998b3f84ab9df
3
+ size 4984
runs/Mar27_21-31-40_r-theoracle-camoscio-oqvxu8bk-2220d-89nt2/events.out.tfevents.1711575101.r-theoracle-camoscio-oqvxu8bk-2220d-89nt2.59.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e190ead842b4f06251ee4e0e6ed3a59cf46929a1d159945b9135b32db6e4be90
3
- size 17615
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fb8d6f86b4a84b6476c6e0c8f799c2b0f22da68ae0b0d7ec63a50c2189fe657
3
+ size 18180
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<bos>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<eos>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<pad>",
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
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0d908b4f9326e0998815690e325b6abbd378978553e10627924dd825db7e243
3
+ size 17477553
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
3
+ size 4241003
tokenizer_config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<pad>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<eos>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "<bos>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "3": {
30
+ "content": "<unk>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ }
37
+ },
38
+ "bos_token": "<bos>",
39
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
40
+ "clean_up_tokenization_spaces": false,
41
+ "eos_token": "<eos>",
42
+ "legacy": null,
43
+ "model_max_length": 2048,
44
+ "pad_token": "<pad>",
45
+ "sp_model_kwargs": {},
46
+ "spaces_between_special_tokens": false,
47
+ "tokenizer_class": "GemmaTokenizer",
48
+ "unk_token": "<unk>",
49
+ "use_default_system_prompt": false
50
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9dd7dc4eb8c9290178577870024a0e08d059c556c3752949322998b3f84ab9df
3
+ size 4984
training_params.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model": "google/gemma-2b",
3
+ "project_name": "autotrain-91gzg-9j8r4",
4
+ "data_path": "autotrain-91gzg-9j8r4/autotrain-data",
5
+ "train_split": "train",
6
+ "valid_split": null,
7
+ "add_eos_token": true,
8
+ "block_size": 1024,
9
+ "model_max_length": 2048,
10
+ "padding": "right",
11
+ "trainer": "default",
12
+ "use_flash_attention_2": false,
13
+ "log": "tensorboard",
14
+ "disable_gradient_checkpointing": false,
15
+ "logging_steps": -1,
16
+ "evaluation_strategy": "epoch",
17
+ "save_total_limit": 1,
18
+ "save_strategy": "epoch",
19
+ "auto_find_batch_size": false,
20
+ "mixed_precision": "fp16",
21
+ "lr": 3e-05,
22
+ "epochs": 5,
23
+ "batch_size": 1,
24
+ "warmup_ratio": 0.1,
25
+ "gradient_accumulation": 4,
26
+ "optimizer": "adamw_torch",
27
+ "scheduler": "linear",
28
+ "weight_decay": 0.0,
29
+ "max_grad_norm": 1.0,
30
+ "seed": 42,
31
+ "chat_template": "none",
32
+ "quantization": "int4",
33
+ "target_modules": "all-linear",
34
+ "merge_adapter": false,
35
+ "peft": true,
36
+ "lora_r": 16,
37
+ "lora_alpha": 32,
38
+ "lora_dropout": 0.05,
39
+ "model_ref": null,
40
+ "dpo_beta": 0.1,
41
+ "prompt_text_column": "autotrain_prompt",
42
+ "text_column": "autotrain_text",
43
+ "rejected_text_column": "autotrain_rejected_text",
44
+ "push_to_hub": true,
45
+ "repo_id": "theoracle/autotrain-91gzg-9j8r4",
46
+ "username": "theoracle"
47
+ }