Text Generation
Safetensors
Chinese
English
conversational
wangrongsheng commited on
Commit
d285247
1 Parent(s): b2e6d34

Upload 12 files

Browse files
checkpoint-14000/README.md ADDED
@@ -0,0 +1,204 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: ../Mixtral-8x7B-Instruct-v0.1
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
+
201
+
202
+ ### Framework versions
203
+
204
+ - PEFT 0.7.1
checkpoint-14000/adapter_config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "../Mixtral-8x7B-Instruct-v0.1",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "loftq_config": {},
12
+ "lora_alpha": 16.0,
13
+ "lora_dropout": 0.1,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 8,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "q_proj",
23
+ "v_proj"
24
+ ],
25
+ "task_type": "CAUSAL_LM"
26
+ }
checkpoint-14000/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:628aa18a3238a03e8b271326930e12cbe4c82d58201345073f0a303ef6763697
3
+ size 13648432
checkpoint-14000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a5b332e7dc741d75ca8a81e212ce764816d7c328467975948aea6d0946b9a20
3
+ size 27370618
checkpoint-14000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21a7c4f22bffb80baa60b488cd4afa64814cad74b5775d6a45f8d595bfb6defa
3
+ size 14244
checkpoint-14000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f24c054a329aefca58564f17807a21d9335c9a0cf81b82e034455dd80c267a73
3
+ size 1064
checkpoint-14000/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
+ }
checkpoint-14000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-14000/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
checkpoint-14000/tokenizer_config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ },
30
+ "additional_special_tokens": [],
31
+ "bos_token": "<s>",
32
+ "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
33
+ "clean_up_tokenization_spaces": false,
34
+ "eos_token": "</s>",
35
+ "legacy": true,
36
+ "model_max_length": 1000000000000000019884624838656,
37
+ "pad_token": "</s>",
38
+ "padding_side": "right",
39
+ "sp_model_kwargs": {},
40
+ "spaces_between_special_tokens": false,
41
+ "split_special_tokens": false,
42
+ "tokenizer_class": "LlamaTokenizer",
43
+ "unk_token": "<unk>",
44
+ "use_default_system_prompt": false
45
+ }
checkpoint-14000/trainer_state.json ADDED
@@ -0,0 +1,861 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.5379316595667545,
5
+ "eval_steps": 500,
6
+ "global_step": 14000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.02,
13
+ "learning_rate": 4.999549488698767e-05,
14
+ "loss": 0.9367,
15
+ "step": 100
16
+ },
17
+ {
18
+ "epoch": 0.04,
19
+ "learning_rate": 4.998198117163414e-05,
20
+ "loss": 0.8539,
21
+ "step": 200
22
+ },
23
+ {
24
+ "epoch": 0.05,
25
+ "learning_rate": 4.995946372440459e-05,
26
+ "loss": 0.8563,
27
+ "step": 300
28
+ },
29
+ {
30
+ "epoch": 0.07,
31
+ "learning_rate": 4.99279506607906e-05,
32
+ "loss": 0.8552,
33
+ "step": 400
34
+ },
35
+ {
36
+ "epoch": 0.09,
37
+ "learning_rate": 4.9887453338385195e-05,
38
+ "loss": 0.8377,
39
+ "step": 500
40
+ },
41
+ {
42
+ "epoch": 0.11,
43
+ "learning_rate": 4.98379863527895e-05,
44
+ "loss": 0.8346,
45
+ "step": 600
46
+ },
47
+ {
48
+ "epoch": 0.13,
49
+ "learning_rate": 4.9779567532352364e-05,
50
+ "loss": 0.8338,
51
+ "step": 700
52
+ },
53
+ {
54
+ "epoch": 0.15,
55
+ "learning_rate": 4.971221793174483e-05,
56
+ "loss": 0.8176,
57
+ "step": 800
58
+ },
59
+ {
60
+ "epoch": 0.16,
61
+ "learning_rate": 4.9635961824371865e-05,
62
+ "loss": 0.8297,
63
+ "step": 900
64
+ },
65
+ {
66
+ "epoch": 0.18,
67
+ "learning_rate": 4.9550826693624e-05,
68
+ "loss": 0.8337,
69
+ "step": 1000
70
+ },
71
+ {
72
+ "epoch": 0.2,
73
+ "learning_rate": 4.945684322297207e-05,
74
+ "loss": 0.8243,
75
+ "step": 1100
76
+ },
77
+ {
78
+ "epoch": 0.22,
79
+ "learning_rate": 4.935404528490858e-05,
80
+ "loss": 0.8289,
81
+ "step": 1200
82
+ },
83
+ {
84
+ "epoch": 0.24,
85
+ "learning_rate": 4.924246992873982e-05,
86
+ "loss": 0.818,
87
+ "step": 1300
88
+ },
89
+ {
90
+ "epoch": 0.25,
91
+ "learning_rate": 4.9122157367232894e-05,
92
+ "loss": 0.8361,
93
+ "step": 1400
94
+ },
95
+ {
96
+ "epoch": 0.27,
97
+ "learning_rate": 4.899315096212272e-05,
98
+ "loss": 0.8055,
99
+ "step": 1500
100
+ },
101
+ {
102
+ "epoch": 0.29,
103
+ "learning_rate": 4.8855497208484046e-05,
104
+ "loss": 0.8284,
105
+ "step": 1600
106
+ },
107
+ {
108
+ "epoch": 0.31,
109
+ "learning_rate": 4.8709245717974204e-05,
110
+ "loss": 0.8214,
111
+ "step": 1700
112
+ },
113
+ {
114
+ "epoch": 0.33,
115
+ "learning_rate": 4.8554449200952635e-05,
116
+ "loss": 0.8243,
117
+ "step": 1800
118
+ },
119
+ {
120
+ "epoch": 0.34,
121
+ "learning_rate": 4.8391163447483587e-05,
122
+ "loss": 0.8191,
123
+ "step": 1900
124
+ },
125
+ {
126
+ "epoch": 0.36,
127
+ "learning_rate": 4.821944730722887e-05,
128
+ "loss": 0.8106,
129
+ "step": 2000
130
+ },
131
+ {
132
+ "epoch": 0.38,
133
+ "learning_rate": 4.803936266823792e-05,
134
+ "loss": 0.8217,
135
+ "step": 2100
136
+ },
137
+ {
138
+ "epoch": 0.4,
139
+ "learning_rate": 4.785097443464276e-05,
140
+ "loss": 0.8071,
141
+ "step": 2200
142
+ },
143
+ {
144
+ "epoch": 0.42,
145
+ "learning_rate": 4.765435050326602e-05,
146
+ "loss": 0.8164,
147
+ "step": 2300
148
+ },
149
+ {
150
+ "epoch": 0.44,
151
+ "learning_rate": 4.744956173915022e-05,
152
+ "loss": 0.8264,
153
+ "step": 2400
154
+ },
155
+ {
156
+ "epoch": 0.45,
157
+ "learning_rate": 4.7236681950017445e-05,
158
+ "loss": 0.8183,
159
+ "step": 2500
160
+ },
161
+ {
162
+ "epoch": 0.47,
163
+ "learning_rate": 4.701578785966834e-05,
164
+ "loss": 0.8035,
165
+ "step": 2600
166
+ },
167
+ {
168
+ "epoch": 0.49,
169
+ "learning_rate": 4.678695908033017e-05,
170
+ "loss": 0.8019,
171
+ "step": 2700
172
+ },
173
+ {
174
+ "epoch": 0.51,
175
+ "learning_rate": 4.655027808396385e-05,
176
+ "loss": 0.8084,
177
+ "step": 2800
178
+ },
179
+ {
180
+ "epoch": 0.53,
181
+ "learning_rate": 4.6305830172540295e-05,
182
+ "loss": 0.8124,
183
+ "step": 2900
184
+ },
185
+ {
186
+ "epoch": 0.54,
187
+ "learning_rate": 4.6053703447296826e-05,
188
+ "loss": 0.8206,
189
+ "step": 3000
190
+ },
191
+ {
192
+ "epoch": 0.56,
193
+ "learning_rate": 4.579398877698471e-05,
194
+ "loss": 0.8137,
195
+ "step": 3100
196
+ },
197
+ {
198
+ "epoch": 0.58,
199
+ "learning_rate": 4.55267797651192e-05,
200
+ "loss": 0.803,
201
+ "step": 3200
202
+ },
203
+ {
204
+ "epoch": 0.6,
205
+ "learning_rate": 4.5252172716244e-05,
206
+ "loss": 0.8108,
207
+ "step": 3300
208
+ },
209
+ {
210
+ "epoch": 0.62,
211
+ "learning_rate": 4.4970266601222243e-05,
212
+ "loss": 0.8154,
213
+ "step": 3400
214
+ },
215
+ {
216
+ "epoch": 0.63,
217
+ "learning_rate": 4.4681163021566496e-05,
218
+ "loss": 0.7998,
219
+ "step": 3500
220
+ },
221
+ {
222
+ "epoch": 0.65,
223
+ "learning_rate": 4.4384966172820644e-05,
224
+ "loss": 0.8109,
225
+ "step": 3600
226
+ },
227
+ {
228
+ "epoch": 0.67,
229
+ "learning_rate": 4.40817828070069e-05,
230
+ "loss": 0.8102,
231
+ "step": 3700
232
+ },
233
+ {
234
+ "epoch": 0.69,
235
+ "learning_rate": 4.377172219415136e-05,
236
+ "loss": 0.8119,
237
+ "step": 3800
238
+ },
239
+ {
240
+ "epoch": 0.71,
241
+ "learning_rate": 4.345489608290216e-05,
242
+ "loss": 0.8041,
243
+ "step": 3900
244
+ },
245
+ {
246
+ "epoch": 0.73,
247
+ "learning_rate": 4.313141866025423e-05,
248
+ "loss": 0.8149,
249
+ "step": 4000
250
+ },
251
+ {
252
+ "epoch": 0.74,
253
+ "learning_rate": 4.280140651039522e-05,
254
+ "loss": 0.8043,
255
+ "step": 4100
256
+ },
257
+ {
258
+ "epoch": 0.76,
259
+ "learning_rate": 4.246497857268759e-05,
260
+ "loss": 0.7933,
261
+ "step": 4200
262
+ },
263
+ {
264
+ "epoch": 0.78,
265
+ "learning_rate": 4.2122256098801726e-05,
266
+ "loss": 0.8022,
267
+ "step": 4300
268
+ },
269
+ {
270
+ "epoch": 0.8,
271
+ "learning_rate": 4.177336260901578e-05,
272
+ "loss": 0.8083,
273
+ "step": 4400
274
+ },
275
+ {
276
+ "epoch": 0.82,
277
+ "learning_rate": 4.1418423847697786e-05,
278
+ "loss": 0.8082,
279
+ "step": 4500
280
+ },
281
+ {
282
+ "epoch": 0.83,
283
+ "learning_rate": 4.105756773798633e-05,
284
+ "loss": 0.7956,
285
+ "step": 4600
286
+ },
287
+ {
288
+ "epoch": 0.85,
289
+ "learning_rate": 4.0690924335685865e-05,
290
+ "loss": 0.8072,
291
+ "step": 4700
292
+ },
293
+ {
294
+ "epoch": 0.87,
295
+ "learning_rate": 4.031862578239338e-05,
296
+ "loss": 0.7954,
297
+ "step": 4800
298
+ },
299
+ {
300
+ "epoch": 0.89,
301
+ "learning_rate": 3.994080625787343e-05,
302
+ "loss": 0.8025,
303
+ "step": 4900
304
+ },
305
+ {
306
+ "epoch": 0.91,
307
+ "learning_rate": 3.955760193169851e-05,
308
+ "loss": 0.796,
309
+ "step": 5000
310
+ },
311
+ {
312
+ "epoch": 0.92,
313
+ "learning_rate": 3.9169150914172324e-05,
314
+ "loss": 0.7924,
315
+ "step": 5100
316
+ },
317
+ {
318
+ "epoch": 0.94,
319
+ "learning_rate": 3.8775593206553575e-05,
320
+ "loss": 0.8076,
321
+ "step": 5200
322
+ },
323
+ {
324
+ "epoch": 0.96,
325
+ "learning_rate": 3.837707065059823e-05,
326
+ "loss": 0.7929,
327
+ "step": 5300
328
+ },
329
+ {
330
+ "epoch": 0.98,
331
+ "learning_rate": 3.79737268774385e-05,
332
+ "loss": 0.7966,
333
+ "step": 5400
334
+ },
335
+ {
336
+ "epoch": 1.0,
337
+ "learning_rate": 3.756570725581684e-05,
338
+ "loss": 0.812,
339
+ "step": 5500
340
+ },
341
+ {
342
+ "epoch": 1.02,
343
+ "learning_rate": 3.71531588396938e-05,
344
+ "loss": 0.7952,
345
+ "step": 5600
346
+ },
347
+ {
348
+ "epoch": 1.03,
349
+ "learning_rate": 3.673623031524838e-05,
350
+ "loss": 0.807,
351
+ "step": 5700
352
+ },
353
+ {
354
+ "epoch": 1.05,
355
+ "learning_rate": 3.6315071947290255e-05,
356
+ "loss": 0.7919,
357
+ "step": 5800
358
+ },
359
+ {
360
+ "epoch": 1.07,
361
+ "learning_rate": 3.588983552510291e-05,
362
+ "loss": 0.8051,
363
+ "step": 5900
364
+ },
365
+ {
366
+ "epoch": 1.09,
367
+ "learning_rate": 3.546067430773747e-05,
368
+ "loss": 0.8067,
369
+ "step": 6000
370
+ },
371
+ {
372
+ "epoch": 1.11,
373
+ "learning_rate": 3.50277429687767e-05,
374
+ "loss": 0.7982,
375
+ "step": 6100
376
+ },
377
+ {
378
+ "epoch": 1.12,
379
+ "learning_rate": 3.459119754058929e-05,
380
+ "loss": 0.7965,
381
+ "step": 6200
382
+ },
383
+ {
384
+ "epoch": 1.14,
385
+ "learning_rate": 3.4151195358094365e-05,
386
+ "loss": 0.7829,
387
+ "step": 6300
388
+ },
389
+ {
390
+ "epoch": 1.16,
391
+ "learning_rate": 3.370789500205656e-05,
392
+ "loss": 0.7905,
393
+ "step": 6400
394
+ },
395
+ {
396
+ "epoch": 1.18,
397
+ "learning_rate": 3.326593563722561e-05,
398
+ "loss": 0.7904,
399
+ "step": 6500
400
+ },
401
+ {
402
+ "epoch": 1.2,
403
+ "learning_rate": 3.281654834858534e-05,
404
+ "loss": 0.7972,
405
+ "step": 6600
406
+ },
407
+ {
408
+ "epoch": 1.21,
409
+ "learning_rate": 3.236434390525093e-05,
410
+ "loss": 0.7995,
411
+ "step": 6700
412
+ },
413
+ {
414
+ "epoch": 1.23,
415
+ "learning_rate": 3.190948528579214e-05,
416
+ "loss": 0.7965,
417
+ "step": 6800
418
+ },
419
+ {
420
+ "epoch": 1.25,
421
+ "learning_rate": 3.1452136425367785e-05,
422
+ "loss": 0.7956,
423
+ "step": 6900
424
+ },
425
+ {
426
+ "epoch": 1.27,
427
+ "learning_rate": 3.099246215664205e-05,
428
+ "loss": 0.7894,
429
+ "step": 7000
430
+ },
431
+ {
432
+ "epoch": 1.29,
433
+ "learning_rate": 3.0530628150377295e-05,
434
+ "loss": 0.8024,
435
+ "step": 7100
436
+ },
437
+ {
438
+ "epoch": 1.31,
439
+ "learning_rate": 3.0066800855724798e-05,
440
+ "loss": 0.7726,
441
+ "step": 7200
442
+ },
443
+ {
444
+ "epoch": 1.32,
445
+ "learning_rate": 2.960114744023503e-05,
446
+ "loss": 0.7881,
447
+ "step": 7300
448
+ },
449
+ {
450
+ "epoch": 1.34,
451
+ "learning_rate": 2.913383572960889e-05,
452
+ "loss": 0.7993,
453
+ "step": 7400
454
+ },
455
+ {
456
+ "epoch": 1.36,
457
+ "learning_rate": 2.866503414721184e-05,
458
+ "loss": 0.8094,
459
+ "step": 7500
460
+ },
461
+ {
462
+ "epoch": 1.38,
463
+ "learning_rate": 2.8194911653372613e-05,
464
+ "loss": 0.7923,
465
+ "step": 7600
466
+ },
467
+ {
468
+ "epoch": 1.4,
469
+ "learning_rate": 2.7723637684488356e-05,
470
+ "loss": 0.8058,
471
+ "step": 7700
472
+ },
473
+ {
474
+ "epoch": 1.41,
475
+ "learning_rate": 2.725138209195824e-05,
476
+ "loss": 0.7852,
477
+ "step": 7800
478
+ },
479
+ {
480
+ "epoch": 1.43,
481
+ "learning_rate": 2.677831508096747e-05,
482
+ "loss": 0.7888,
483
+ "step": 7900
484
+ },
485
+ {
486
+ "epoch": 1.45,
487
+ "learning_rate": 2.630460714914379e-05,
488
+ "loss": 0.8021,
489
+ "step": 8000
490
+ },
491
+ {
492
+ "epoch": 1.47,
493
+ "learning_rate": 2.5830429025108627e-05,
494
+ "loss": 0.7901,
495
+ "step": 8100
496
+ },
497
+ {
498
+ "epoch": 1.49,
499
+ "learning_rate": 2.5355951606944913e-05,
500
+ "loss": 0.8147,
501
+ "step": 8200
502
+ },
503
+ {
504
+ "epoch": 1.5,
505
+ "learning_rate": 2.488134590060391e-05,
506
+ "loss": 0.7986,
507
+ "step": 8300
508
+ },
509
+ {
510
+ "epoch": 1.52,
511
+ "learning_rate": 2.441152781437193e-05,
512
+ "loss": 0.8005,
513
+ "step": 8400
514
+ },
515
+ {
516
+ "epoch": 1.54,
517
+ "learning_rate": 2.393717568838824e-05,
518
+ "loss": 0.7923,
519
+ "step": 8500
520
+ },
521
+ {
522
+ "epoch": 1.56,
523
+ "learning_rate": 2.346320661389542e-05,
524
+ "loss": 0.789,
525
+ "step": 8600
526
+ },
527
+ {
528
+ "epoch": 1.58,
529
+ "learning_rate": 2.2989791413633083e-05,
530
+ "loss": 0.7746,
531
+ "step": 8700
532
+ },
533
+ {
534
+ "epoch": 1.6,
535
+ "learning_rate": 2.2517100710719537e-05,
536
+ "loss": 0.7861,
537
+ "step": 8800
538
+ },
539
+ {
540
+ "epoch": 1.61,
541
+ "learning_rate": 2.2045304867157723e-05,
542
+ "loss": 0.7853,
543
+ "step": 8900
544
+ },
545
+ {
546
+ "epoch": 1.63,
547
+ "learning_rate": 2.157457392243513e-05,
548
+ "loss": 0.7903,
549
+ "step": 9000
550
+ },
551
+ {
552
+ "epoch": 1.65,
553
+ "learning_rate": 2.110507753224012e-05,
554
+ "loss": 0.7986,
555
+ "step": 9100
556
+ },
557
+ {
558
+ "epoch": 1.67,
559
+ "learning_rate": 2.0636984907316447e-05,
560
+ "loss": 0.7961,
561
+ "step": 9200
562
+ },
563
+ {
564
+ "epoch": 1.69,
565
+ "learning_rate": 2.017046475247813e-05,
566
+ "loss": 0.7958,
567
+ "step": 9300
568
+ },
569
+ {
570
+ "epoch": 1.7,
571
+ "learning_rate": 1.9705685205806772e-05,
572
+ "loss": 0.7866,
573
+ "step": 9400
574
+ },
575
+ {
576
+ "epoch": 1.72,
577
+ "learning_rate": 1.9242813778053085e-05,
578
+ "loss": 0.7816,
579
+ "step": 9500
580
+ },
581
+ {
582
+ "epoch": 1.74,
583
+ "learning_rate": 1.8782017292264426e-05,
584
+ "loss": 0.7848,
585
+ "step": 9600
586
+ },
587
+ {
588
+ "epoch": 1.76,
589
+ "learning_rate": 1.8323461823660335e-05,
590
+ "loss": 0.7935,
591
+ "step": 9700
592
+ },
593
+ {
594
+ "epoch": 1.78,
595
+ "learning_rate": 1.786731263977748e-05,
596
+ "loss": 0.7978,
597
+ "step": 9800
598
+ },
599
+ {
600
+ "epoch": 1.79,
601
+ "learning_rate": 1.7413734140905783e-05,
602
+ "loss": 0.7936,
603
+ "step": 9900
604
+ },
605
+ {
606
+ "epoch": 1.81,
607
+ "learning_rate": 1.696288980083704e-05,
608
+ "loss": 0.7996,
609
+ "step": 10000
610
+ },
611
+ {
612
+ "epoch": 1.83,
613
+ "learning_rate": 1.6514942107947466e-05,
614
+ "loss": 0.7798,
615
+ "step": 10100
616
+ },
617
+ {
618
+ "epoch": 1.85,
619
+ "learning_rate": 1.6070052506635487e-05,
620
+ "loss": 0.786,
621
+ "step": 10200
622
+ },
623
+ {
624
+ "epoch": 1.87,
625
+ "learning_rate": 1.5628381339135647e-05,
626
+ "loss": 0.7912,
627
+ "step": 10300
628
+ },
629
+ {
630
+ "epoch": 1.89,
631
+ "learning_rate": 1.5190087787729873e-05,
632
+ "loss": 0.7767,
633
+ "step": 10400
634
+ },
635
+ {
636
+ "epoch": 1.9,
637
+ "learning_rate": 1.4755329817376672e-05,
638
+ "loss": 0.7891,
639
+ "step": 10500
640
+ },
641
+ {
642
+ "epoch": 1.92,
643
+ "learning_rate": 1.4324264118779218e-05,
644
+ "loss": 0.7885,
645
+ "step": 10600
646
+ },
647
+ {
648
+ "epoch": 1.94,
649
+ "learning_rate": 1.389704605191254e-05,
650
+ "loss": 0.7969,
651
+ "step": 10700
652
+ },
653
+ {
654
+ "epoch": 1.96,
655
+ "learning_rate": 1.3473829590030412e-05,
656
+ "loss": 0.788,
657
+ "step": 10800
658
+ },
659
+ {
660
+ "epoch": 1.98,
661
+ "learning_rate": 1.3054767264171989e-05,
662
+ "loss": 0.7861,
663
+ "step": 10900
664
+ },
665
+ {
666
+ "epoch": 1.99,
667
+ "learning_rate": 1.2640010108188234e-05,
668
+ "loss": 0.7864,
669
+ "step": 11000
670
+ },
671
+ {
672
+ "epoch": 2.01,
673
+ "learning_rate": 1.2229707604308002e-05,
674
+ "loss": 0.7989,
675
+ "step": 11100
676
+ },
677
+ {
678
+ "epoch": 2.03,
679
+ "learning_rate": 1.1824007629263217e-05,
680
+ "loss": 0.7764,
681
+ "step": 11200
682
+ },
683
+ {
684
+ "epoch": 2.05,
685
+ "learning_rate": 1.1423056400992816e-05,
686
+ "loss": 0.7934,
687
+ "step": 11300
688
+ },
689
+ {
690
+ "epoch": 2.07,
691
+ "learning_rate": 1.1026998425944449e-05,
692
+ "loss": 0.786,
693
+ "step": 11400
694
+ },
695
+ {
696
+ "epoch": 2.08,
697
+ "learning_rate": 1.0635976446993102e-05,
698
+ "loss": 0.7922,
699
+ "step": 11500
700
+ },
701
+ {
702
+ "epoch": 2.1,
703
+ "learning_rate": 1.02501313919952e-05,
704
+ "loss": 0.7842,
705
+ "step": 11600
706
+ },
707
+ {
708
+ "epoch": 2.12,
709
+ "learning_rate": 9.869602322996985e-06,
710
+ "loss": 0.7932,
711
+ "step": 11700
712
+ },
713
+ {
714
+ "epoch": 2.14,
715
+ "learning_rate": 9.494526386115285e-06,
716
+ "loss": 0.7754,
717
+ "step": 11800
718
+ },
719
+ {
720
+ "epoch": 2.16,
721
+ "learning_rate": 9.125038762108796e-06,
722
+ "loss": 0.7921,
723
+ "step": 11900
724
+ },
725
+ {
726
+ "epoch": 2.18,
727
+ "learning_rate": 8.76127261765777e-06,
728
+ "loss": 0.7935,
729
+ "step": 12000
730
+ },
731
+ {
732
+ "epoch": 2.19,
733
+ "learning_rate": 8.403359057369443e-06,
734
+ "loss": 0.7857,
735
+ "step": 12100
736
+ },
737
+ {
738
+ "epoch": 2.21,
739
+ "learning_rate": 8.05142707652685e-06,
740
+ "loss": 0.7884,
741
+ "step": 12200
742
+ },
743
+ {
744
+ "epoch": 2.23,
745
+ "learning_rate": 7.705603514597697e-06,
746
+ "loss": 0.7896,
747
+ "step": 12300
748
+ },
749
+ {
750
+ "epoch": 2.25,
751
+ "learning_rate": 7.366013009520287e-06,
752
+ "loss": 0.7823,
753
+ "step": 12400
754
+ },
755
+ {
756
+ "epoch": 2.27,
757
+ "learning_rate": 7.032777952782879e-06,
758
+ "loss": 0.7743,
759
+ "step": 12500
760
+ },
761
+ {
762
+ "epoch": 2.28,
763
+ "learning_rate": 6.7060184453127065e-06,
764
+ "loss": 0.7912,
765
+ "step": 12600
766
+ },
767
+ {
768
+ "epoch": 2.3,
769
+ "learning_rate": 6.385852254190483e-06,
770
+ "loss": 0.7814,
771
+ "step": 12700
772
+ },
773
+ {
774
+ "epoch": 2.32,
775
+ "learning_rate": 6.072394770206108e-06,
776
+ "loss": 0.7882,
777
+ "step": 12800
778
+ },
779
+ {
780
+ "epoch": 2.34,
781
+ "learning_rate": 5.7657589662707655e-06,
782
+ "loss": 0.7895,
783
+ "step": 12900
784
+ },
785
+ {
786
+ "epoch": 2.36,
787
+ "learning_rate": 5.4660553567005e-06,
788
+ "loss": 0.7872,
789
+ "step": 13000
790
+ },
791
+ {
792
+ "epoch": 2.37,
793
+ "learning_rate": 5.173391957385812e-06,
794
+ "loss": 0.7932,
795
+ "step": 13100
796
+ },
797
+ {
798
+ "epoch": 2.39,
799
+ "learning_rate": 4.887874246861776e-06,
800
+ "loss": 0.7979,
801
+ "step": 13200
802
+ },
803
+ {
804
+ "epoch": 2.41,
805
+ "learning_rate": 4.609605128292627e-06,
806
+ "loss": 0.7816,
807
+ "step": 13300
808
+ },
809
+ {
810
+ "epoch": 2.43,
811
+ "learning_rate": 4.33868489238452e-06,
812
+ "loss": 0.798,
813
+ "step": 13400
814
+ },
815
+ {
816
+ "epoch": 2.45,
817
+ "learning_rate": 4.0752111812398825e-06,
818
+ "loss": 0.7787,
819
+ "step": 13500
820
+ },
821
+ {
822
+ "epoch": 2.47,
823
+ "learning_rate": 3.819278953166247e-06,
824
+ "loss": 0.7929,
825
+ "step": 13600
826
+ },
827
+ {
828
+ "epoch": 2.48,
829
+ "learning_rate": 3.570980448452507e-06,
830
+ "loss": 0.7856,
831
+ "step": 13700
832
+ },
833
+ {
834
+ "epoch": 2.5,
835
+ "learning_rate": 3.3304051561246193e-06,
836
+ "loss": 0.7891,
837
+ "step": 13800
838
+ },
839
+ {
840
+ "epoch": 2.52,
841
+ "learning_rate": 3.0976397816929847e-06,
842
+ "loss": 0.7871,
843
+ "step": 13900
844
+ },
845
+ {
846
+ "epoch": 2.54,
847
+ "learning_rate": 2.872768215902963e-06,
848
+ "loss": 0.7771,
849
+ "step": 14000
850
+ }
851
+ ],
852
+ "logging_steps": 100,
853
+ "max_steps": 16548,
854
+ "num_input_tokens_seen": 0,
855
+ "num_train_epochs": 3,
856
+ "save_steps": 1000,
857
+ "total_flos": 1.2626281575022697e+20,
858
+ "train_batch_size": 8,
859
+ "trial_name": null,
860
+ "trial_params": null
861
+ }
checkpoint-14000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:455309350511831905966b7bcd78c583e37410b1d5d2c6d9a872ef97bbccde28
3
+ size 4856