farmery commited on
Commit
3250bf6
1 Parent(s): 00e1fc2

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ 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
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,165 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: bigscience-bloom-rail-1.0
4
+ base_model: bigscience/bloomz-560m
5
+ tags:
6
+ - axolotl
7
+ - generated_from_trainer
8
+ model-index:
9
+ - name: 53ae6792-8a1c-4aad-b0e9-56452c4cfa48
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ [<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)
17
+ <details><summary>See axolotl config</summary>
18
+
19
+ axolotl version: `0.4.1`
20
+ ```yaml
21
+ accelerate_config:
22
+ dynamo_backend: inductor
23
+ mixed_precision: bf16
24
+ num_machines: 1
25
+ num_processes: auto
26
+ use_cpu: false
27
+ adapter: lora
28
+ base_model: bigscience/bloomz-560m
29
+ bf16: auto
30
+ chat_template: llama3
31
+ dataset_prepared_path: null
32
+ datasets:
33
+ - data_files:
34
+ - bf638221d9621524_train_data.json
35
+ ds_type: json
36
+ format: custom
37
+ path: /workspace/input_data/bf638221d9621524_train_data.json
38
+ type:
39
+ field_input: new-context
40
+ field_instruction: new-instruction
41
+ field_output: new-response
42
+ format: '{instruction} {input}'
43
+ no_input_format: '{instruction}'
44
+ system_format: '{system}'
45
+ system_prompt: ''
46
+ debug: null
47
+ deepspeed: null
48
+ device_map: auto
49
+ early_stopping_patience: null
50
+ eval_max_new_tokens: 128
51
+ eval_table_size: null
52
+ evals_per_epoch: 4
53
+ flash_attention: false
54
+ fp16: null
55
+ fsdp: null
56
+ fsdp_config: null
57
+ gradient_accumulation_steps: 16
58
+ gradient_checkpointing: true
59
+ group_by_length: false
60
+ hub_model_id: sn56m1/53ae6792-8a1c-4aad-b0e9-56452c4cfa48
61
+ hub_repo: null
62
+ hub_strategy: checkpoint
63
+ hub_token: null
64
+ learning_rate: 0.0001
65
+ local_rank: null
66
+ logging_steps: 1
67
+ lora_alpha: 16
68
+ lora_dropout: 0.05
69
+ lora_fan_in_fan_out: null
70
+ lora_model_dir: null
71
+ lora_r: 8
72
+ lora_target_linear: true
73
+ lora_target_modules:
74
+ - q_proj
75
+ - v_proj
76
+ lr_scheduler: cosine
77
+ max_memory:
78
+ 0: 70GiB
79
+ max_steps: 5
80
+ micro_batch_size: 2
81
+ mlflow_experiment_name: /tmp/bf638221d9621524_train_data.json
82
+ model_type: AutoModelForCausalLM
83
+ num_epochs: 1
84
+ optimizer: adamw_bnb_8bit
85
+ output_dir: miner_id_24
86
+ pad_to_sequence_len: true
87
+ quantization_config:
88
+ llm_int8_enable_fp32_cpu_offload: true
89
+ load_in_8bit: true
90
+ resume_from_checkpoint: null
91
+ s2_attention: null
92
+ sample_packing: false
93
+ saves_per_epoch: 4
94
+ sequence_len: 512
95
+ strict: false
96
+ tf32: false
97
+ tokenizer_type: AutoTokenizer
98
+ torch_compile: true
99
+ train_on_inputs: false
100
+ trust_remote_code: true
101
+ val_set_size: 0.05
102
+ wandb_entity: sn56-miner
103
+ wandb_mode: disabled
104
+ wandb_name: 53ae6792-8a1c-4aad-b0e9-56452c4cfa48
105
+ wandb_project: god
106
+ wandb_run: 53ae6792-8a1c-4aad-b0e9-56452c4cfa48
107
+ wandb_runid: 53ae6792-8a1c-4aad-b0e9-56452c4cfa48
108
+ warmup_steps: 10
109
+ weight_decay: 0.0
110
+ xformers_attention: null
111
+
112
+ ```
113
+
114
+ </details><br>
115
+
116
+ # 53ae6792-8a1c-4aad-b0e9-56452c4cfa48
117
+
118
+ This model is a fine-tuned version of [bigscience/bloomz-560m](https://huggingface.co/bigscience/bloomz-560m) on the None dataset.
119
+ It achieves the following results on the evaluation set:
120
+ - Loss: 2.1607
121
+
122
+ ## Model description
123
+
124
+ More information needed
125
+
126
+ ## Intended uses & limitations
127
+
128
+ More information needed
129
+
130
+ ## Training and evaluation data
131
+
132
+ More information needed
133
+
134
+ ## Training procedure
135
+
136
+ ### Training hyperparameters
137
+
138
+ The following hyperparameters were used during training:
139
+ - learning_rate: 0.0001
140
+ - train_batch_size: 2
141
+ - eval_batch_size: 2
142
+ - seed: 42
143
+ - gradient_accumulation_steps: 16
144
+ - total_train_batch_size: 32
145
+ - optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
146
+ - lr_scheduler_type: cosine
147
+ - lr_scheduler_warmup_steps: 10
148
+ - training_steps: 5
149
+
150
+ ### Training results
151
+
152
+ | Training Loss | Epoch | Step | Validation Loss |
153
+ |:-------------:|:------:|:----:|:---------------:|
154
+ | 34.7305 | 0.0023 | 1 | 2.1851 |
155
+ | 38.2578 | 0.0045 | 2 | 2.1764 |
156
+ | 34.0078 | 0.0090 | 4 | 2.1607 |
157
+
158
+
159
+ ### Framework versions
160
+
161
+ - PEFT 0.13.2
162
+ - Transformers 4.46.0
163
+ - Pytorch 2.5.0+cu124
164
+ - Datasets 3.0.1
165
+ - Tokenizers 0.20.1
adapter_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "bigscience/bloomz-560m",
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
+ "query_key_value",
24
+ "dense_4h_to_h",
25
+ "q_proj",
26
+ "dense_h_to_4h",
27
+ "dense",
28
+ "v_proj"
29
+ ],
30
+ "task_type": "CAUSAL_LM",
31
+ "use_dora": false,
32
+ "use_rslora": false
33
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f38696b78a99eef0e76f0b1b932deaf686fba57815619c8849ea2840fc1eb64a
3
+ size 12653386
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1570760d2f4dcd2f008038a4b4325a256833167c8e7ca7420b94edbef10cd0f0
3
+ size 12609416
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_attn_implementation_autoset": true,
3
+ "_name_or_path": "bigscience/bloomz-560m",
4
+ "apply_residual_connection_post_layernorm": false,
5
+ "architectures": [
6
+ "BloomForCausalLM"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "attention_softmax_in_fp32": true,
10
+ "bias_dropout_fusion": true,
11
+ "bos_token_id": 1,
12
+ "eos_token_id": 2,
13
+ "hidden_dropout": 0.0,
14
+ "hidden_size": 1024,
15
+ "initializer_range": 0.02,
16
+ "layer_norm_epsilon": 1e-05,
17
+ "masked_softmax_fusion": true,
18
+ "model_type": "bloom",
19
+ "n_head": 16,
20
+ "n_inner": null,
21
+ "n_layer": 24,
22
+ "offset_alibi": 100,
23
+ "pad_token_id": 3,
24
+ "pretraining_tp": 1,
25
+ "seq_length": 2048,
26
+ "skip_bias_add": true,
27
+ "skip_bias_add_qkv": false,
28
+ "slow_but_exact": false,
29
+ "transformers_version": "4.46.0",
30
+ "unk_token_id": 0,
31
+ "use_cache": false,
32
+ "vocab_size": 250880
33
+ }
last-checkpoint/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: bigscience/bloomz-560m
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 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "bigscience/bloomz-560m",
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
+ "query_key_value",
24
+ "dense_4h_to_h",
25
+ "q_proj",
26
+ "dense_h_to_4h",
27
+ "dense",
28
+ "v_proj"
29
+ ],
30
+ "task_type": "CAUSAL_LM",
31
+ "use_dora": false,
32
+ "use_rslora": false
33
+ }
last-checkpoint/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1570760d2f4dcd2f008038a4b4325a256833167c8e7ca7420b94edbef10cd0f0
3
+ size 12609416
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb172c541ac50a3b8bbb27818f6fc211464d94276a9fbdfc27693d2a7ee0e3f9
3
+ size 6614970
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:572c5653b97399d6dc550389d4e48df5479adab7c80147f357d4d04c0f7252da
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": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
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
+ }
last-checkpoint/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d963066d6adae5034a1dc114c3ac444512de09928cf14ed4562ba94d9a440e66
3
+ size 21763085
last-checkpoint/tokenizer_config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<unk>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<s>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<pad>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ }
36
+ },
37
+ "bos_token": "<s>",
38
+ "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 %}",
39
+ "clean_up_tokenization_spaces": false,
40
+ "eos_token": "</s>",
41
+ "merges_file": null,
42
+ "model_max_length": 1000000000000000019884624838656,
43
+ "pad_token": "<pad>",
44
+ "padding_side": "left",
45
+ "tokenizer_class": "BloomTokenizer",
46
+ "unk_token": "<unk>",
47
+ "vocab_file": null
48
+ }
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,92 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.011291460832745237,
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": 0.0022582921665490474,
13
+ "grad_norm": Infinity,
14
+ "learning_rate": 1e-05,
15
+ "loss": 34.7305,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.0022582921665490474,
20
+ "eval_loss": 2.1850547790527344,
21
+ "eval_runtime": 60.1674,
22
+ "eval_samples_per_second": 12.399,
23
+ "eval_steps_per_second": 6.199,
24
+ "step": 1
25
+ },
26
+ {
27
+ "epoch": 0.004516584333098095,
28
+ "grad_norm": 15.04525375366211,
29
+ "learning_rate": 2e-05,
30
+ "loss": 38.2578,
31
+ "step": 2
32
+ },
33
+ {
34
+ "epoch": 0.004516584333098095,
35
+ "eval_loss": 2.17636775970459,
36
+ "eval_runtime": 15.3363,
37
+ "eval_samples_per_second": 48.643,
38
+ "eval_steps_per_second": 24.321,
39
+ "step": 2
40
+ },
41
+ {
42
+ "epoch": 0.006774876499647142,
43
+ "grad_norm": 14.231776237487793,
44
+ "learning_rate": 3e-05,
45
+ "loss": 35.4102,
46
+ "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.00903316866619619,
50
+ "grad_norm": 15.738994598388672,
51
+ "learning_rate": 4e-05,
52
+ "loss": 34.0078,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.00903316866619619,
57
+ "eval_loss": 2.160700798034668,
58
+ "eval_runtime": 15.3137,
59
+ "eval_samples_per_second": 48.714,
60
+ "eval_steps_per_second": 24.357,
61
+ "step": 4
62
+ },
63
+ {
64
+ "epoch": 0.011291460832745237,
65
+ "grad_norm": 14.535213470458984,
66
+ "learning_rate": 5e-05,
67
+ "loss": 34.8828,
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": 174536943206400.0,
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 sha256:7a849e875f1161878daf1b54ecfe8c5ab169cfe39eb17f579b703c266f46ccce
3
+ size 6776
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
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:d963066d6adae5034a1dc114c3ac444512de09928cf14ed4562ba94d9a440e66
3
+ size 21763085
tokenizer_config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<unk>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<s>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<pad>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ }
36
+ },
37
+ "bos_token": "<s>",
38
+ "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 %}",
39
+ "clean_up_tokenization_spaces": false,
40
+ "eos_token": "</s>",
41
+ "merges_file": null,
42
+ "model_max_length": 1000000000000000019884624838656,
43
+ "pad_token": "<pad>",
44
+ "padding_side": "left",
45
+ "tokenizer_class": "BloomTokenizer",
46
+ "unk_token": "<unk>",
47
+ "vocab_file": null
48
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a849e875f1161878daf1b54ecfe8c5ab169cfe39eb17f579b703c266f46ccce
3
+ size 6776