Text Generation
Safetensors
Chinese
English
wangrongsheng commited on
Commit
dbb7a66
1 Parent(s): 5e4f629

Upload 12 files

Browse files
checkpoint-16000/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-16000/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-16000/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9df721771a196508551976cd73cd4de6fce7e0fe05979b7e6c53c49e5fff27f
3
+ size 13648432
checkpoint-16000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23266e2bf3af3442959de9ca0a5913967479f74787295d8b51e79ad6e98e2b2a
3
+ size 27370618
checkpoint-16000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6262cad58087f208a88e0bbcf5e87e1c0449000e16f6e0c134bb3a1dceb626ee
3
+ size 14244
checkpoint-16000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbf63f86ea51df2a8ba9f2dd7c80ab769a24c5fe84893e916d29d87464737f1d
3
+ size 1064
checkpoint-16000/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-16000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-16000/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
checkpoint-16000/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-16000/trainer_state.json ADDED
@@ -0,0 +1,981 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.8241581353422188,
5
+ "eval_steps": 500,
6
+ "global_step": 16000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.01,
13
+ "learning_rate": 4.9996726480206315e-05,
14
+ "loss": 0.7422,
15
+ "step": 100
16
+ },
17
+ {
18
+ "epoch": 0.01,
19
+ "learning_rate": 4.9986906778099784e-05,
20
+ "loss": 0.6673,
21
+ "step": 200
22
+ },
23
+ {
24
+ "epoch": 0.02,
25
+ "learning_rate": 4.9970543465279565e-05,
26
+ "loss": 0.6749,
27
+ "step": 300
28
+ },
29
+ {
30
+ "epoch": 0.02,
31
+ "learning_rate": 4.994764082699591e-05,
32
+ "loss": 0.6481,
33
+ "step": 400
34
+ },
35
+ {
36
+ "epoch": 0.03,
37
+ "learning_rate": 4.991820486102801e-05,
38
+ "loss": 0.6505,
39
+ "step": 500
40
+ },
41
+ {
42
+ "epoch": 0.03,
43
+ "learning_rate": 4.9882243276113245e-05,
44
+ "loss": 0.6708,
45
+ "step": 600
46
+ },
47
+ {
48
+ "epoch": 0.04,
49
+ "learning_rate": 4.983976548992841e-05,
50
+ "loss": 0.6596,
51
+ "step": 700
52
+ },
53
+ {
54
+ "epoch": 0.04,
55
+ "learning_rate": 4.9790782626623436e-05,
56
+ "loss": 0.6657,
57
+ "step": 800
58
+ },
59
+ {
60
+ "epoch": 0.05,
61
+ "learning_rate": 4.97353075139081e-05,
62
+ "loss": 0.659,
63
+ "step": 900
64
+ },
65
+ {
66
+ "epoch": 0.05,
67
+ "learning_rate": 4.9673354679692785e-05,
68
+ "loss": 0.6519,
69
+ "step": 1000
70
+ },
71
+ {
72
+ "epoch": 0.06,
73
+ "learning_rate": 4.960494034828381e-05,
74
+ "loss": 0.638,
75
+ "step": 1100
76
+ },
77
+ {
78
+ "epoch": 0.06,
79
+ "learning_rate": 4.9530082436134614e-05,
80
+ "loss": 0.629,
81
+ "step": 1200
82
+ },
83
+ {
84
+ "epoch": 0.07,
85
+ "learning_rate": 4.944880054715378e-05,
86
+ "loss": 0.6464,
87
+ "step": 1300
88
+ },
89
+ {
90
+ "epoch": 0.07,
91
+ "learning_rate": 4.9361115967571094e-05,
92
+ "loss": 0.642,
93
+ "step": 1400
94
+ },
95
+ {
96
+ "epoch": 0.08,
97
+ "learning_rate": 4.926705166036311e-05,
98
+ "loss": 0.6431,
99
+ "step": 1500
100
+ },
101
+ {
102
+ "epoch": 0.08,
103
+ "learning_rate": 4.916663225923953e-05,
104
+ "loss": 0.6465,
105
+ "step": 1600
106
+ },
107
+ {
108
+ "epoch": 0.09,
109
+ "learning_rate": 4.905988406219217e-05,
110
+ "loss": 0.6439,
111
+ "step": 1700
112
+ },
113
+ {
114
+ "epoch": 0.09,
115
+ "learning_rate": 4.8946835024607885e-05,
116
+ "loss": 0.652,
117
+ "step": 1800
118
+ },
119
+ {
120
+ "epoch": 0.1,
121
+ "learning_rate": 4.8827514751947656e-05,
122
+ "loss": 0.6376,
123
+ "step": 1900
124
+ },
125
+ {
126
+ "epoch": 0.1,
127
+ "learning_rate": 4.8701954491993426e-05,
128
+ "loss": 0.6357,
129
+ "step": 2000
130
+ },
131
+ {
132
+ "epoch": 0.11,
133
+ "learning_rate": 4.85701871266649e-05,
134
+ "loss": 0.6338,
135
+ "step": 2100
136
+ },
137
+ {
138
+ "epoch": 0.11,
139
+ "learning_rate": 4.8432247163408365e-05,
140
+ "loss": 0.6591,
141
+ "step": 2200
142
+ },
143
+ {
144
+ "epoch": 0.12,
145
+ "learning_rate": 4.8288170726159815e-05,
146
+ "loss": 0.621,
147
+ "step": 2300
148
+ },
149
+ {
150
+ "epoch": 0.12,
151
+ "learning_rate": 4.8137995545884794e-05,
152
+ "loss": 0.6337,
153
+ "step": 2400
154
+ },
155
+ {
156
+ "epoch": 0.13,
157
+ "learning_rate": 4.798176095069731e-05,
158
+ "loss": 0.637,
159
+ "step": 2500
160
+ },
161
+ {
162
+ "epoch": 0.13,
163
+ "learning_rate": 4.781950785556054e-05,
164
+ "loss": 0.6464,
165
+ "step": 2600
166
+ },
167
+ {
168
+ "epoch": 0.14,
169
+ "learning_rate": 4.7651278751571984e-05,
170
+ "loss": 0.6539,
171
+ "step": 2700
172
+ },
173
+ {
174
+ "epoch": 0.14,
175
+ "learning_rate": 4.747711769483576e-05,
176
+ "loss": 0.6233,
177
+ "step": 2800
178
+ },
179
+ {
180
+ "epoch": 0.15,
181
+ "learning_rate": 4.729707029492521e-05,
182
+ "loss": 0.6476,
183
+ "step": 2900
184
+ },
185
+ {
186
+ "epoch": 0.15,
187
+ "learning_rate": 4.711118370293852e-05,
188
+ "loss": 0.6302,
189
+ "step": 3000
190
+ },
191
+ {
192
+ "epoch": 0.16,
193
+ "learning_rate": 4.691950659915074e-05,
194
+ "loss": 0.632,
195
+ "step": 3100
196
+ },
197
+ {
198
+ "epoch": 0.16,
199
+ "learning_rate": 4.672208918026535e-05,
200
+ "loss": 0.6281,
201
+ "step": 3200
202
+ },
203
+ {
204
+ "epoch": 0.17,
205
+ "learning_rate": 4.6518983146268604e-05,
206
+ "loss": 0.6514,
207
+ "step": 3300
208
+ },
209
+ {
210
+ "epoch": 0.18,
211
+ "learning_rate": 4.63102416868903e-05,
212
+ "loss": 0.6254,
213
+ "step": 3400
214
+ },
215
+ {
216
+ "epoch": 0.18,
217
+ "learning_rate": 4.609591946767437e-05,
218
+ "loss": 0.6412,
219
+ "step": 3500
220
+ },
221
+ {
222
+ "epoch": 0.19,
223
+ "learning_rate": 4.587607261566294e-05,
224
+ "loss": 0.6647,
225
+ "step": 3600
226
+ },
227
+ {
228
+ "epoch": 0.19,
229
+ "learning_rate": 4.565075870469777e-05,
230
+ "loss": 0.644,
231
+ "step": 3700
232
+ },
233
+ {
234
+ "epoch": 0.2,
235
+ "learning_rate": 4.542003674034263e-05,
236
+ "loss": 0.6328,
237
+ "step": 3800
238
+ },
239
+ {
240
+ "epoch": 0.2,
241
+ "learning_rate": 4.5183967144430904e-05,
242
+ "loss": 0.6454,
243
+ "step": 3900
244
+ },
245
+ {
246
+ "epoch": 0.21,
247
+ "learning_rate": 4.4942611739242166e-05,
248
+ "loss": 0.6619,
249
+ "step": 4000
250
+ },
251
+ {
252
+ "epoch": 0.21,
253
+ "learning_rate": 4.469603373131214e-05,
254
+ "loss": 0.6326,
255
+ "step": 4100
256
+ },
257
+ {
258
+ "epoch": 0.22,
259
+ "learning_rate": 4.444429769487997e-05,
260
+ "loss": 0.6373,
261
+ "step": 4200
262
+ },
263
+ {
264
+ "epoch": 0.22,
265
+ "learning_rate": 4.4187469554977503e-05,
266
+ "loss": 0.6375,
267
+ "step": 4300
268
+ },
269
+ {
270
+ "epoch": 0.23,
271
+ "learning_rate": 4.392561657016472e-05,
272
+ "loss": 0.6181,
273
+ "step": 4400
274
+ },
275
+ {
276
+ "epoch": 0.23,
277
+ "learning_rate": 4.3658807314915915e-05,
278
+ "loss": 0.6415,
279
+ "step": 4500
280
+ },
281
+ {
282
+ "epoch": 0.24,
283
+ "learning_rate": 4.338711166166135e-05,
284
+ "loss": 0.6235,
285
+ "step": 4600
286
+ },
287
+ {
288
+ "epoch": 0.24,
289
+ "learning_rate": 4.3110600762488915e-05,
290
+ "loss": 0.643,
291
+ "step": 4700
292
+ },
293
+ {
294
+ "epoch": 0.25,
295
+ "learning_rate": 4.282934703051076e-05,
296
+ "loss": 0.6488,
297
+ "step": 4800
298
+ },
299
+ {
300
+ "epoch": 0.25,
301
+ "learning_rate": 4.2543424120899556e-05,
302
+ "loss": 0.6536,
303
+ "step": 4900
304
+ },
305
+ {
306
+ "epoch": 0.26,
307
+ "learning_rate": 4.2252906911599646e-05,
308
+ "loss": 0.6396,
309
+ "step": 5000
310
+ },
311
+ {
312
+ "epoch": 0.26,
313
+ "learning_rate": 4.195787148371782e-05,
314
+ "loss": 0.6456,
315
+ "step": 5100
316
+ },
317
+ {
318
+ "epoch": 0.27,
319
+ "learning_rate": 4.165839510159914e-05,
320
+ "loss": 0.6213,
321
+ "step": 5200
322
+ },
323
+ {
324
+ "epoch": 0.27,
325
+ "learning_rate": 4.1354556192592766e-05,
326
+ "loss": 0.6408,
327
+ "step": 5300
328
+ },
329
+ {
330
+ "epoch": 0.28,
331
+ "learning_rate": 4.1046434326513305e-05,
332
+ "loss": 0.6394,
333
+ "step": 5400
334
+ },
335
+ {
336
+ "epoch": 0.28,
337
+ "learning_rate": 4.073411019480297e-05,
338
+ "loss": 0.6338,
339
+ "step": 5500
340
+ },
341
+ {
342
+ "epoch": 0.29,
343
+ "learning_rate": 4.041766558939991e-05,
344
+ "loss": 0.6271,
345
+ "step": 5600
346
+ },
347
+ {
348
+ "epoch": 0.29,
349
+ "learning_rate": 4.009718338131851e-05,
350
+ "loss": 0.6269,
351
+ "step": 5700
352
+ },
353
+ {
354
+ "epoch": 0.3,
355
+ "learning_rate": 3.97727474989469e-05,
356
+ "loss": 0.6465,
357
+ "step": 5800
358
+ },
359
+ {
360
+ "epoch": 0.3,
361
+ "learning_rate": 3.944444290606768e-05,
362
+ "loss": 0.6372,
363
+ "step": 5900
364
+ },
365
+ {
366
+ "epoch": 0.31,
367
+ "learning_rate": 3.911235557960752e-05,
368
+ "loss": 0.6399,
369
+ "step": 6000
370
+ },
371
+ {
372
+ "epoch": 0.31,
373
+ "learning_rate": 3.877657248712131e-05,
374
+ "loss": 0.62,
375
+ "step": 6100
376
+ },
377
+ {
378
+ "epoch": 0.32,
379
+ "learning_rate": 3.844059304094324e-05,
380
+ "loss": 0.6468,
381
+ "step": 6200
382
+ },
383
+ {
384
+ "epoch": 0.32,
385
+ "learning_rate": 3.8097717913954655e-05,
386
+ "loss": 0.6362,
387
+ "step": 6300
388
+ },
389
+ {
390
+ "epoch": 0.33,
391
+ "learning_rate": 3.775141273585859e-05,
392
+ "loss": 0.6302,
393
+ "step": 6400
394
+ },
395
+ {
396
+ "epoch": 0.33,
397
+ "learning_rate": 3.740176819760346e-05,
398
+ "loss": 0.6334,
399
+ "step": 6500
400
+ },
401
+ {
402
+ "epoch": 0.34,
403
+ "learning_rate": 3.704887586465459e-05,
404
+ "loss": 0.6507,
405
+ "step": 6600
406
+ },
407
+ {
408
+ "epoch": 0.35,
409
+ "learning_rate": 3.669282815301495e-05,
410
+ "loss": 0.6403,
411
+ "step": 6700
412
+ },
413
+ {
414
+ "epoch": 0.35,
415
+ "learning_rate": 3.6333718305023066e-05,
416
+ "loss": 0.6407,
417
+ "step": 6800
418
+ },
419
+ {
420
+ "epoch": 0.36,
421
+ "learning_rate": 3.597164036493457e-05,
422
+ "loss": 0.6477,
423
+ "step": 6900
424
+ },
425
+ {
426
+ "epoch": 0.36,
427
+ "learning_rate": 3.560668915429376e-05,
428
+ "loss": 0.656,
429
+ "step": 7000
430
+ },
431
+ {
432
+ "epoch": 0.37,
433
+ "learning_rate": 3.5238960247101584e-05,
434
+ "loss": 0.6252,
435
+ "step": 7100
436
+ },
437
+ {
438
+ "epoch": 0.37,
439
+ "learning_rate": 3.486854994478655e-05,
440
+ "loss": 0.6345,
441
+ "step": 7200
442
+ },
443
+ {
444
+ "epoch": 0.38,
445
+ "learning_rate": 3.4499297670475796e-05,
446
+ "loss": 0.6355,
447
+ "step": 7300
448
+ },
449
+ {
450
+ "epoch": 0.38,
451
+ "learning_rate": 3.412384064706181e-05,
452
+ "loss": 0.6468,
453
+ "step": 7400
454
+ },
455
+ {
456
+ "epoch": 0.39,
457
+ "learning_rate": 3.374599425781161e-05,
458
+ "loss": 0.6356,
459
+ "step": 7500
460
+ },
461
+ {
462
+ "epoch": 0.39,
463
+ "learning_rate": 3.336585745373593e-05,
464
+ "loss": 0.6335,
465
+ "step": 7600
466
+ },
467
+ {
468
+ "epoch": 0.4,
469
+ "learning_rate": 3.2983529785662964e-05,
470
+ "loss": 0.6092,
471
+ "step": 7700
472
+ },
473
+ {
474
+ "epoch": 0.4,
475
+ "learning_rate": 3.2599111378167855e-05,
476
+ "loss": 0.6337,
477
+ "step": 7800
478
+ },
479
+ {
480
+ "epoch": 0.41,
481
+ "learning_rate": 3.221657650708416e-05,
482
+ "loss": 0.6455,
483
+ "step": 7900
484
+ },
485
+ {
486
+ "epoch": 0.41,
487
+ "learning_rate": 3.182829754439824e-05,
488
+ "loss": 0.627,
489
+ "step": 8000
490
+ },
491
+ {
492
+ "epoch": 0.42,
493
+ "learning_rate": 3.143823037633881e-05,
494
+ "loss": 0.6272,
495
+ "step": 8100
496
+ },
497
+ {
498
+ "epoch": 0.42,
499
+ "learning_rate": 3.104647715431351e-05,
500
+ "loss": 0.6337,
501
+ "step": 8200
502
+ },
503
+ {
504
+ "epoch": 0.43,
505
+ "learning_rate": 3.0653140471276476e-05,
506
+ "loss": 0.6562,
507
+ "step": 8300
508
+ },
509
+ {
510
+ "epoch": 0.43,
511
+ "learning_rate": 3.0258323334861104e-05,
512
+ "loss": 0.6184,
513
+ "step": 8400
514
+ },
515
+ {
516
+ "epoch": 0.44,
517
+ "learning_rate": 2.9862129140404272e-05,
518
+ "loss": 0.6175,
519
+ "step": 8500
520
+ },
521
+ {
522
+ "epoch": 0.44,
523
+ "learning_rate": 2.9464661643868984e-05,
524
+ "loss": 0.6489,
525
+ "step": 8600
526
+ },
527
+ {
528
+ "epoch": 0.45,
529
+ "learning_rate": 2.9066024934672632e-05,
530
+ "loss": 0.6423,
531
+ "step": 8700
532
+ },
533
+ {
534
+ "epoch": 0.45,
535
+ "learning_rate": 2.866632340842786e-05,
536
+ "loss": 0.6127,
537
+ "step": 8800
538
+ },
539
+ {
540
+ "epoch": 0.46,
541
+ "learning_rate": 2.8265661739603277e-05,
542
+ "loss": 0.6247,
543
+ "step": 8900
544
+ },
545
+ {
546
+ "epoch": 0.46,
547
+ "learning_rate": 2.7864144854111168e-05,
548
+ "loss": 0.6307,
549
+ "step": 9000
550
+ },
551
+ {
552
+ "epoch": 0.47,
553
+ "learning_rate": 2.7461877901829303e-05,
554
+ "loss": 0.6231,
555
+ "step": 9100
556
+ },
557
+ {
558
+ "epoch": 0.47,
559
+ "learning_rate": 2.7058966229064143e-05,
560
+ "loss": 0.6304,
561
+ "step": 9200
562
+ },
563
+ {
564
+ "epoch": 0.48,
565
+ "learning_rate": 2.6655515350962545e-05,
566
+ "loss": 0.6408,
567
+ "step": 9300
568
+ },
569
+ {
570
+ "epoch": 0.48,
571
+ "learning_rate": 2.625163092387934e-05,
572
+ "loss": 0.6198,
573
+ "step": 9400
574
+ },
575
+ {
576
+ "epoch": 0.49,
577
+ "learning_rate": 2.584741871770784e-05,
578
+ "loss": 0.6378,
579
+ "step": 9500
580
+ },
581
+ {
582
+ "epoch": 0.49,
583
+ "learning_rate": 2.5442984588180657e-05,
584
+ "loss": 0.6303,
585
+ "step": 9600
586
+ },
587
+ {
588
+ "epoch": 0.5,
589
+ "learning_rate": 2.5038434449148057e-05,
590
+ "loss": 0.6297,
591
+ "step": 9700
592
+ },
593
+ {
594
+ "epoch": 0.5,
595
+ "learning_rate": 2.463387424484106e-05,
596
+ "loss": 0.6258,
597
+ "step": 9800
598
+ },
599
+ {
600
+ "epoch": 0.51,
601
+ "learning_rate": 2.4229409922126572e-05,
602
+ "loss": 0.6349,
603
+ "step": 9900
604
+ },
605
+ {
606
+ "epoch": 0.52,
607
+ "learning_rate": 2.382514740276191e-05,
608
+ "loss": 0.6259,
609
+ "step": 10000
610
+ },
611
+ {
612
+ "epoch": 0.52,
613
+ "learning_rate": 2.3421192555655785e-05,
614
+ "loss": 0.6067,
615
+ "step": 10100
616
+ },
617
+ {
618
+ "epoch": 0.53,
619
+ "learning_rate": 2.3017651169143217e-05,
620
+ "loss": 0.6316,
621
+ "step": 10200
622
+ },
623
+ {
624
+ "epoch": 0.53,
625
+ "learning_rate": 2.2614628923281524e-05,
626
+ "loss": 0.6402,
627
+ "step": 10300
628
+ },
629
+ {
630
+ "epoch": 0.54,
631
+ "learning_rate": 2.2212231362174614e-05,
632
+ "loss": 0.6211,
633
+ "step": 10400
634
+ },
635
+ {
636
+ "epoch": 0.54,
637
+ "learning_rate": 2.1810563866332996e-05,
638
+ "loss": 0.6315,
639
+ "step": 10500
640
+ },
641
+ {
642
+ "epoch": 0.55,
643
+ "learning_rate": 2.1409731625076533e-05,
644
+ "loss": 0.6206,
645
+ "step": 10600
646
+ },
647
+ {
648
+ "epoch": 0.55,
649
+ "learning_rate": 2.1009839608987253e-05,
650
+ "loss": 0.6201,
651
+ "step": 10700
652
+ },
653
+ {
654
+ "epoch": 0.56,
655
+ "learning_rate": 2.0610992542419582e-05,
656
+ "loss": 0.6489,
657
+ "step": 10800
658
+ },
659
+ {
660
+ "epoch": 0.56,
661
+ "learning_rate": 2.0213294876074866e-05,
662
+ "loss": 0.6381,
663
+ "step": 10900
664
+ },
665
+ {
666
+ "epoch": 0.57,
667
+ "learning_rate": 1.9816850759647733e-05,
668
+ "loss": 0.6321,
669
+ "step": 11000
670
+ },
671
+ {
672
+ "epoch": 0.57,
673
+ "learning_rate": 1.9421764014551165e-05,
674
+ "loss": 0.6222,
675
+ "step": 11100
676
+ },
677
+ {
678
+ "epoch": 0.58,
679
+ "learning_rate": 1.902813810672756e-05,
680
+ "loss": 0.6275,
681
+ "step": 11200
682
+ },
683
+ {
684
+ "epoch": 0.58,
685
+ "learning_rate": 1.8636076119553e-05,
686
+ "loss": 0.6281,
687
+ "step": 11300
688
+ },
689
+ {
690
+ "epoch": 0.59,
691
+ "learning_rate": 1.824568072684148e-05,
692
+ "loss": 0.6345,
693
+ "step": 11400
694
+ },
695
+ {
696
+ "epoch": 0.59,
697
+ "learning_rate": 1.7857054165956648e-05,
698
+ "loss": 0.621,
699
+ "step": 11500
700
+ },
701
+ {
702
+ "epoch": 0.6,
703
+ "learning_rate": 1.7470298211037665e-05,
704
+ "loss": 0.5951,
705
+ "step": 11600
706
+ },
707
+ {
708
+ "epoch": 0.6,
709
+ "learning_rate": 1.7085514146346415e-05,
710
+ "loss": 0.6293,
711
+ "step": 11700
712
+ },
713
+ {
714
+ "epoch": 0.61,
715
+ "learning_rate": 1.6702802739743083e-05,
716
+ "loss": 0.626,
717
+ "step": 11800
718
+ },
719
+ {
720
+ "epoch": 0.61,
721
+ "learning_rate": 1.6322264216296822e-05,
722
+ "loss": 0.6376,
723
+ "step": 11900
724
+ },
725
+ {
726
+ "epoch": 0.62,
727
+ "learning_rate": 1.594399823203876e-05,
728
+ "loss": 0.643,
729
+ "step": 12000
730
+ },
731
+ {
732
+ "epoch": 0.62,
733
+ "learning_rate": 1.5568103847863835e-05,
734
+ "loss": 0.6274,
735
+ "step": 12100
736
+ },
737
+ {
738
+ "epoch": 0.63,
739
+ "learning_rate": 1.5194679503588585e-05,
740
+ "loss": 0.6421,
741
+ "step": 12200
742
+ },
743
+ {
744
+ "epoch": 0.63,
745
+ "learning_rate": 1.4823822992171621e-05,
746
+ "loss": 0.6202,
747
+ "step": 12300
748
+ },
749
+ {
750
+ "epoch": 0.64,
751
+ "learning_rate": 1.445563143410339e-05,
752
+ "loss": 0.6156,
753
+ "step": 12400
754
+ },
755
+ {
756
+ "epoch": 0.64,
757
+ "learning_rate": 1.4090201251972163e-05,
758
+ "loss": 0.6159,
759
+ "step": 12500
760
+ },
761
+ {
762
+ "epoch": 0.65,
763
+ "learning_rate": 1.3727628145212673e-05,
764
+ "loss": 0.6285,
765
+ "step": 12600
766
+ },
767
+ {
768
+ "epoch": 0.65,
769
+ "learning_rate": 1.3368007065044269e-05,
770
+ "loss": 0.6356,
771
+ "step": 12700
772
+ },
773
+ {
774
+ "epoch": 0.66,
775
+ "learning_rate": 1.3011432189604872e-05,
776
+ "loss": 0.6285,
777
+ "step": 12800
778
+ },
779
+ {
780
+ "epoch": 0.66,
781
+ "learning_rate": 1.2657996899287505e-05,
782
+ "loss": 0.6319,
783
+ "step": 12900
784
+ },
785
+ {
786
+ "epoch": 0.67,
787
+ "learning_rate": 1.2307793752285665e-05,
788
+ "loss": 0.6166,
789
+ "step": 13000
790
+ },
791
+ {
792
+ "epoch": 0.67,
793
+ "learning_rate": 1.1960914460354017e-05,
794
+ "loss": 0.6316,
795
+ "step": 13100
796
+ },
797
+ {
798
+ "epoch": 0.68,
799
+ "learning_rate": 1.1617449864790823e-05,
800
+ "loss": 0.6124,
801
+ "step": 13200
802
+ },
803
+ {
804
+ "epoch": 0.69,
805
+ "learning_rate": 1.1277489912648251e-05,
806
+ "loss": 0.6318,
807
+ "step": 13300
808
+ },
809
+ {
810
+ "epoch": 0.69,
811
+ "learning_rate": 1.0944469217262731e-05,
812
+ "loss": 0.6409,
813
+ "step": 13400
814
+ },
815
+ {
816
+ "epoch": 0.7,
817
+ "learning_rate": 1.0615056158497555e-05,
818
+ "loss": 0.6244,
819
+ "step": 13500
820
+ },
821
+ {
822
+ "epoch": 0.7,
823
+ "learning_rate": 1.0286064299421735e-05,
824
+ "loss": 0.6529,
825
+ "step": 13600
826
+ },
827
+ {
828
+ "epoch": 0.71,
829
+ "learning_rate": 9.964157780320574e-06,
830
+ "loss": 0.6174,
831
+ "step": 13700
832
+ },
833
+ {
834
+ "epoch": 0.71,
835
+ "learning_rate": 9.642917883925478e-06,
836
+ "loss": 0.6359,
837
+ "step": 13800
838
+ },
839
+ {
840
+ "epoch": 0.72,
841
+ "learning_rate": 9.325699724512796e-06,
842
+ "loss": 0.6289,
843
+ "step": 13900
844
+ },
845
+ {
846
+ "epoch": 0.72,
847
+ "learning_rate": 9.012586375676443e-06,
848
+ "loss": 0.6221,
849
+ "step": 14000
850
+ },
851
+ {
852
+ "epoch": 0.73,
853
+ "learning_rate": 8.70365983603603e-06,
854
+ "loss": 0.6368,
855
+ "step": 14100
856
+ },
857
+ {
858
+ "epoch": 0.73,
859
+ "learning_rate": 8.399001007762921e-06,
860
+ "loss": 0.6225,
861
+ "step": 14200
862
+ },
863
+ {
864
+ "epoch": 0.74,
865
+ "learning_rate": 8.098689675393509e-06,
866
+ "loss": 0.6258,
867
+ "step": 14300
868
+ },
869
+ {
870
+ "epoch": 0.74,
871
+ "learning_rate": 7.802804484935048e-06,
872
+ "loss": 0.6212,
873
+ "step": 14400
874
+ },
875
+ {
876
+ "epoch": 0.75,
877
+ "learning_rate": 7.511422923269759e-06,
878
+ "loss": 0.6354,
879
+ "step": 14500
880
+ },
881
+ {
882
+ "epoch": 0.75,
883
+ "learning_rate": 7.224621297862396e-06,
884
+ "loss": 0.6396,
885
+ "step": 14600
886
+ },
887
+ {
888
+ "epoch": 0.76,
889
+ "learning_rate": 6.9424747167767785e-06,
890
+ "loss": 0.6066,
891
+ "step": 14700
892
+ },
893
+ {
894
+ "epoch": 0.76,
895
+ "learning_rate": 6.665057069006344e-06,
896
+ "loss": 0.6273,
897
+ "step": 14800
898
+ },
899
+ {
900
+ "epoch": 0.77,
901
+ "learning_rate": 6.39244100512397e-06,
902
+ "loss": 0.6264,
903
+ "step": 14900
904
+ },
905
+ {
906
+ "epoch": 0.77,
907
+ "learning_rate": 6.124697918256153e-06,
908
+ "loss": 0.6335,
909
+ "step": 15000
910
+ },
911
+ {
912
+ "epoch": 0.78,
913
+ "learning_rate": 5.8618979253864585e-06,
914
+ "loss": 0.6205,
915
+ "step": 15100
916
+ },
917
+ {
918
+ "epoch": 0.78,
919
+ "learning_rate": 5.604109848993158e-06,
920
+ "loss": 0.6349,
921
+ "step": 15200
922
+ },
923
+ {
924
+ "epoch": 0.79,
925
+ "learning_rate": 5.35140119902591e-06,
926
+ "loss": 0.6134,
927
+ "step": 15300
928
+ },
929
+ {
930
+ "epoch": 0.79,
931
+ "learning_rate": 5.103838155226118e-06,
932
+ "loss": 0.6275,
933
+ "step": 15400
934
+ },
935
+ {
936
+ "epoch": 0.8,
937
+ "learning_rate": 4.861485549795722e-06,
938
+ "loss": 0.6228,
939
+ "step": 15500
940
+ },
941
+ {
942
+ "epoch": 0.8,
943
+ "learning_rate": 4.6244068504187835e-06,
944
+ "loss": 0.6288,
945
+ "step": 15600
946
+ },
947
+ {
948
+ "epoch": 0.81,
949
+ "learning_rate": 4.392664143640512e-06,
950
+ "loss": 0.625,
951
+ "step": 15700
952
+ },
953
+ {
954
+ "epoch": 0.81,
955
+ "learning_rate": 4.166318118607923e-06,
956
+ "loss": 0.6322,
957
+ "step": 15800
958
+ },
959
+ {
960
+ "epoch": 0.82,
961
+ "learning_rate": 3.945428051176472e-06,
962
+ "loss": 0.6477,
963
+ "step": 15900
964
+ },
965
+ {
966
+ "epoch": 0.82,
967
+ "learning_rate": 3.7300517883868015e-06,
968
+ "loss": 0.6406,
969
+ "step": 16000
970
+ }
971
+ ],
972
+ "logging_steps": 100,
973
+ "max_steps": 19413,
974
+ "num_input_tokens_seen": 0,
975
+ "num_train_epochs": 1,
976
+ "save_steps": 2000,
977
+ "total_flos": 3.6293215114795155e+19,
978
+ "train_batch_size": 2,
979
+ "trial_name": null,
980
+ "trial_params": null
981
+ }
checkpoint-16000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d478a4b43de7b19064a77e4740036edd604501f17a30e1008e6ef525fefdc95e
3
+ size 4856