farmery commited on
Commit
fe03610
1 Parent(s): 183f0cb

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,163 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: NousResearch/Yarn-Llama-2-13b-128k
4
+ tags:
5
+ - axolotl
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: 4af38394-9880-49df-97e6-8482c93ef8f4
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ [<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
16
+ <details><summary>See axolotl config</summary>
17
+
18
+ axolotl version: `0.4.1`
19
+ ```yaml
20
+ accelerate_config:
21
+ dynamo_backend: inductor
22
+ mixed_precision: bf16
23
+ num_machines: 1
24
+ num_processes: auto
25
+ use_cpu: false
26
+ adapter: lora
27
+ base_model: NousResearch/Yarn-Llama-2-13b-128k
28
+ bf16: auto
29
+ chat_template: llama3
30
+ dataset_prepared_path: null
31
+ datasets:
32
+ - data_files:
33
+ - 401ebe42ab876f94_train_data.json
34
+ ds_type: json
35
+ format: custom
36
+ path: /workspace/input_data/401ebe42ab876f94_train_data.json
37
+ type:
38
+ field_instruction: parts of speech
39
+ field_output: original text
40
+ format: '{instruction}'
41
+ no_input_format: '{instruction}'
42
+ system_format: '{system}'
43
+ system_prompt: ''
44
+ debug: null
45
+ deepspeed: null
46
+ device_map: auto
47
+ early_stopping_patience: null
48
+ eval_max_new_tokens: 128
49
+ eval_table_size: null
50
+ evals_per_epoch: 4
51
+ flash_attention: false
52
+ fp16: null
53
+ fsdp: null
54
+ fsdp_config: null
55
+ gradient_accumulation_steps: 16
56
+ gradient_checkpointing: true
57
+ group_by_length: false
58
+ hub_model_id: sn56m2/4af38394-9880-49df-97e6-8482c93ef8f4
59
+ hub_repo: null
60
+ hub_strategy: checkpoint
61
+ hub_token: null
62
+ learning_rate: 0.0001
63
+ local_rank: null
64
+ logging_steps: 1
65
+ lora_alpha: 16
66
+ lora_dropout: 0.05
67
+ lora_fan_in_fan_out: null
68
+ lora_model_dir: null
69
+ lora_r: 8
70
+ lora_target_linear: true
71
+ lora_target_modules:
72
+ - q_proj
73
+ - v_proj
74
+ lr_scheduler: cosine
75
+ max_memory:
76
+ 0: 70GiB
77
+ max_steps: 5
78
+ micro_batch_size: 2
79
+ mlflow_experiment_name: /tmp/401ebe42ab876f94_train_data.json
80
+ model_type: AutoModelForCausalLM
81
+ num_epochs: 1
82
+ optimizer: adamw_bnb_8bit
83
+ output_dir: miner_id_24
84
+ pad_to_sequence_len: true
85
+ quantization_config:
86
+ llm_int8_enable_fp32_cpu_offload: true
87
+ load_in_8bit: true
88
+ resume_from_checkpoint: null
89
+ s2_attention: null
90
+ sample_packing: false
91
+ saves_per_epoch: 4
92
+ sequence_len: 512
93
+ strict: false
94
+ tf32: false
95
+ tokenizer_type: AutoTokenizer
96
+ torch_compile: true
97
+ train_on_inputs: false
98
+ trust_remote_code: true
99
+ val_set_size: 0.05
100
+ wandb_entity: sn56-miner
101
+ wandb_mode: disabled
102
+ wandb_name: 4af38394-9880-49df-97e6-8482c93ef8f4
103
+ wandb_project: god
104
+ wandb_run: 4af38394-9880-49df-97e6-8482c93ef8f4
105
+ wandb_runid: 4af38394-9880-49df-97e6-8482c93ef8f4
106
+ warmup_steps: 10
107
+ weight_decay: 0.0
108
+ xformers_attention: null
109
+
110
+ ```
111
+
112
+ </details><br>
113
+
114
+ # 4af38394-9880-49df-97e6-8482c93ef8f4
115
+
116
+ This model is a fine-tuned version of [NousResearch/Yarn-Llama-2-13b-128k](https://huggingface.co/NousResearch/Yarn-Llama-2-13b-128k) on the None dataset.
117
+ It achieves the following results on the evaluation set:
118
+ - Loss: 10.6198
119
+
120
+ ## Model description
121
+
122
+ More information needed
123
+
124
+ ## Intended uses & limitations
125
+
126
+ More information needed
127
+
128
+ ## Training and evaluation data
129
+
130
+ More information needed
131
+
132
+ ## Training procedure
133
+
134
+ ### Training hyperparameters
135
+
136
+ The following hyperparameters were used during training:
137
+ - learning_rate: 0.0001
138
+ - train_batch_size: 2
139
+ - eval_batch_size: 2
140
+ - seed: 42
141
+ - gradient_accumulation_steps: 16
142
+ - total_train_batch_size: 32
143
+ - optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
144
+ - lr_scheduler_type: cosine
145
+ - lr_scheduler_warmup_steps: 10
146
+ - training_steps: 5
147
+
148
+ ### Training results
149
+
150
+ | Training Loss | Epoch | Step | Validation Loss |
151
+ |:-------------:|:------:|:----:|:---------------:|
152
+ | 172.9864 | 0.0026 | 1 | 10.9837 |
153
+ | 180.1079 | 0.0052 | 2 | 10.8069 |
154
+ | 176.9486 | 0.0104 | 4 | 10.6198 |
155
+
156
+
157
+ ### Framework versions
158
+
159
+ - PEFT 0.13.2
160
+ - Transformers 4.46.0
161
+ - Pytorch 2.5.0+cu124
162
+ - Datasets 3.0.1
163
+ - Tokenizers 0.20.1
adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "NousResearch/Yarn-Llama-2-13b-128k",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
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": 16,
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": 8,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "q_proj",
24
+ "v_proj",
25
+ "k_proj",
26
+ "down_proj",
27
+ "o_proj",
28
+ "gate_proj",
29
+ "up_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c37699a216387b1b3b80a7c317d9bf6c46053c21ca5f873ec6727fc493bf8de
3
+ size 125375434
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e1392c33e5d5a10caa2039d9b8eb734e30636a315137e365f64a1270f435025
3
+ size 125248064
config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_attn_implementation_autoset": true,
3
+ "_name_or_path": "NousResearch/Yarn-Llama-2-13b-128k",
4
+ "architectures": [
5
+ "LlamaForCausalLM"
6
+ ],
7
+ "auto_map": {
8
+ "AutoConfig": "NousResearch/Yarn-Llama-2-13b-128k--configuration_llama.LlamaConfig",
9
+ "AutoModelForCausalLM": "NousResearch/Yarn-Llama-2-13b-128k--modeling_llama_together_yarn.LlamaForCausalLM"
10
+ },
11
+ "bos_token_id": 1,
12
+ "eos_token_id": 2,
13
+ "hidden_act": "silu",
14
+ "hidden_size": 5120,
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 13824,
17
+ "max_position_embeddings": 131072,
18
+ "model_type": "llama",
19
+ "num_attention_heads": 40,
20
+ "num_hidden_layers": 40,
21
+ "num_key_value_heads": 40,
22
+ "pad_token_id": 0,
23
+ "pretraining_tp": 1,
24
+ "rms_norm_eps": 1e-05,
25
+ "rope_scaling": {
26
+ "factor": 32.0,
27
+ "finetuned": true,
28
+ "original_max_position_embeddings": 4096,
29
+ "type": "yarn"
30
+ },
31
+ "tie_word_embeddings": false,
32
+ "torch_dtype": "bfloat16",
33
+ "transformers_version": "4.46.0",
34
+ "use_cache": false,
35
+ "use_flash_attention": false,
36
+ "vocab_size": 32000
37
+ }
last-checkpoint/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: NousResearch/Yarn-Llama-2-13b-128k
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 0.13.2
last-checkpoint/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "NousResearch/Yarn-Llama-2-13b-128k",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
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": 16,
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": 8,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "q_proj",
24
+ "v_proj",
25
+ "k_proj",
26
+ "down_proj",
27
+ "o_proj",
28
+ "gate_proj",
29
+ "up_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
last-checkpoint/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e1392c33e5d5a10caa2039d9b8eb734e30636a315137e365f64a1270f435025
3
+ size 125248064
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bb940e87675bab774b550a16e6ac71b85600e7abeeb0a4679ab3485da631649
3
+ size 64219860
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afbf885258eba70f5506df642b9914670073e12a659d870c912f419df3669557
3
+ size 14244
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d63217b923cb177f669d6bc2174b89abdc6a56d968d279b505491b37976d9bb
3
+ size 1064
last-checkpoint/special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<unk>",
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": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
last-checkpoint/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
last-checkpoint/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
last-checkpoint/tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": true,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": true,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": true,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ }
30
+ },
31
+ "bos_token": "<s>",
32
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
33
+ "clean_up_tokenization_spaces": false,
34
+ "eos_token": "</s>",
35
+ "legacy": false,
36
+ "model_max_length": 1000000000000000019884624838656,
37
+ "pad_token": "<unk>",
38
+ "sp_model_kwargs": {},
39
+ "spaces_between_special_tokens": false,
40
+ "tokenizer_class": "LlamaTokenizer",
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": false
43
+ }
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,92 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.013029315960912053,
5
+ "eval_steps": 2,
6
+ "global_step": 5,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0026058631921824105,
13
+ "grad_norm": 83.162109375,
14
+ "learning_rate": 1e-05,
15
+ "loss": 172.9864,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.0026058631921824105,
20
+ "eval_loss": 10.98365306854248,
21
+ "eval_runtime": 63.2057,
22
+ "eval_samples_per_second": 10.236,
23
+ "eval_steps_per_second": 5.126,
24
+ "step": 1
25
+ },
26
+ {
27
+ "epoch": 0.005211726384364821,
28
+ "grad_norm": 86.73918151855469,
29
+ "learning_rate": 2e-05,
30
+ "loss": 180.1079,
31
+ "step": 2
32
+ },
33
+ {
34
+ "epoch": 0.005211726384364821,
35
+ "eval_loss": 10.806900024414062,
36
+ "eval_runtime": 34.0248,
37
+ "eval_samples_per_second": 19.016,
38
+ "eval_steps_per_second": 9.522,
39
+ "step": 2
40
+ },
41
+ {
42
+ "epoch": 0.007817589576547232,
43
+ "grad_norm": 103.43224334716797,
44
+ "learning_rate": 3e-05,
45
+ "loss": 174.1901,
46
+ "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.010423452768729642,
50
+ "grad_norm": 88.40193176269531,
51
+ "learning_rate": 4e-05,
52
+ "loss": 176.9486,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.010423452768729642,
57
+ "eval_loss": 10.61976146697998,
58
+ "eval_runtime": 34.2698,
59
+ "eval_samples_per_second": 18.88,
60
+ "eval_steps_per_second": 9.454,
61
+ "step": 4
62
+ },
63
+ {
64
+ "epoch": 0.013029315960912053,
65
+ "grad_norm": 97.77085876464844,
66
+ "learning_rate": 5e-05,
67
+ "loss": 174.9047,
68
+ "step": 5
69
+ }
70
+ ],
71
+ "logging_steps": 1,
72
+ "max_steps": 5,
73
+ "num_input_tokens_seen": 0,
74
+ "num_train_epochs": 1,
75
+ "save_steps": 2,
76
+ "stateful_callbacks": {
77
+ "TrainerControl": {
78
+ "args": {
79
+ "should_epoch_stop": false,
80
+ "should_evaluate": false,
81
+ "should_log": false,
82
+ "should_save": true,
83
+ "should_training_stop": true
84
+ },
85
+ "attributes": {}
86
+ }
87
+ },
88
+ "total_flos": 6332408345395200.0,
89
+ "train_batch_size": 2,
90
+ "trial_name": null,
91
+ "trial_params": null
92
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00f8c50fa6e67d2290870c82a843306927cfd013cef7b168b6fca3b826a4236a
3
+ size 6776
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<unk>",
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": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": true,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": true,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": true,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ }
30
+ },
31
+ "bos_token": "<s>",
32
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
33
+ "clean_up_tokenization_spaces": false,
34
+ "eos_token": "</s>",
35
+ "legacy": false,
36
+ "model_max_length": 1000000000000000019884624838656,
37
+ "pad_token": "<unk>",
38
+ "sp_model_kwargs": {},
39
+ "spaces_between_special_tokens": false,
40
+ "tokenizer_class": "LlamaTokenizer",
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": false
43
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00f8c50fa6e67d2290870c82a843306927cfd013cef7b168b6fca3b826a4236a
3
+ size 6776