athirdpath commited on
Commit
47c2ed1
1 Parent(s): c911821

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: teknium/OpenHermes-2.5-Mistral-7B
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: lora-outB
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ [<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
15
+ # lora-outB
16
+
17
+ This model is a fine-tuned version of [teknium/OpenHermes-2.5-Mistral-7B](https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B) on the None dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 1.4546
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 2e-05
39
+ - train_batch_size: 8
40
+ - eval_batch_size: 8
41
+ - seed: 42
42
+ - gradient_accumulation_steps: 5
43
+ - total_train_batch_size: 40
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: cosine
46
+ - lr_scheduler_warmup_steps: 10
47
+ - num_epochs: 5
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss |
52
+ |:-------------:|:-----:|:----:|:---------------:|
53
+ | 1.5629 | 0.75 | 25 | 1.6511 |
54
+ | 1.5253 | 1.5 | 50 | 1.5730 |
55
+ | 1.3363 | 2.25 | 75 | 1.5014 |
56
+ | 1.4017 | 2.99 | 100 | 1.4690 |
57
+ | 1.2677 | 3.74 | 125 | 1.4593 |
58
+ | 1.351 | 4.49 | 150 | 1.4546 |
59
+
60
+
61
+ ### Framework versions
62
+
63
+ - Transformers 4.34.1
64
+ - Pytorch 2.1.0+cu118
65
+ - Datasets 2.14.6
66
+ - Tokenizers 0.14.1
adapter_config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "teknium/OpenHermes-2.5-Mistral-7B",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "lora_alpha": 32,
12
+ "lora_dropout": 0.05,
13
+ "modules_to_save": null,
14
+ "peft_type": "LORA",
15
+ "r": 128,
16
+ "rank_pattern": {},
17
+ "revision": null,
18
+ "target_modules": [
19
+ "q_proj",
20
+ "k_proj",
21
+ "up_proj",
22
+ "o_proj",
23
+ "gate_proj",
24
+ "down_proj",
25
+ "v_proj"
26
+ ],
27
+ "task_type": "CAUSAL_LM"
28
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cc4f98f72e6ab33b93346265f31f32adcc362ffd925e5c929c2561d2fb3dd34
3
+ size 1342339274
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<|im_end|>": 32000,
3
+ "<|im_start|>": 32001
4
+ }
checkpoint-100/README.md ADDED
@@ -0,0 +1,219 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: teknium/OpenHermes-2.5-Mistral-7B
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
+ - **Shared by [optional]:** [More Information Needed]
22
+ - **Model type:** [More Information Needed]
23
+ - **Language(s) (NLP):** [More Information Needed]
24
+ - **License:** [More Information Needed]
25
+ - **Finetuned from model [optional]:** [More Information Needed]
26
+
27
+ ### Model Sources [optional]
28
+
29
+ <!-- Provide the basic links for the model. -->
30
+
31
+ - **Repository:** [More Information Needed]
32
+ - **Paper [optional]:** [More Information Needed]
33
+ - **Demo [optional]:** [More Information Needed]
34
+
35
+ ## Uses
36
+
37
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
38
+
39
+ ### Direct Use
40
+
41
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
42
+
43
+ [More Information Needed]
44
+
45
+ ### Downstream Use [optional]
46
+
47
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
48
+
49
+ [More Information Needed]
50
+
51
+ ### Out-of-Scope Use
52
+
53
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
54
+
55
+ [More Information Needed]
56
+
57
+ ## Bias, Risks, and Limitations
58
+
59
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
60
+
61
+ [More Information Needed]
62
+
63
+ ### Recommendations
64
+
65
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
66
+
67
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
68
+
69
+ ## How to Get Started with the Model
70
+
71
+ Use the code below to get started with the model.
72
+
73
+ [More Information Needed]
74
+
75
+ ## Training Details
76
+
77
+ ### Training Data
78
+
79
+ <!-- This should link to a Data 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. -->
80
+
81
+ [More Information Needed]
82
+
83
+ ### Training Procedure
84
+
85
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
86
+
87
+ #### Preprocessing [optional]
88
+
89
+ [More Information Needed]
90
+
91
+
92
+ #### Training Hyperparameters
93
+
94
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
95
+
96
+ #### Speeds, Sizes, Times [optional]
97
+
98
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
99
+
100
+ [More Information Needed]
101
+
102
+ ## Evaluation
103
+
104
+ <!-- This section describes the evaluation protocols and provides the results. -->
105
+
106
+ ### Testing Data, Factors & Metrics
107
+
108
+ #### Testing Data
109
+
110
+ <!-- This should link to a Data Card if possible. -->
111
+
112
+ [More Information Needed]
113
+
114
+ #### Factors
115
+
116
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
117
+
118
+ [More Information Needed]
119
+
120
+ #### Metrics
121
+
122
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
123
+
124
+ [More Information Needed]
125
+
126
+ ### Results
127
+
128
+ [More Information Needed]
129
+
130
+ #### Summary
131
+
132
+
133
+
134
+ ## Model Examination [optional]
135
+
136
+ <!-- Relevant interpretability work for the model goes here -->
137
+
138
+ [More Information Needed]
139
+
140
+ ## Environmental Impact
141
+
142
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
143
+
144
+ 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).
145
+
146
+ - **Hardware Type:** [More Information Needed]
147
+ - **Hours used:** [More Information Needed]
148
+ - **Cloud Provider:** [More Information Needed]
149
+ - **Compute Region:** [More Information Needed]
150
+ - **Carbon Emitted:** [More Information Needed]
151
+
152
+ ## Technical Specifications [optional]
153
+
154
+ ### Model Architecture and Objective
155
+
156
+ [More Information Needed]
157
+
158
+ ### Compute Infrastructure
159
+
160
+ [More Information Needed]
161
+
162
+ #### Hardware
163
+
164
+ [More Information Needed]
165
+
166
+ #### Software
167
+
168
+ [More Information Needed]
169
+
170
+ ## Citation [optional]
171
+
172
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
173
+
174
+ **BibTeX:**
175
+
176
+ [More Information Needed]
177
+
178
+ **APA:**
179
+
180
+ [More Information Needed]
181
+
182
+ ## Glossary [optional]
183
+
184
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
185
+
186
+ [More Information Needed]
187
+
188
+ ## More Information [optional]
189
+
190
+ [More Information Needed]
191
+
192
+ ## Model Card Authors [optional]
193
+
194
+ [More Information Needed]
195
+
196
+ ## Model Card Contact
197
+
198
+ [More Information Needed]
199
+
200
+
201
+ ## Training procedure
202
+
203
+
204
+ The following `bitsandbytes` quantization config was used during training:
205
+ - quant_method: bitsandbytes
206
+ - load_in_8bit: True
207
+ - load_in_4bit: False
208
+ - llm_int8_threshold: 6.0
209
+ - llm_int8_skip_modules: None
210
+ - llm_int8_enable_fp32_cpu_offload: False
211
+ - llm_int8_has_fp16_weight: False
212
+ - bnb_4bit_quant_type: fp4
213
+ - bnb_4bit_use_double_quant: False
214
+ - bnb_4bit_compute_dtype: float32
215
+
216
+ ### Framework versions
217
+
218
+
219
+ - PEFT 0.6.0
checkpoint-100/adapter_config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "teknium/OpenHermes-2.5-Mistral-7B",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "lora_alpha": 32,
12
+ "lora_dropout": 0.05,
13
+ "modules_to_save": null,
14
+ "peft_type": "LORA",
15
+ "r": 128,
16
+ "rank_pattern": {},
17
+ "revision": null,
18
+ "target_modules": [
19
+ "q_proj",
20
+ "k_proj",
21
+ "up_proj",
22
+ "o_proj",
23
+ "gate_proj",
24
+ "down_proj",
25
+ "v_proj"
26
+ ],
27
+ "task_type": "CAUSAL_LM"
28
+ }
checkpoint-100/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17456f76fd7f3e462cafac25cfea3e25b950daa3039e42090bce88b5cd477666
3
+ size 1342339274
checkpoint-100/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9181035a5616518d113eaec2ff777dc792db8076fb052494f25f8a486552c08f
3
+ size 14244
checkpoint-100/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5d2ad6e302cd5816cfcc3c90378a6581d35b9b572941ccc3a9cc7f9abac53f2
3
+ size 1064
checkpoint-100/trainer_state.json ADDED
@@ -0,0 +1,651 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.4689786434173584,
3
+ "best_model_checkpoint": "./lora-outB/checkpoint-100",
4
+ "epoch": 2.9940119760479043,
5
+ "eval_steps": 25,
6
+ "global_step": 100,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.03,
13
+ "learning_rate": 2.0000000000000003e-06,
14
+ "loss": 1.866,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.06,
19
+ "learning_rate": 4.000000000000001e-06,
20
+ "loss": 1.7383,
21
+ "step": 2
22
+ },
23
+ {
24
+ "epoch": 0.09,
25
+ "learning_rate": 6e-06,
26
+ "loss": 1.8306,
27
+ "step": 3
28
+ },
29
+ {
30
+ "epoch": 0.12,
31
+ "learning_rate": 8.000000000000001e-06,
32
+ "loss": 1.9213,
33
+ "step": 4
34
+ },
35
+ {
36
+ "epoch": 0.15,
37
+ "learning_rate": 1e-05,
38
+ "loss": 1.9524,
39
+ "step": 5
40
+ },
41
+ {
42
+ "epoch": 0.18,
43
+ "learning_rate": 1.2e-05,
44
+ "loss": 1.7308,
45
+ "step": 6
46
+ },
47
+ {
48
+ "epoch": 0.21,
49
+ "learning_rate": 1.4e-05,
50
+ "loss": 1.7334,
51
+ "step": 7
52
+ },
53
+ {
54
+ "epoch": 0.24,
55
+ "learning_rate": 1.6000000000000003e-05,
56
+ "loss": 1.6749,
57
+ "step": 8
58
+ },
59
+ {
60
+ "epoch": 0.27,
61
+ "learning_rate": 1.8e-05,
62
+ "loss": 1.805,
63
+ "step": 9
64
+ },
65
+ {
66
+ "epoch": 0.3,
67
+ "learning_rate": 2e-05,
68
+ "loss": 1.778,
69
+ "step": 10
70
+ },
71
+ {
72
+ "epoch": 0.33,
73
+ "learning_rate": 1.9997946042345128e-05,
74
+ "loss": 1.7804,
75
+ "step": 11
76
+ },
77
+ {
78
+ "epoch": 0.36,
79
+ "learning_rate": 1.9991785013128922e-05,
80
+ "loss": 1.8191,
81
+ "step": 12
82
+ },
83
+ {
84
+ "epoch": 0.39,
85
+ "learning_rate": 1.998151944325001e-05,
86
+ "loss": 1.7089,
87
+ "step": 13
88
+ },
89
+ {
90
+ "epoch": 0.42,
91
+ "learning_rate": 1.996715354971755e-05,
92
+ "loss": 1.7131,
93
+ "step": 14
94
+ },
95
+ {
96
+ "epoch": 0.45,
97
+ "learning_rate": 1.994869323391895e-05,
98
+ "loss": 1.917,
99
+ "step": 15
100
+ },
101
+ {
102
+ "epoch": 0.48,
103
+ "learning_rate": 1.9926146079195597e-05,
104
+ "loss": 1.6701,
105
+ "step": 16
106
+ },
107
+ {
108
+ "epoch": 0.51,
109
+ "learning_rate": 1.989952134772769e-05,
110
+ "loss": 1.7119,
111
+ "step": 17
112
+ },
113
+ {
114
+ "epoch": 0.54,
115
+ "learning_rate": 1.9868829976729444e-05,
116
+ "loss": 1.7037,
117
+ "step": 18
118
+ },
119
+ {
120
+ "epoch": 0.57,
121
+ "learning_rate": 1.983408457395613e-05,
122
+ "loss": 1.7314,
123
+ "step": 19
124
+ },
125
+ {
126
+ "epoch": 0.6,
127
+ "learning_rate": 1.9795299412524948e-05,
128
+ "loss": 1.6771,
129
+ "step": 20
130
+ },
131
+ {
132
+ "epoch": 0.63,
133
+ "learning_rate": 1.975249042505174e-05,
134
+ "loss": 1.6734,
135
+ "step": 21
136
+ },
137
+ {
138
+ "epoch": 0.66,
139
+ "learning_rate": 1.970567519710602e-05,
140
+ "loss": 1.689,
141
+ "step": 22
142
+ },
143
+ {
144
+ "epoch": 0.69,
145
+ "learning_rate": 1.9654872959986936e-05,
146
+ "loss": 1.7452,
147
+ "step": 23
148
+ },
149
+ {
150
+ "epoch": 0.72,
151
+ "learning_rate": 1.960010458282326e-05,
152
+ "loss": 1.7126,
153
+ "step": 24
154
+ },
155
+ {
156
+ "epoch": 0.75,
157
+ "learning_rate": 1.954139256400049e-05,
158
+ "loss": 1.5629,
159
+ "step": 25
160
+ },
161
+ {
162
+ "epoch": 0.75,
163
+ "eval_loss": 1.6511253118515015,
164
+ "eval_runtime": 5.4427,
165
+ "eval_samples_per_second": 5.145,
166
+ "eval_steps_per_second": 0.735,
167
+ "step": 25
168
+ },
169
+ {
170
+ "epoch": 0.78,
171
+ "learning_rate": 1.947876102191873e-05,
172
+ "loss": 1.6948,
173
+ "step": 26
174
+ },
175
+ {
176
+ "epoch": 0.81,
177
+ "learning_rate": 1.9412235685085034e-05,
178
+ "loss": 1.5969,
179
+ "step": 27
180
+ },
181
+ {
182
+ "epoch": 0.84,
183
+ "learning_rate": 1.9341843881544372e-05,
184
+ "loss": 1.5367,
185
+ "step": 28
186
+ },
187
+ {
188
+ "epoch": 0.87,
189
+ "learning_rate": 1.926761452765349e-05,
190
+ "loss": 1.463,
191
+ "step": 29
192
+ },
193
+ {
194
+ "epoch": 0.9,
195
+ "learning_rate": 1.918957811620231e-05,
196
+ "loss": 1.4575,
197
+ "step": 30
198
+ },
199
+ {
200
+ "epoch": 0.93,
201
+ "learning_rate": 1.9107766703887764e-05,
202
+ "loss": 1.5928,
203
+ "step": 31
204
+ },
205
+ {
206
+ "epoch": 0.96,
207
+ "learning_rate": 1.9022213898145176e-05,
208
+ "loss": 1.5604,
209
+ "step": 32
210
+ },
211
+ {
212
+ "epoch": 0.99,
213
+ "learning_rate": 1.893295484334259e-05,
214
+ "loss": 1.6508,
215
+ "step": 33
216
+ },
217
+ {
218
+ "epoch": 1.02,
219
+ "learning_rate": 1.8840026206343786e-05,
220
+ "loss": 1.4583,
221
+ "step": 34
222
+ },
223
+ {
224
+ "epoch": 1.05,
225
+ "learning_rate": 1.8743466161445823e-05,
226
+ "loss": 1.7124,
227
+ "step": 35
228
+ },
229
+ {
230
+ "epoch": 1.08,
231
+ "learning_rate": 1.8643314374697377e-05,
232
+ "loss": 1.462,
233
+ "step": 36
234
+ },
235
+ {
236
+ "epoch": 1.11,
237
+ "learning_rate": 1.853961198760426e-05,
238
+ "loss": 1.6664,
239
+ "step": 37
240
+ },
241
+ {
242
+ "epoch": 1.14,
243
+ "learning_rate": 1.8432401600228823e-05,
244
+ "loss": 1.6264,
245
+ "step": 38
246
+ },
247
+ {
248
+ "epoch": 1.17,
249
+ "learning_rate": 1.832172725369024e-05,
250
+ "loss": 1.6704,
251
+ "step": 39
252
+ },
253
+ {
254
+ "epoch": 1.2,
255
+ "learning_rate": 1.8207634412072765e-05,
256
+ "loss": 1.5221,
257
+ "step": 40
258
+ },
259
+ {
260
+ "epoch": 1.23,
261
+ "learning_rate": 1.8090169943749477e-05,
262
+ "loss": 1.5411,
263
+ "step": 41
264
+ },
265
+ {
266
+ "epoch": 1.26,
267
+ "learning_rate": 1.7969382102129153e-05,
268
+ "loss": 1.4493,
269
+ "step": 42
270
+ },
271
+ {
272
+ "epoch": 1.29,
273
+ "learning_rate": 1.7845320505834176e-05,
274
+ "loss": 1.4783,
275
+ "step": 43
276
+ },
277
+ {
278
+ "epoch": 1.32,
279
+ "learning_rate": 1.771803611831762e-05,
280
+ "loss": 1.5882,
281
+ "step": 44
282
+ },
283
+ {
284
+ "epoch": 1.35,
285
+ "learning_rate": 1.758758122692791e-05,
286
+ "loss": 1.5848,
287
+ "step": 45
288
+ },
289
+ {
290
+ "epoch": 1.38,
291
+ "learning_rate": 1.74540094214296e-05,
292
+ "loss": 1.4439,
293
+ "step": 46
294
+ },
295
+ {
296
+ "epoch": 1.41,
297
+ "learning_rate": 1.7317375571989158e-05,
298
+ "loss": 1.5398,
299
+ "step": 47
300
+ },
301
+ {
302
+ "epoch": 1.44,
303
+ "learning_rate": 1.717773580663479e-05,
304
+ "loss": 1.3689,
305
+ "step": 48
306
+ },
307
+ {
308
+ "epoch": 1.47,
309
+ "learning_rate": 1.703514748819948e-05,
310
+ "loss": 1.5311,
311
+ "step": 49
312
+ },
313
+ {
314
+ "epoch": 1.5,
315
+ "learning_rate": 1.688966919075687e-05,
316
+ "loss": 1.5253,
317
+ "step": 50
318
+ },
319
+ {
320
+ "epoch": 1.5,
321
+ "eval_loss": 1.5729879140853882,
322
+ "eval_runtime": 5.4053,
323
+ "eval_samples_per_second": 5.18,
324
+ "eval_steps_per_second": 0.74,
325
+ "step": 50
326
+ },
327
+ {
328
+ "epoch": 1.53,
329
+ "learning_rate": 1.6741360675559475e-05,
330
+ "loss": 1.3689,
331
+ "step": 51
332
+ },
333
+ {
334
+ "epoch": 1.56,
335
+ "learning_rate": 1.659028286648932e-05,
336
+ "loss": 1.4167,
337
+ "step": 52
338
+ },
339
+ {
340
+ "epoch": 1.59,
341
+ "learning_rate": 1.6436497825030886e-05,
342
+ "loss": 1.6581,
343
+ "step": 53
344
+ },
345
+ {
346
+ "epoch": 1.62,
347
+ "learning_rate": 1.6280068724776795e-05,
348
+ "loss": 1.5004,
349
+ "step": 54
350
+ },
351
+ {
352
+ "epoch": 1.65,
353
+ "learning_rate": 1.612105982547663e-05,
354
+ "loss": 1.4912,
355
+ "step": 55
356
+ },
357
+ {
358
+ "epoch": 1.68,
359
+ "learning_rate": 1.5959536446639572e-05,
360
+ "loss": 1.5128,
361
+ "step": 56
362
+ },
363
+ {
364
+ "epoch": 1.71,
365
+ "learning_rate": 1.57955649407017e-05,
366
+ "loss": 1.4908,
367
+ "step": 57
368
+ },
369
+ {
370
+ "epoch": 1.74,
371
+ "learning_rate": 1.562921266576898e-05,
372
+ "loss": 1.4826,
373
+ "step": 58
374
+ },
375
+ {
376
+ "epoch": 1.77,
377
+ "learning_rate": 1.5460547957947105e-05,
378
+ "loss": 1.423,
379
+ "step": 59
380
+ },
381
+ {
382
+ "epoch": 1.8,
383
+ "learning_rate": 1.5289640103269626e-05,
384
+ "loss": 1.5394,
385
+ "step": 60
386
+ },
387
+ {
388
+ "epoch": 1.83,
389
+ "learning_rate": 1.5116559309235825e-05,
390
+ "loss": 1.4102,
391
+ "step": 61
392
+ },
393
+ {
394
+ "epoch": 1.86,
395
+ "learning_rate": 1.4941376675970058e-05,
396
+ "loss": 1.3556,
397
+ "step": 62
398
+ },
399
+ {
400
+ "epoch": 1.89,
401
+ "learning_rate": 1.4764164167014451e-05,
402
+ "loss": 1.5444,
403
+ "step": 63
404
+ },
405
+ {
406
+ "epoch": 1.92,
407
+ "learning_rate": 1.4584994579766865e-05,
408
+ "loss": 1.4466,
409
+ "step": 64
410
+ },
411
+ {
412
+ "epoch": 1.95,
413
+ "learning_rate": 1.4403941515576344e-05,
414
+ "loss": 1.4467,
415
+ "step": 65
416
+ },
417
+ {
418
+ "epoch": 1.98,
419
+ "learning_rate": 1.422107934950832e-05,
420
+ "loss": 1.4268,
421
+ "step": 66
422
+ },
423
+ {
424
+ "epoch": 2.01,
425
+ "learning_rate": 1.4036483199791949e-05,
426
+ "loss": 1.4073,
427
+ "step": 67
428
+ },
429
+ {
430
+ "epoch": 2.04,
431
+ "learning_rate": 1.3850228896962178e-05,
432
+ "loss": 1.5186,
433
+ "step": 68
434
+ },
435
+ {
436
+ "epoch": 2.07,
437
+ "learning_rate": 1.366239295270923e-05,
438
+ "loss": 1.5014,
439
+ "step": 69
440
+ },
441
+ {
442
+ "epoch": 2.1,
443
+ "learning_rate": 1.3473052528448203e-05,
444
+ "loss": 1.3933,
445
+ "step": 70
446
+ },
447
+ {
448
+ "epoch": 2.13,
449
+ "learning_rate": 1.3282285403621864e-05,
450
+ "loss": 1.4067,
451
+ "step": 71
452
+ },
453
+ {
454
+ "epoch": 2.16,
455
+ "learning_rate": 1.3090169943749475e-05,
456
+ "loss": 1.5052,
457
+ "step": 72
458
+ },
459
+ {
460
+ "epoch": 2.19,
461
+ "learning_rate": 1.2896785068234925e-05,
462
+ "loss": 1.3016,
463
+ "step": 73
464
+ },
465
+ {
466
+ "epoch": 2.22,
467
+ "learning_rate": 1.2702210217947289e-05,
468
+ "loss": 1.3951,
469
+ "step": 74
470
+ },
471
+ {
472
+ "epoch": 2.25,
473
+ "learning_rate": 1.2506525322587207e-05,
474
+ "loss": 1.3363,
475
+ "step": 75
476
+ },
477
+ {
478
+ "epoch": 2.25,
479
+ "eval_loss": 1.5013550519943237,
480
+ "eval_runtime": 5.4016,
481
+ "eval_samples_per_second": 5.184,
482
+ "eval_steps_per_second": 0.741,
483
+ "step": 75
484
+ },
485
+ {
486
+ "epoch": 2.28,
487
+ "learning_rate": 1.2309810767852435e-05,
488
+ "loss": 1.3622,
489
+ "step": 76
490
+ },
491
+ {
492
+ "epoch": 2.31,
493
+ "learning_rate": 1.2112147362416076e-05,
494
+ "loss": 1.3339,
495
+ "step": 77
496
+ },
497
+ {
498
+ "epoch": 2.34,
499
+ "learning_rate": 1.1913616304731064e-05,
500
+ "loss": 1.3832,
501
+ "step": 78
502
+ },
503
+ {
504
+ "epoch": 2.37,
505
+ "learning_rate": 1.1714299149674538e-05,
506
+ "loss": 1.2172,
507
+ "step": 79
508
+ },
509
+ {
510
+ "epoch": 2.4,
511
+ "learning_rate": 1.1514277775045768e-05,
512
+ "loss": 1.2421,
513
+ "step": 80
514
+ },
515
+ {
516
+ "epoch": 2.43,
517
+ "learning_rate": 1.1313634347931466e-05,
518
+ "loss": 1.3649,
519
+ "step": 81
520
+ },
521
+ {
522
+ "epoch": 2.46,
523
+ "learning_rate": 1.1112451290952238e-05,
524
+ "loss": 1.5337,
525
+ "step": 82
526
+ },
527
+ {
528
+ "epoch": 2.49,
529
+ "learning_rate": 1.0910811248404064e-05,
530
+ "loss": 1.2464,
531
+ "step": 83
532
+ },
533
+ {
534
+ "epoch": 2.51,
535
+ "learning_rate": 1.070879705230873e-05,
536
+ "loss": 1.4806,
537
+ "step": 84
538
+ },
539
+ {
540
+ "epoch": 2.54,
541
+ "learning_rate": 1.0506491688387128e-05,
542
+ "loss": 1.3603,
543
+ "step": 85
544
+ },
545
+ {
546
+ "epoch": 2.57,
547
+ "learning_rate": 1.030397826196943e-05,
548
+ "loss": 1.2416,
549
+ "step": 86
550
+ },
551
+ {
552
+ "epoch": 2.6,
553
+ "learning_rate": 1.0101339963856112e-05,
554
+ "loss": 1.2974,
555
+ "step": 87
556
+ },
557
+ {
558
+ "epoch": 2.63,
559
+ "learning_rate": 9.898660036143893e-06,
560
+ "loss": 1.6356,
561
+ "step": 88
562
+ },
563
+ {
564
+ "epoch": 2.66,
565
+ "learning_rate": 9.696021738030575e-06,
566
+ "loss": 1.2952,
567
+ "step": 89
568
+ },
569
+ {
570
+ "epoch": 2.69,
571
+ "learning_rate": 9.493508311612874e-06,
572
+ "loss": 1.3857,
573
+ "step": 90
574
+ },
575
+ {
576
+ "epoch": 2.72,
577
+ "learning_rate": 9.291202947691272e-06,
578
+ "loss": 1.3712,
579
+ "step": 91
580
+ },
581
+ {
582
+ "epoch": 2.75,
583
+ "learning_rate": 9.089188751595937e-06,
584
+ "loss": 1.3713,
585
+ "step": 92
586
+ },
587
+ {
588
+ "epoch": 2.78,
589
+ "learning_rate": 8.887548709047765e-06,
590
+ "loss": 1.4597,
591
+ "step": 93
592
+ },
593
+ {
594
+ "epoch": 2.81,
595
+ "learning_rate": 8.686365652068536e-06,
596
+ "loss": 1.225,
597
+ "step": 94
598
+ },
599
+ {
600
+ "epoch": 2.84,
601
+ "learning_rate": 8.485722224954237e-06,
602
+ "loss": 1.3307,
603
+ "step": 95
604
+ },
605
+ {
606
+ "epoch": 2.87,
607
+ "learning_rate": 8.285700850325467e-06,
608
+ "loss": 1.3423,
609
+ "step": 96
610
+ },
611
+ {
612
+ "epoch": 2.9,
613
+ "learning_rate": 8.086383695268937e-06,
614
+ "loss": 1.352,
615
+ "step": 97
616
+ },
617
+ {
618
+ "epoch": 2.93,
619
+ "learning_rate": 7.887852637583927e-06,
620
+ "loss": 1.3908,
621
+ "step": 98
622
+ },
623
+ {
624
+ "epoch": 2.96,
625
+ "learning_rate": 7.690189232147566e-06,
626
+ "loss": 1.406,
627
+ "step": 99
628
+ },
629
+ {
630
+ "epoch": 2.99,
631
+ "learning_rate": 7.493474677412795e-06,
632
+ "loss": 1.4017,
633
+ "step": 100
634
+ },
635
+ {
636
+ "epoch": 2.99,
637
+ "eval_loss": 1.4689786434173584,
638
+ "eval_runtime": 5.4385,
639
+ "eval_samples_per_second": 5.148,
640
+ "eval_steps_per_second": 0.735,
641
+ "step": 100
642
+ }
643
+ ],
644
+ "logging_steps": 1,
645
+ "max_steps": 165,
646
+ "num_train_epochs": 5,
647
+ "save_steps": 50,
648
+ "total_flos": 1.1345883505360896e+17,
649
+ "trial_name": null,
650
+ "trial_params": null
651
+ }
checkpoint-100/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:218e6b2697498e27486ba1b06651dcc4e8143ab7c7f81e54381850c57f692daf
3
+ size 4920
checkpoint-150/README.md ADDED
@@ -0,0 +1,219 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: teknium/OpenHermes-2.5-Mistral-7B
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
+ - **Shared by [optional]:** [More Information Needed]
22
+ - **Model type:** [More Information Needed]
23
+ - **Language(s) (NLP):** [More Information Needed]
24
+ - **License:** [More Information Needed]
25
+ - **Finetuned from model [optional]:** [More Information Needed]
26
+
27
+ ### Model Sources [optional]
28
+
29
+ <!-- Provide the basic links for the model. -->
30
+
31
+ - **Repository:** [More Information Needed]
32
+ - **Paper [optional]:** [More Information Needed]
33
+ - **Demo [optional]:** [More Information Needed]
34
+
35
+ ## Uses
36
+
37
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
38
+
39
+ ### Direct Use
40
+
41
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
42
+
43
+ [More Information Needed]
44
+
45
+ ### Downstream Use [optional]
46
+
47
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
48
+
49
+ [More Information Needed]
50
+
51
+ ### Out-of-Scope Use
52
+
53
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
54
+
55
+ [More Information Needed]
56
+
57
+ ## Bias, Risks, and Limitations
58
+
59
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
60
+
61
+ [More Information Needed]
62
+
63
+ ### Recommendations
64
+
65
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
66
+
67
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
68
+
69
+ ## How to Get Started with the Model
70
+
71
+ Use the code below to get started with the model.
72
+
73
+ [More Information Needed]
74
+
75
+ ## Training Details
76
+
77
+ ### Training Data
78
+
79
+ <!-- This should link to a Data 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. -->
80
+
81
+ [More Information Needed]
82
+
83
+ ### Training Procedure
84
+
85
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
86
+
87
+ #### Preprocessing [optional]
88
+
89
+ [More Information Needed]
90
+
91
+
92
+ #### Training Hyperparameters
93
+
94
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
95
+
96
+ #### Speeds, Sizes, Times [optional]
97
+
98
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
99
+
100
+ [More Information Needed]
101
+
102
+ ## Evaluation
103
+
104
+ <!-- This section describes the evaluation protocols and provides the results. -->
105
+
106
+ ### Testing Data, Factors & Metrics
107
+
108
+ #### Testing Data
109
+
110
+ <!-- This should link to a Data Card if possible. -->
111
+
112
+ [More Information Needed]
113
+
114
+ #### Factors
115
+
116
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
117
+
118
+ [More Information Needed]
119
+
120
+ #### Metrics
121
+
122
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
123
+
124
+ [More Information Needed]
125
+
126
+ ### Results
127
+
128
+ [More Information Needed]
129
+
130
+ #### Summary
131
+
132
+
133
+
134
+ ## Model Examination [optional]
135
+
136
+ <!-- Relevant interpretability work for the model goes here -->
137
+
138
+ [More Information Needed]
139
+
140
+ ## Environmental Impact
141
+
142
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
143
+
144
+ 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).
145
+
146
+ - **Hardware Type:** [More Information Needed]
147
+ - **Hours used:** [More Information Needed]
148
+ - **Cloud Provider:** [More Information Needed]
149
+ - **Compute Region:** [More Information Needed]
150
+ - **Carbon Emitted:** [More Information Needed]
151
+
152
+ ## Technical Specifications [optional]
153
+
154
+ ### Model Architecture and Objective
155
+
156
+ [More Information Needed]
157
+
158
+ ### Compute Infrastructure
159
+
160
+ [More Information Needed]
161
+
162
+ #### Hardware
163
+
164
+ [More Information Needed]
165
+
166
+ #### Software
167
+
168
+ [More Information Needed]
169
+
170
+ ## Citation [optional]
171
+
172
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
173
+
174
+ **BibTeX:**
175
+
176
+ [More Information Needed]
177
+
178
+ **APA:**
179
+
180
+ [More Information Needed]
181
+
182
+ ## Glossary [optional]
183
+
184
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
185
+
186
+ [More Information Needed]
187
+
188
+ ## More Information [optional]
189
+
190
+ [More Information Needed]
191
+
192
+ ## Model Card Authors [optional]
193
+
194
+ [More Information Needed]
195
+
196
+ ## Model Card Contact
197
+
198
+ [More Information Needed]
199
+
200
+
201
+ ## Training procedure
202
+
203
+
204
+ The following `bitsandbytes` quantization config was used during training:
205
+ - quant_method: bitsandbytes
206
+ - load_in_8bit: True
207
+ - load_in_4bit: False
208
+ - llm_int8_threshold: 6.0
209
+ - llm_int8_skip_modules: None
210
+ - llm_int8_enable_fp32_cpu_offload: False
211
+ - llm_int8_has_fp16_weight: False
212
+ - bnb_4bit_quant_type: fp4
213
+ - bnb_4bit_use_double_quant: False
214
+ - bnb_4bit_compute_dtype: float32
215
+
216
+ ### Framework versions
217
+
218
+
219
+ - PEFT 0.6.0
checkpoint-150/adapter_config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "teknium/OpenHermes-2.5-Mistral-7B",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "lora_alpha": 32,
12
+ "lora_dropout": 0.05,
13
+ "modules_to_save": null,
14
+ "peft_type": "LORA",
15
+ "r": 128,
16
+ "rank_pattern": {},
17
+ "revision": null,
18
+ "target_modules": [
19
+ "q_proj",
20
+ "k_proj",
21
+ "up_proj",
22
+ "o_proj",
23
+ "gate_proj",
24
+ "down_proj",
25
+ "v_proj"
26
+ ],
27
+ "task_type": "CAUSAL_LM"
28
+ }
checkpoint-150/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cc4f98f72e6ab33b93346265f31f32adcc362ffd925e5c929c2561d2fb3dd34
3
+ size 1342339274
checkpoint-150/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4be8ffc6a9fea3b3284aed54a6b2d8a63e87d3db1ad09cac5db71797b5aab76
3
+ size 2684631802
checkpoint-150/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a527cb0c734c3ed4b752b8c8297514a163a179a2ae48f49423d896146d405ad9
3
+ size 14244
checkpoint-150/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8cc87633ee72247fca3b2919660e92d8e30dcf0e412f83ccd1f650d1d2f8e39c
3
+ size 1064
checkpoint-150/trainer_state.json ADDED
@@ -0,0 +1,967 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.4545527696609497,
3
+ "best_model_checkpoint": "./lora-outB/checkpoint-150",
4
+ "epoch": 4.491017964071856,
5
+ "eval_steps": 25,
6
+ "global_step": 150,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.03,
13
+ "learning_rate": 2.0000000000000003e-06,
14
+ "loss": 1.866,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.06,
19
+ "learning_rate": 4.000000000000001e-06,
20
+ "loss": 1.7383,
21
+ "step": 2
22
+ },
23
+ {
24
+ "epoch": 0.09,
25
+ "learning_rate": 6e-06,
26
+ "loss": 1.8306,
27
+ "step": 3
28
+ },
29
+ {
30
+ "epoch": 0.12,
31
+ "learning_rate": 8.000000000000001e-06,
32
+ "loss": 1.9213,
33
+ "step": 4
34
+ },
35
+ {
36
+ "epoch": 0.15,
37
+ "learning_rate": 1e-05,
38
+ "loss": 1.9524,
39
+ "step": 5
40
+ },
41
+ {
42
+ "epoch": 0.18,
43
+ "learning_rate": 1.2e-05,
44
+ "loss": 1.7308,
45
+ "step": 6
46
+ },
47
+ {
48
+ "epoch": 0.21,
49
+ "learning_rate": 1.4e-05,
50
+ "loss": 1.7334,
51
+ "step": 7
52
+ },
53
+ {
54
+ "epoch": 0.24,
55
+ "learning_rate": 1.6000000000000003e-05,
56
+ "loss": 1.6749,
57
+ "step": 8
58
+ },
59
+ {
60
+ "epoch": 0.27,
61
+ "learning_rate": 1.8e-05,
62
+ "loss": 1.805,
63
+ "step": 9
64
+ },
65
+ {
66
+ "epoch": 0.3,
67
+ "learning_rate": 2e-05,
68
+ "loss": 1.778,
69
+ "step": 10
70
+ },
71
+ {
72
+ "epoch": 0.33,
73
+ "learning_rate": 1.9997946042345128e-05,
74
+ "loss": 1.7804,
75
+ "step": 11
76
+ },
77
+ {
78
+ "epoch": 0.36,
79
+ "learning_rate": 1.9991785013128922e-05,
80
+ "loss": 1.8191,
81
+ "step": 12
82
+ },
83
+ {
84
+ "epoch": 0.39,
85
+ "learning_rate": 1.998151944325001e-05,
86
+ "loss": 1.7089,
87
+ "step": 13
88
+ },
89
+ {
90
+ "epoch": 0.42,
91
+ "learning_rate": 1.996715354971755e-05,
92
+ "loss": 1.7131,
93
+ "step": 14
94
+ },
95
+ {
96
+ "epoch": 0.45,
97
+ "learning_rate": 1.994869323391895e-05,
98
+ "loss": 1.917,
99
+ "step": 15
100
+ },
101
+ {
102
+ "epoch": 0.48,
103
+ "learning_rate": 1.9926146079195597e-05,
104
+ "loss": 1.6701,
105
+ "step": 16
106
+ },
107
+ {
108
+ "epoch": 0.51,
109
+ "learning_rate": 1.989952134772769e-05,
110
+ "loss": 1.7119,
111
+ "step": 17
112
+ },
113
+ {
114
+ "epoch": 0.54,
115
+ "learning_rate": 1.9868829976729444e-05,
116
+ "loss": 1.7037,
117
+ "step": 18
118
+ },
119
+ {
120
+ "epoch": 0.57,
121
+ "learning_rate": 1.983408457395613e-05,
122
+ "loss": 1.7314,
123
+ "step": 19
124
+ },
125
+ {
126
+ "epoch": 0.6,
127
+ "learning_rate": 1.9795299412524948e-05,
128
+ "loss": 1.6771,
129
+ "step": 20
130
+ },
131
+ {
132
+ "epoch": 0.63,
133
+ "learning_rate": 1.975249042505174e-05,
134
+ "loss": 1.6734,
135
+ "step": 21
136
+ },
137
+ {
138
+ "epoch": 0.66,
139
+ "learning_rate": 1.970567519710602e-05,
140
+ "loss": 1.689,
141
+ "step": 22
142
+ },
143
+ {
144
+ "epoch": 0.69,
145
+ "learning_rate": 1.9654872959986936e-05,
146
+ "loss": 1.7452,
147
+ "step": 23
148
+ },
149
+ {
150
+ "epoch": 0.72,
151
+ "learning_rate": 1.960010458282326e-05,
152
+ "loss": 1.7126,
153
+ "step": 24
154
+ },
155
+ {
156
+ "epoch": 0.75,
157
+ "learning_rate": 1.954139256400049e-05,
158
+ "loss": 1.5629,
159
+ "step": 25
160
+ },
161
+ {
162
+ "epoch": 0.75,
163
+ "eval_loss": 1.6511253118515015,
164
+ "eval_runtime": 5.4427,
165
+ "eval_samples_per_second": 5.145,
166
+ "eval_steps_per_second": 0.735,
167
+ "step": 25
168
+ },
169
+ {
170
+ "epoch": 0.78,
171
+ "learning_rate": 1.947876102191873e-05,
172
+ "loss": 1.6948,
173
+ "step": 26
174
+ },
175
+ {
176
+ "epoch": 0.81,
177
+ "learning_rate": 1.9412235685085034e-05,
178
+ "loss": 1.5969,
179
+ "step": 27
180
+ },
181
+ {
182
+ "epoch": 0.84,
183
+ "learning_rate": 1.9341843881544372e-05,
184
+ "loss": 1.5367,
185
+ "step": 28
186
+ },
187
+ {
188
+ "epoch": 0.87,
189
+ "learning_rate": 1.926761452765349e-05,
190
+ "loss": 1.463,
191
+ "step": 29
192
+ },
193
+ {
194
+ "epoch": 0.9,
195
+ "learning_rate": 1.918957811620231e-05,
196
+ "loss": 1.4575,
197
+ "step": 30
198
+ },
199
+ {
200
+ "epoch": 0.93,
201
+ "learning_rate": 1.9107766703887764e-05,
202
+ "loss": 1.5928,
203
+ "step": 31
204
+ },
205
+ {
206
+ "epoch": 0.96,
207
+ "learning_rate": 1.9022213898145176e-05,
208
+ "loss": 1.5604,
209
+ "step": 32
210
+ },
211
+ {
212
+ "epoch": 0.99,
213
+ "learning_rate": 1.893295484334259e-05,
214
+ "loss": 1.6508,
215
+ "step": 33
216
+ },
217
+ {
218
+ "epoch": 1.02,
219
+ "learning_rate": 1.8840026206343786e-05,
220
+ "loss": 1.4583,
221
+ "step": 34
222
+ },
223
+ {
224
+ "epoch": 1.05,
225
+ "learning_rate": 1.8743466161445823e-05,
226
+ "loss": 1.7124,
227
+ "step": 35
228
+ },
229
+ {
230
+ "epoch": 1.08,
231
+ "learning_rate": 1.8643314374697377e-05,
232
+ "loss": 1.462,
233
+ "step": 36
234
+ },
235
+ {
236
+ "epoch": 1.11,
237
+ "learning_rate": 1.853961198760426e-05,
238
+ "loss": 1.6664,
239
+ "step": 37
240
+ },
241
+ {
242
+ "epoch": 1.14,
243
+ "learning_rate": 1.8432401600228823e-05,
244
+ "loss": 1.6264,
245
+ "step": 38
246
+ },
247
+ {
248
+ "epoch": 1.17,
249
+ "learning_rate": 1.832172725369024e-05,
250
+ "loss": 1.6704,
251
+ "step": 39
252
+ },
253
+ {
254
+ "epoch": 1.2,
255
+ "learning_rate": 1.8207634412072765e-05,
256
+ "loss": 1.5221,
257
+ "step": 40
258
+ },
259
+ {
260
+ "epoch": 1.23,
261
+ "learning_rate": 1.8090169943749477e-05,
262
+ "loss": 1.5411,
263
+ "step": 41
264
+ },
265
+ {
266
+ "epoch": 1.26,
267
+ "learning_rate": 1.7969382102129153e-05,
268
+ "loss": 1.4493,
269
+ "step": 42
270
+ },
271
+ {
272
+ "epoch": 1.29,
273
+ "learning_rate": 1.7845320505834176e-05,
274
+ "loss": 1.4783,
275
+ "step": 43
276
+ },
277
+ {
278
+ "epoch": 1.32,
279
+ "learning_rate": 1.771803611831762e-05,
280
+ "loss": 1.5882,
281
+ "step": 44
282
+ },
283
+ {
284
+ "epoch": 1.35,
285
+ "learning_rate": 1.758758122692791e-05,
286
+ "loss": 1.5848,
287
+ "step": 45
288
+ },
289
+ {
290
+ "epoch": 1.38,
291
+ "learning_rate": 1.74540094214296e-05,
292
+ "loss": 1.4439,
293
+ "step": 46
294
+ },
295
+ {
296
+ "epoch": 1.41,
297
+ "learning_rate": 1.7317375571989158e-05,
298
+ "loss": 1.5398,
299
+ "step": 47
300
+ },
301
+ {
302
+ "epoch": 1.44,
303
+ "learning_rate": 1.717773580663479e-05,
304
+ "loss": 1.3689,
305
+ "step": 48
306
+ },
307
+ {
308
+ "epoch": 1.47,
309
+ "learning_rate": 1.703514748819948e-05,
310
+ "loss": 1.5311,
311
+ "step": 49
312
+ },
313
+ {
314
+ "epoch": 1.5,
315
+ "learning_rate": 1.688966919075687e-05,
316
+ "loss": 1.5253,
317
+ "step": 50
318
+ },
319
+ {
320
+ "epoch": 1.5,
321
+ "eval_loss": 1.5729879140853882,
322
+ "eval_runtime": 5.4053,
323
+ "eval_samples_per_second": 5.18,
324
+ "eval_steps_per_second": 0.74,
325
+ "step": 50
326
+ },
327
+ {
328
+ "epoch": 1.53,
329
+ "learning_rate": 1.6741360675559475e-05,
330
+ "loss": 1.3689,
331
+ "step": 51
332
+ },
333
+ {
334
+ "epoch": 1.56,
335
+ "learning_rate": 1.659028286648932e-05,
336
+ "loss": 1.4167,
337
+ "step": 52
338
+ },
339
+ {
340
+ "epoch": 1.59,
341
+ "learning_rate": 1.6436497825030886e-05,
342
+ "loss": 1.6581,
343
+ "step": 53
344
+ },
345
+ {
346
+ "epoch": 1.62,
347
+ "learning_rate": 1.6280068724776795e-05,
348
+ "loss": 1.5004,
349
+ "step": 54
350
+ },
351
+ {
352
+ "epoch": 1.65,
353
+ "learning_rate": 1.612105982547663e-05,
354
+ "loss": 1.4912,
355
+ "step": 55
356
+ },
357
+ {
358
+ "epoch": 1.68,
359
+ "learning_rate": 1.5959536446639572e-05,
360
+ "loss": 1.5128,
361
+ "step": 56
362
+ },
363
+ {
364
+ "epoch": 1.71,
365
+ "learning_rate": 1.57955649407017e-05,
366
+ "loss": 1.4908,
367
+ "step": 57
368
+ },
369
+ {
370
+ "epoch": 1.74,
371
+ "learning_rate": 1.562921266576898e-05,
372
+ "loss": 1.4826,
373
+ "step": 58
374
+ },
375
+ {
376
+ "epoch": 1.77,
377
+ "learning_rate": 1.5460547957947105e-05,
378
+ "loss": 1.423,
379
+ "step": 59
380
+ },
381
+ {
382
+ "epoch": 1.8,
383
+ "learning_rate": 1.5289640103269626e-05,
384
+ "loss": 1.5394,
385
+ "step": 60
386
+ },
387
+ {
388
+ "epoch": 1.83,
389
+ "learning_rate": 1.5116559309235825e-05,
390
+ "loss": 1.4102,
391
+ "step": 61
392
+ },
393
+ {
394
+ "epoch": 1.86,
395
+ "learning_rate": 1.4941376675970058e-05,
396
+ "loss": 1.3556,
397
+ "step": 62
398
+ },
399
+ {
400
+ "epoch": 1.89,
401
+ "learning_rate": 1.4764164167014451e-05,
402
+ "loss": 1.5444,
403
+ "step": 63
404
+ },
405
+ {
406
+ "epoch": 1.92,
407
+ "learning_rate": 1.4584994579766865e-05,
408
+ "loss": 1.4466,
409
+ "step": 64
410
+ },
411
+ {
412
+ "epoch": 1.95,
413
+ "learning_rate": 1.4403941515576344e-05,
414
+ "loss": 1.4467,
415
+ "step": 65
416
+ },
417
+ {
418
+ "epoch": 1.98,
419
+ "learning_rate": 1.422107934950832e-05,
420
+ "loss": 1.4268,
421
+ "step": 66
422
+ },
423
+ {
424
+ "epoch": 2.01,
425
+ "learning_rate": 1.4036483199791949e-05,
426
+ "loss": 1.4073,
427
+ "step": 67
428
+ },
429
+ {
430
+ "epoch": 2.04,
431
+ "learning_rate": 1.3850228896962178e-05,
432
+ "loss": 1.5186,
433
+ "step": 68
434
+ },
435
+ {
436
+ "epoch": 2.07,
437
+ "learning_rate": 1.366239295270923e-05,
438
+ "loss": 1.5014,
439
+ "step": 69
440
+ },
441
+ {
442
+ "epoch": 2.1,
443
+ "learning_rate": 1.3473052528448203e-05,
444
+ "loss": 1.3933,
445
+ "step": 70
446
+ },
447
+ {
448
+ "epoch": 2.13,
449
+ "learning_rate": 1.3282285403621864e-05,
450
+ "loss": 1.4067,
451
+ "step": 71
452
+ },
453
+ {
454
+ "epoch": 2.16,
455
+ "learning_rate": 1.3090169943749475e-05,
456
+ "loss": 1.5052,
457
+ "step": 72
458
+ },
459
+ {
460
+ "epoch": 2.19,
461
+ "learning_rate": 1.2896785068234925e-05,
462
+ "loss": 1.3016,
463
+ "step": 73
464
+ },
465
+ {
466
+ "epoch": 2.22,
467
+ "learning_rate": 1.2702210217947289e-05,
468
+ "loss": 1.3951,
469
+ "step": 74
470
+ },
471
+ {
472
+ "epoch": 2.25,
473
+ "learning_rate": 1.2506525322587207e-05,
474
+ "loss": 1.3363,
475
+ "step": 75
476
+ },
477
+ {
478
+ "epoch": 2.25,
479
+ "eval_loss": 1.5013550519943237,
480
+ "eval_runtime": 5.4016,
481
+ "eval_samples_per_second": 5.184,
482
+ "eval_steps_per_second": 0.741,
483
+ "step": 75
484
+ },
485
+ {
486
+ "epoch": 2.28,
487
+ "learning_rate": 1.2309810767852435e-05,
488
+ "loss": 1.3622,
489
+ "step": 76
490
+ },
491
+ {
492
+ "epoch": 2.31,
493
+ "learning_rate": 1.2112147362416076e-05,
494
+ "loss": 1.3339,
495
+ "step": 77
496
+ },
497
+ {
498
+ "epoch": 2.34,
499
+ "learning_rate": 1.1913616304731064e-05,
500
+ "loss": 1.3832,
501
+ "step": 78
502
+ },
503
+ {
504
+ "epoch": 2.37,
505
+ "learning_rate": 1.1714299149674538e-05,
506
+ "loss": 1.2172,
507
+ "step": 79
508
+ },
509
+ {
510
+ "epoch": 2.4,
511
+ "learning_rate": 1.1514277775045768e-05,
512
+ "loss": 1.2421,
513
+ "step": 80
514
+ },
515
+ {
516
+ "epoch": 2.43,
517
+ "learning_rate": 1.1313634347931466e-05,
518
+ "loss": 1.3649,
519
+ "step": 81
520
+ },
521
+ {
522
+ "epoch": 2.46,
523
+ "learning_rate": 1.1112451290952238e-05,
524
+ "loss": 1.5337,
525
+ "step": 82
526
+ },
527
+ {
528
+ "epoch": 2.49,
529
+ "learning_rate": 1.0910811248404064e-05,
530
+ "loss": 1.2464,
531
+ "step": 83
532
+ },
533
+ {
534
+ "epoch": 2.51,
535
+ "learning_rate": 1.070879705230873e-05,
536
+ "loss": 1.4806,
537
+ "step": 84
538
+ },
539
+ {
540
+ "epoch": 2.54,
541
+ "learning_rate": 1.0506491688387128e-05,
542
+ "loss": 1.3603,
543
+ "step": 85
544
+ },
545
+ {
546
+ "epoch": 2.57,
547
+ "learning_rate": 1.030397826196943e-05,
548
+ "loss": 1.2416,
549
+ "step": 86
550
+ },
551
+ {
552
+ "epoch": 2.6,
553
+ "learning_rate": 1.0101339963856112e-05,
554
+ "loss": 1.2974,
555
+ "step": 87
556
+ },
557
+ {
558
+ "epoch": 2.63,
559
+ "learning_rate": 9.898660036143893e-06,
560
+ "loss": 1.6356,
561
+ "step": 88
562
+ },
563
+ {
564
+ "epoch": 2.66,
565
+ "learning_rate": 9.696021738030575e-06,
566
+ "loss": 1.2952,
567
+ "step": 89
568
+ },
569
+ {
570
+ "epoch": 2.69,
571
+ "learning_rate": 9.493508311612874e-06,
572
+ "loss": 1.3857,
573
+ "step": 90
574
+ },
575
+ {
576
+ "epoch": 2.72,
577
+ "learning_rate": 9.291202947691272e-06,
578
+ "loss": 1.3712,
579
+ "step": 91
580
+ },
581
+ {
582
+ "epoch": 2.75,
583
+ "learning_rate": 9.089188751595937e-06,
584
+ "loss": 1.3713,
585
+ "step": 92
586
+ },
587
+ {
588
+ "epoch": 2.78,
589
+ "learning_rate": 8.887548709047765e-06,
590
+ "loss": 1.4597,
591
+ "step": 93
592
+ },
593
+ {
594
+ "epoch": 2.81,
595
+ "learning_rate": 8.686365652068536e-06,
596
+ "loss": 1.225,
597
+ "step": 94
598
+ },
599
+ {
600
+ "epoch": 2.84,
601
+ "learning_rate": 8.485722224954237e-06,
602
+ "loss": 1.3307,
603
+ "step": 95
604
+ },
605
+ {
606
+ "epoch": 2.87,
607
+ "learning_rate": 8.285700850325467e-06,
608
+ "loss": 1.3423,
609
+ "step": 96
610
+ },
611
+ {
612
+ "epoch": 2.9,
613
+ "learning_rate": 8.086383695268937e-06,
614
+ "loss": 1.352,
615
+ "step": 97
616
+ },
617
+ {
618
+ "epoch": 2.93,
619
+ "learning_rate": 7.887852637583927e-06,
620
+ "loss": 1.3908,
621
+ "step": 98
622
+ },
623
+ {
624
+ "epoch": 2.96,
625
+ "learning_rate": 7.690189232147566e-06,
626
+ "loss": 1.406,
627
+ "step": 99
628
+ },
629
+ {
630
+ "epoch": 2.99,
631
+ "learning_rate": 7.493474677412795e-06,
632
+ "loss": 1.4017,
633
+ "step": 100
634
+ },
635
+ {
636
+ "epoch": 2.99,
637
+ "eval_loss": 1.4689786434173584,
638
+ "eval_runtime": 5.4385,
639
+ "eval_samples_per_second": 5.148,
640
+ "eval_steps_per_second": 0.735,
641
+ "step": 100
642
+ },
643
+ {
644
+ "epoch": 3.02,
645
+ "learning_rate": 7.297789782052716e-06,
646
+ "loss": 1.2587,
647
+ "step": 101
648
+ },
649
+ {
650
+ "epoch": 3.05,
651
+ "learning_rate": 7.10321493176508e-06,
652
+ "loss": 1.2309,
653
+ "step": 102
654
+ },
655
+ {
656
+ "epoch": 3.08,
657
+ "learning_rate": 6.909830056250527e-06,
658
+ "loss": 1.3232,
659
+ "step": 103
660
+ },
661
+ {
662
+ "epoch": 3.11,
663
+ "learning_rate": 6.717714596378138e-06,
664
+ "loss": 1.2715,
665
+ "step": 104
666
+ },
667
+ {
668
+ "epoch": 3.14,
669
+ "learning_rate": 6.526947471551799e-06,
670
+ "loss": 1.3015,
671
+ "step": 105
672
+ },
673
+ {
674
+ "epoch": 3.17,
675
+ "learning_rate": 6.337607047290774e-06,
676
+ "loss": 1.3752,
677
+ "step": 106
678
+ },
679
+ {
680
+ "epoch": 3.2,
681
+ "learning_rate": 6.149771103037821e-06,
682
+ "loss": 1.3156,
683
+ "step": 107
684
+ },
685
+ {
686
+ "epoch": 3.23,
687
+ "learning_rate": 5.963516800208056e-06,
688
+ "loss": 1.3419,
689
+ "step": 108
690
+ },
691
+ {
692
+ "epoch": 3.26,
693
+ "learning_rate": 5.7789206504916815e-06,
694
+ "loss": 1.4729,
695
+ "step": 109
696
+ },
697
+ {
698
+ "epoch": 3.29,
699
+ "learning_rate": 5.5960584844236565e-06,
700
+ "loss": 1.3619,
701
+ "step": 110
702
+ },
703
+ {
704
+ "epoch": 3.32,
705
+ "learning_rate": 5.415005420233141e-06,
706
+ "loss": 1.4708,
707
+ "step": 111
708
+ },
709
+ {
710
+ "epoch": 3.35,
711
+ "learning_rate": 5.235835832985552e-06,
712
+ "loss": 1.4684,
713
+ "step": 112
714
+ },
715
+ {
716
+ "epoch": 3.38,
717
+ "learning_rate": 5.058623324029944e-06,
718
+ "loss": 1.2379,
719
+ "step": 113
720
+ },
721
+ {
722
+ "epoch": 3.41,
723
+ "learning_rate": 4.8834406907641784e-06,
724
+ "loss": 1.2921,
725
+ "step": 114
726
+ },
727
+ {
728
+ "epoch": 3.44,
729
+ "learning_rate": 4.710359896730379e-06,
730
+ "loss": 1.3846,
731
+ "step": 115
732
+ },
733
+ {
734
+ "epoch": 3.47,
735
+ "learning_rate": 4.539452042052901e-06,
736
+ "loss": 1.218,
737
+ "step": 116
738
+ },
739
+ {
740
+ "epoch": 3.5,
741
+ "learning_rate": 4.370787334231026e-06,
742
+ "loss": 1.2349,
743
+ "step": 117
744
+ },
745
+ {
746
+ "epoch": 3.53,
747
+ "learning_rate": 4.204435059298303e-06,
748
+ "loss": 1.1808,
749
+ "step": 118
750
+ },
751
+ {
752
+ "epoch": 3.56,
753
+ "learning_rate": 4.040463553360431e-06,
754
+ "loss": 1.2824,
755
+ "step": 119
756
+ },
757
+ {
758
+ "epoch": 3.59,
759
+ "learning_rate": 3.878940174523371e-06,
760
+ "loss": 1.4456,
761
+ "step": 120
762
+ },
763
+ {
764
+ "epoch": 3.62,
765
+ "learning_rate": 3.7199312752232053e-06,
766
+ "loss": 1.3098,
767
+ "step": 121
768
+ },
769
+ {
770
+ "epoch": 3.65,
771
+ "learning_rate": 3.563502174969117e-06,
772
+ "loss": 1.2517,
773
+ "step": 122
774
+ },
775
+ {
776
+ "epoch": 3.68,
777
+ "learning_rate": 3.409717133510683e-06,
778
+ "loss": 1.3281,
779
+ "step": 123
780
+ },
781
+ {
782
+ "epoch": 3.71,
783
+ "learning_rate": 3.258639324440527e-06,
784
+ "loss": 1.3068,
785
+ "step": 124
786
+ },
787
+ {
788
+ "epoch": 3.74,
789
+ "learning_rate": 3.110330809243134e-06,
790
+ "loss": 1.2677,
791
+ "step": 125
792
+ },
793
+ {
794
+ "epoch": 3.74,
795
+ "eval_loss": 1.4592927694320679,
796
+ "eval_runtime": 5.3759,
797
+ "eval_samples_per_second": 5.208,
798
+ "eval_steps_per_second": 0.744,
799
+ "step": 125
800
+ },
801
+ {
802
+ "epoch": 3.77,
803
+ "learning_rate": 2.964852511800519e-06,
804
+ "loss": 1.2642,
805
+ "step": 126
806
+ },
807
+ {
808
+ "epoch": 3.8,
809
+ "learning_rate": 2.822264193365212e-06,
810
+ "loss": 1.2629,
811
+ "step": 127
812
+ },
813
+ {
814
+ "epoch": 3.83,
815
+ "learning_rate": 2.6826244280108438e-06,
816
+ "loss": 1.4554,
817
+ "step": 128
818
+ },
819
+ {
820
+ "epoch": 3.86,
821
+ "learning_rate": 2.545990578570404e-06,
822
+ "loss": 1.4209,
823
+ "step": 129
824
+ },
825
+ {
826
+ "epoch": 3.89,
827
+ "learning_rate": 2.4124187730720916e-06,
828
+ "loss": 1.3152,
829
+ "step": 130
830
+ },
831
+ {
832
+ "epoch": 3.92,
833
+ "learning_rate": 2.2819638816823796e-06,
834
+ "loss": 1.2729,
835
+ "step": 131
836
+ },
837
+ {
838
+ "epoch": 3.95,
839
+ "learning_rate": 2.154679494165829e-06,
840
+ "loss": 1.3608,
841
+ "step": 132
842
+ },
843
+ {
844
+ "epoch": 3.98,
845
+ "learning_rate": 2.030617897870851e-06,
846
+ "loss": 1.3871,
847
+ "step": 133
848
+ },
849
+ {
850
+ "epoch": 4.01,
851
+ "learning_rate": 1.9098300562505266e-06,
852
+ "loss": 1.3255,
853
+ "step": 134
854
+ },
855
+ {
856
+ "epoch": 4.04,
857
+ "learning_rate": 1.7923655879272395e-06,
858
+ "loss": 1.3443,
859
+ "step": 135
860
+ },
861
+ {
862
+ "epoch": 4.07,
863
+ "learning_rate": 1.6782727463097626e-06,
864
+ "loss": 1.41,
865
+ "step": 136
866
+ },
867
+ {
868
+ "epoch": 4.1,
869
+ "learning_rate": 1.5675983997711797e-06,
870
+ "loss": 1.2783,
871
+ "step": 137
872
+ },
873
+ {
874
+ "epoch": 4.13,
875
+ "learning_rate": 1.4603880123957448e-06,
876
+ "loss": 1.169,
877
+ "step": 138
878
+ },
879
+ {
880
+ "epoch": 4.16,
881
+ "learning_rate": 1.356685625302625e-06,
882
+ "loss": 1.1928,
883
+ "step": 139
884
+ },
885
+ {
886
+ "epoch": 4.19,
887
+ "learning_rate": 1.2565338385541792e-06,
888
+ "loss": 1.4349,
889
+ "step": 140
890
+ },
891
+ {
892
+ "epoch": 4.22,
893
+ "learning_rate": 1.159973793656215e-06,
894
+ "loss": 1.4173,
895
+ "step": 141
896
+ },
897
+ {
898
+ "epoch": 4.25,
899
+ "learning_rate": 1.0670451566574102e-06,
900
+ "loss": 1.3533,
901
+ "step": 142
902
+ },
903
+ {
904
+ "epoch": 4.28,
905
+ "learning_rate": 9.77786101854825e-07,
906
+ "loss": 1.188,
907
+ "step": 143
908
+ },
909
+ {
910
+ "epoch": 4.31,
911
+ "learning_rate": 8.92233296112236e-07,
912
+ "loss": 1.2933,
913
+ "step": 144
914
+ },
915
+ {
916
+ "epoch": 4.34,
917
+ "learning_rate": 8.10421883797694e-07,
918
+ "loss": 1.2848,
919
+ "step": 145
920
+ },
921
+ {
922
+ "epoch": 4.37,
923
+ "learning_rate": 7.32385472346514e-07,
924
+ "loss": 1.3775,
925
+ "step": 146
926
+ },
927
+ {
928
+ "epoch": 4.4,
929
+ "learning_rate": 6.581561184556296e-07,
930
+ "loss": 1.2679,
931
+ "step": 147
932
+ },
933
+ {
934
+ "epoch": 4.43,
935
+ "learning_rate": 5.877643149149669e-07,
936
+ "loss": 1.2643,
937
+ "step": 148
938
+ },
939
+ {
940
+ "epoch": 4.46,
941
+ "learning_rate": 5.212389780812733e-07,
942
+ "loss": 1.3166,
943
+ "step": 149
944
+ },
945
+ {
946
+ "epoch": 4.49,
947
+ "learning_rate": 4.5860743599951186e-07,
948
+ "loss": 1.351,
949
+ "step": 150
950
+ },
951
+ {
952
+ "epoch": 4.49,
953
+ "eval_loss": 1.4545527696609497,
954
+ "eval_runtime": 5.4009,
955
+ "eval_samples_per_second": 5.184,
956
+ "eval_steps_per_second": 0.741,
957
+ "step": 150
958
+ }
959
+ ],
960
+ "logging_steps": 1,
961
+ "max_steps": 165,
962
+ "num_train_epochs": 5,
963
+ "save_steps": 50,
964
+ "total_flos": 1.7018825258041344e+17,
965
+ "trial_name": null,
966
+ "trial_params": null
967
+ }
checkpoint-150/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:218e6b2697498e27486ba1b06651dcc4e8143ab7c7f81e54381850c57f692daf
3
+ size 4920
checkpoint-50/README.md ADDED
@@ -0,0 +1,219 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: teknium/OpenHermes-2.5-Mistral-7B
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
+ - **Shared by [optional]:** [More Information Needed]
22
+ - **Model type:** [More Information Needed]
23
+ - **Language(s) (NLP):** [More Information Needed]
24
+ - **License:** [More Information Needed]
25
+ - **Finetuned from model [optional]:** [More Information Needed]
26
+
27
+ ### Model Sources [optional]
28
+
29
+ <!-- Provide the basic links for the model. -->
30
+
31
+ - **Repository:** [More Information Needed]
32
+ - **Paper [optional]:** [More Information Needed]
33
+ - **Demo [optional]:** [More Information Needed]
34
+
35
+ ## Uses
36
+
37
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
38
+
39
+ ### Direct Use
40
+
41
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
42
+
43
+ [More Information Needed]
44
+
45
+ ### Downstream Use [optional]
46
+
47
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
48
+
49
+ [More Information Needed]
50
+
51
+ ### Out-of-Scope Use
52
+
53
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
54
+
55
+ [More Information Needed]
56
+
57
+ ## Bias, Risks, and Limitations
58
+
59
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
60
+
61
+ [More Information Needed]
62
+
63
+ ### Recommendations
64
+
65
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
66
+
67
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
68
+
69
+ ## How to Get Started with the Model
70
+
71
+ Use the code below to get started with the model.
72
+
73
+ [More Information Needed]
74
+
75
+ ## Training Details
76
+
77
+ ### Training Data
78
+
79
+ <!-- This should link to a Data 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. -->
80
+
81
+ [More Information Needed]
82
+
83
+ ### Training Procedure
84
+
85
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
86
+
87
+ #### Preprocessing [optional]
88
+
89
+ [More Information Needed]
90
+
91
+
92
+ #### Training Hyperparameters
93
+
94
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
95
+
96
+ #### Speeds, Sizes, Times [optional]
97
+
98
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
99
+
100
+ [More Information Needed]
101
+
102
+ ## Evaluation
103
+
104
+ <!-- This section describes the evaluation protocols and provides the results. -->
105
+
106
+ ### Testing Data, Factors & Metrics
107
+
108
+ #### Testing Data
109
+
110
+ <!-- This should link to a Data Card if possible. -->
111
+
112
+ [More Information Needed]
113
+
114
+ #### Factors
115
+
116
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
117
+
118
+ [More Information Needed]
119
+
120
+ #### Metrics
121
+
122
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
123
+
124
+ [More Information Needed]
125
+
126
+ ### Results
127
+
128
+ [More Information Needed]
129
+
130
+ #### Summary
131
+
132
+
133
+
134
+ ## Model Examination [optional]
135
+
136
+ <!-- Relevant interpretability work for the model goes here -->
137
+
138
+ [More Information Needed]
139
+
140
+ ## Environmental Impact
141
+
142
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
143
+
144
+ 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).
145
+
146
+ - **Hardware Type:** [More Information Needed]
147
+ - **Hours used:** [More Information Needed]
148
+ - **Cloud Provider:** [More Information Needed]
149
+ - **Compute Region:** [More Information Needed]
150
+ - **Carbon Emitted:** [More Information Needed]
151
+
152
+ ## Technical Specifications [optional]
153
+
154
+ ### Model Architecture and Objective
155
+
156
+ [More Information Needed]
157
+
158
+ ### Compute Infrastructure
159
+
160
+ [More Information Needed]
161
+
162
+ #### Hardware
163
+
164
+ [More Information Needed]
165
+
166
+ #### Software
167
+
168
+ [More Information Needed]
169
+
170
+ ## Citation [optional]
171
+
172
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
173
+
174
+ **BibTeX:**
175
+
176
+ [More Information Needed]
177
+
178
+ **APA:**
179
+
180
+ [More Information Needed]
181
+
182
+ ## Glossary [optional]
183
+
184
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
185
+
186
+ [More Information Needed]
187
+
188
+ ## More Information [optional]
189
+
190
+ [More Information Needed]
191
+
192
+ ## Model Card Authors [optional]
193
+
194
+ [More Information Needed]
195
+
196
+ ## Model Card Contact
197
+
198
+ [More Information Needed]
199
+
200
+
201
+ ## Training procedure
202
+
203
+
204
+ The following `bitsandbytes` quantization config was used during training:
205
+ - quant_method: bitsandbytes
206
+ - load_in_8bit: True
207
+ - load_in_4bit: False
208
+ - llm_int8_threshold: 6.0
209
+ - llm_int8_skip_modules: None
210
+ - llm_int8_enable_fp32_cpu_offload: False
211
+ - llm_int8_has_fp16_weight: False
212
+ - bnb_4bit_quant_type: fp4
213
+ - bnb_4bit_use_double_quant: False
214
+ - bnb_4bit_compute_dtype: float32
215
+
216
+ ### Framework versions
217
+
218
+
219
+ - PEFT 0.6.0
checkpoint-50/adapter_config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "teknium/OpenHermes-2.5-Mistral-7B",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "lora_alpha": 32,
12
+ "lora_dropout": 0.05,
13
+ "modules_to_save": null,
14
+ "peft_type": "LORA",
15
+ "r": 128,
16
+ "rank_pattern": {},
17
+ "revision": null,
18
+ "target_modules": [
19
+ "q_proj",
20
+ "k_proj",
21
+ "up_proj",
22
+ "o_proj",
23
+ "gate_proj",
24
+ "down_proj",
25
+ "v_proj"
26
+ ],
27
+ "task_type": "CAUSAL_LM"
28
+ }
checkpoint-50/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a3cc46d7df08a29e40f60cbaebba3ffd740879f78150efafa78f8c933c9e6f0
3
+ size 1342339274
checkpoint-50/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b672f6b7accac26d4e8ea17b64b36cda058493ceafae493ea42869a72891a8df
3
+ size 14244
checkpoint-50/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66fc4977d94a5c5aba2bc63e71c04c1edca2632bc98631eb22dde6d4b9c38dbf
3
+ size 1064
checkpoint-50/trainer_state.json ADDED
@@ -0,0 +1,335 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.5729879140853882,
3
+ "best_model_checkpoint": "./lora-outB/checkpoint-50",
4
+ "epoch": 1.4970059880239521,
5
+ "eval_steps": 25,
6
+ "global_step": 50,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.03,
13
+ "learning_rate": 2.0000000000000003e-06,
14
+ "loss": 1.866,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.06,
19
+ "learning_rate": 4.000000000000001e-06,
20
+ "loss": 1.7383,
21
+ "step": 2
22
+ },
23
+ {
24
+ "epoch": 0.09,
25
+ "learning_rate": 6e-06,
26
+ "loss": 1.8306,
27
+ "step": 3
28
+ },
29
+ {
30
+ "epoch": 0.12,
31
+ "learning_rate": 8.000000000000001e-06,
32
+ "loss": 1.9213,
33
+ "step": 4
34
+ },
35
+ {
36
+ "epoch": 0.15,
37
+ "learning_rate": 1e-05,
38
+ "loss": 1.9524,
39
+ "step": 5
40
+ },
41
+ {
42
+ "epoch": 0.18,
43
+ "learning_rate": 1.2e-05,
44
+ "loss": 1.7308,
45
+ "step": 6
46
+ },
47
+ {
48
+ "epoch": 0.21,
49
+ "learning_rate": 1.4e-05,
50
+ "loss": 1.7334,
51
+ "step": 7
52
+ },
53
+ {
54
+ "epoch": 0.24,
55
+ "learning_rate": 1.6000000000000003e-05,
56
+ "loss": 1.6749,
57
+ "step": 8
58
+ },
59
+ {
60
+ "epoch": 0.27,
61
+ "learning_rate": 1.8e-05,
62
+ "loss": 1.805,
63
+ "step": 9
64
+ },
65
+ {
66
+ "epoch": 0.3,
67
+ "learning_rate": 2e-05,
68
+ "loss": 1.778,
69
+ "step": 10
70
+ },
71
+ {
72
+ "epoch": 0.33,
73
+ "learning_rate": 1.9997946042345128e-05,
74
+ "loss": 1.7804,
75
+ "step": 11
76
+ },
77
+ {
78
+ "epoch": 0.36,
79
+ "learning_rate": 1.9991785013128922e-05,
80
+ "loss": 1.8191,
81
+ "step": 12
82
+ },
83
+ {
84
+ "epoch": 0.39,
85
+ "learning_rate": 1.998151944325001e-05,
86
+ "loss": 1.7089,
87
+ "step": 13
88
+ },
89
+ {
90
+ "epoch": 0.42,
91
+ "learning_rate": 1.996715354971755e-05,
92
+ "loss": 1.7131,
93
+ "step": 14
94
+ },
95
+ {
96
+ "epoch": 0.45,
97
+ "learning_rate": 1.994869323391895e-05,
98
+ "loss": 1.917,
99
+ "step": 15
100
+ },
101
+ {
102
+ "epoch": 0.48,
103
+ "learning_rate": 1.9926146079195597e-05,
104
+ "loss": 1.6701,
105
+ "step": 16
106
+ },
107
+ {
108
+ "epoch": 0.51,
109
+ "learning_rate": 1.989952134772769e-05,
110
+ "loss": 1.7119,
111
+ "step": 17
112
+ },
113
+ {
114
+ "epoch": 0.54,
115
+ "learning_rate": 1.9868829976729444e-05,
116
+ "loss": 1.7037,
117
+ "step": 18
118
+ },
119
+ {
120
+ "epoch": 0.57,
121
+ "learning_rate": 1.983408457395613e-05,
122
+ "loss": 1.7314,
123
+ "step": 19
124
+ },
125
+ {
126
+ "epoch": 0.6,
127
+ "learning_rate": 1.9795299412524948e-05,
128
+ "loss": 1.6771,
129
+ "step": 20
130
+ },
131
+ {
132
+ "epoch": 0.63,
133
+ "learning_rate": 1.975249042505174e-05,
134
+ "loss": 1.6734,
135
+ "step": 21
136
+ },
137
+ {
138
+ "epoch": 0.66,
139
+ "learning_rate": 1.970567519710602e-05,
140
+ "loss": 1.689,
141
+ "step": 22
142
+ },
143
+ {
144
+ "epoch": 0.69,
145
+ "learning_rate": 1.9654872959986936e-05,
146
+ "loss": 1.7452,
147
+ "step": 23
148
+ },
149
+ {
150
+ "epoch": 0.72,
151
+ "learning_rate": 1.960010458282326e-05,
152
+ "loss": 1.7126,
153
+ "step": 24
154
+ },
155
+ {
156
+ "epoch": 0.75,
157
+ "learning_rate": 1.954139256400049e-05,
158
+ "loss": 1.5629,
159
+ "step": 25
160
+ },
161
+ {
162
+ "epoch": 0.75,
163
+ "eval_loss": 1.6511253118515015,
164
+ "eval_runtime": 5.4427,
165
+ "eval_samples_per_second": 5.145,
166
+ "eval_steps_per_second": 0.735,
167
+ "step": 25
168
+ },
169
+ {
170
+ "epoch": 0.78,
171
+ "learning_rate": 1.947876102191873e-05,
172
+ "loss": 1.6948,
173
+ "step": 26
174
+ },
175
+ {
176
+ "epoch": 0.81,
177
+ "learning_rate": 1.9412235685085034e-05,
178
+ "loss": 1.5969,
179
+ "step": 27
180
+ },
181
+ {
182
+ "epoch": 0.84,
183
+ "learning_rate": 1.9341843881544372e-05,
184
+ "loss": 1.5367,
185
+ "step": 28
186
+ },
187
+ {
188
+ "epoch": 0.87,
189
+ "learning_rate": 1.926761452765349e-05,
190
+ "loss": 1.463,
191
+ "step": 29
192
+ },
193
+ {
194
+ "epoch": 0.9,
195
+ "learning_rate": 1.918957811620231e-05,
196
+ "loss": 1.4575,
197
+ "step": 30
198
+ },
199
+ {
200
+ "epoch": 0.93,
201
+ "learning_rate": 1.9107766703887764e-05,
202
+ "loss": 1.5928,
203
+ "step": 31
204
+ },
205
+ {
206
+ "epoch": 0.96,
207
+ "learning_rate": 1.9022213898145176e-05,
208
+ "loss": 1.5604,
209
+ "step": 32
210
+ },
211
+ {
212
+ "epoch": 0.99,
213
+ "learning_rate": 1.893295484334259e-05,
214
+ "loss": 1.6508,
215
+ "step": 33
216
+ },
217
+ {
218
+ "epoch": 1.02,
219
+ "learning_rate": 1.8840026206343786e-05,
220
+ "loss": 1.4583,
221
+ "step": 34
222
+ },
223
+ {
224
+ "epoch": 1.05,
225
+ "learning_rate": 1.8743466161445823e-05,
226
+ "loss": 1.7124,
227
+ "step": 35
228
+ },
229
+ {
230
+ "epoch": 1.08,
231
+ "learning_rate": 1.8643314374697377e-05,
232
+ "loss": 1.462,
233
+ "step": 36
234
+ },
235
+ {
236
+ "epoch": 1.11,
237
+ "learning_rate": 1.853961198760426e-05,
238
+ "loss": 1.6664,
239
+ "step": 37
240
+ },
241
+ {
242
+ "epoch": 1.14,
243
+ "learning_rate": 1.8432401600228823e-05,
244
+ "loss": 1.6264,
245
+ "step": 38
246
+ },
247
+ {
248
+ "epoch": 1.17,
249
+ "learning_rate": 1.832172725369024e-05,
250
+ "loss": 1.6704,
251
+ "step": 39
252
+ },
253
+ {
254
+ "epoch": 1.2,
255
+ "learning_rate": 1.8207634412072765e-05,
256
+ "loss": 1.5221,
257
+ "step": 40
258
+ },
259
+ {
260
+ "epoch": 1.23,
261
+ "learning_rate": 1.8090169943749477e-05,
262
+ "loss": 1.5411,
263
+ "step": 41
264
+ },
265
+ {
266
+ "epoch": 1.26,
267
+ "learning_rate": 1.7969382102129153e-05,
268
+ "loss": 1.4493,
269
+ "step": 42
270
+ },
271
+ {
272
+ "epoch": 1.29,
273
+ "learning_rate": 1.7845320505834176e-05,
274
+ "loss": 1.4783,
275
+ "step": 43
276
+ },
277
+ {
278
+ "epoch": 1.32,
279
+ "learning_rate": 1.771803611831762e-05,
280
+ "loss": 1.5882,
281
+ "step": 44
282
+ },
283
+ {
284
+ "epoch": 1.35,
285
+ "learning_rate": 1.758758122692791e-05,
286
+ "loss": 1.5848,
287
+ "step": 45
288
+ },
289
+ {
290
+ "epoch": 1.38,
291
+ "learning_rate": 1.74540094214296e-05,
292
+ "loss": 1.4439,
293
+ "step": 46
294
+ },
295
+ {
296
+ "epoch": 1.41,
297
+ "learning_rate": 1.7317375571989158e-05,
298
+ "loss": 1.5398,
299
+ "step": 47
300
+ },
301
+ {
302
+ "epoch": 1.44,
303
+ "learning_rate": 1.717773580663479e-05,
304
+ "loss": 1.3689,
305
+ "step": 48
306
+ },
307
+ {
308
+ "epoch": 1.47,
309
+ "learning_rate": 1.703514748819948e-05,
310
+ "loss": 1.5311,
311
+ "step": 49
312
+ },
313
+ {
314
+ "epoch": 1.5,
315
+ "learning_rate": 1.688966919075687e-05,
316
+ "loss": 1.5253,
317
+ "step": 50
318
+ },
319
+ {
320
+ "epoch": 1.5,
321
+ "eval_loss": 1.5729879140853882,
322
+ "eval_runtime": 5.4053,
323
+ "eval_samples_per_second": 5.18,
324
+ "eval_steps_per_second": 0.74,
325
+ "step": 50
326
+ }
327
+ ],
328
+ "logging_steps": 1,
329
+ "max_steps": 165,
330
+ "num_train_epochs": 5,
331
+ "save_steps": 50,
332
+ "total_flos": 5.618042316364186e+16,
333
+ "trial_name": null,
334
+ "trial_params": null
335
+ }
checkpoint-50/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:218e6b2697498e27486ba1b06651dcc4e8143ab7c7f81e54381850c57f692daf
3
+ size 4920
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "teknium/OpenHermes-2.5-Mistral-7B",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 14336,
13
+ "max_position_embeddings": 32768,
14
+ "model_type": "llama",
15
+ "num_attention_heads": 32,
16
+ "num_hidden_layers": 32,
17
+ "num_key_value_heads": 8,
18
+ "pretraining_tp": 1,
19
+ "quantization_config": {
20
+ "bnb_4bit_compute_dtype": "float32",
21
+ "bnb_4bit_quant_type": "fp4",
22
+ "bnb_4bit_use_double_quant": false,
23
+ "llm_int8_enable_fp32_cpu_offload": false,
24
+ "llm_int8_has_fp16_weight": false,
25
+ "llm_int8_skip_modules": null,
26
+ "llm_int8_threshold": 6.0,
27
+ "load_in_4bit": false,
28
+ "load_in_8bit": true,
29
+ "quant_method": "bitsandbytes"
30
+ },
31
+ "rms_norm_eps": 1e-05,
32
+ "rope_scaling": null,
33
+ "rope_theta": 10000.0,
34
+ "sliding_window": 4096,
35
+ "tie_word_embeddings": false,
36
+ "torch_dtype": "bfloat16",
37
+ "transformers_version": "4.34.1",
38
+ "use_cache": false,
39
+ "vocab_size": 32002
40
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "32000": {
30
+ "content": "<|im_end|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "32001": {
38
+ "content": "<|im_start|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ }
45
+ },
46
+ "additional_special_tokens": [],
47
+ "bos_token": "<s>",
48
+ "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
49
+ "clean_up_tokenization_spaces": false,
50
+ "eos_token": "</s>",
51
+ "legacy": true,
52
+ "model_max_length": 1000000000000000019884624838656,
53
+ "pad_token": "</s>",
54
+ "sp_model_kwargs": {},
55
+ "spaces_between_special_tokens": false,
56
+ "tokenizer_class": "LlamaTokenizer",
57
+ "trust_remote_code": false,
58
+ "unk_token": "<unk>",
59
+ "use_default_system_prompt": true,
60
+ "use_fast": true
61
+ }