bxw315-umd commited on
Commit
a96db1c
·
verified ·
1 Parent(s): dfbb238

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Qwen/Qwen2-VL-2B-Instruct
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.15.2
adapter_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "Qwen/Qwen2-VL-2B-Instruct",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": null,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 16,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.05,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "r": 32,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": "model.layers.[\\d]+.(mlp|cross_attn|self_attn).(up|down|gate|q|k|v|o)_proj",
27
+ "task_type": "CAUSAL_LM",
28
+ "trainable_token_indices": null,
29
+ "use_dora": false,
30
+ "use_rslora": false
31
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1611f7e57b0e71d4fefa595d0bdf8acb826c61cfbefd87b417b3b184ca677e13
3
+ size 147770496
added_tokens.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|box_end|>": 151649,
3
+ "<|box_start|>": 151648,
4
+ "<|endoftext|>": 151643,
5
+ "<|im_end|>": 151645,
6
+ "<|im_start|>": 151644,
7
+ "<|image_pad|>": 151655,
8
+ "<|object_ref_end|>": 151647,
9
+ "<|object_ref_start|>": 151646,
10
+ "<|quad_end|>": 151651,
11
+ "<|quad_start|>": 151650,
12
+ "<|video_pad|>": 151656,
13
+ "<|vision_end|>": 151653,
14
+ "<|vision_pad|>": 151654,
15
+ "<|vision_start|>": 151652
16
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d83ebe95f3b4704d826ceb22f2a818928b4e2bf5ec4c5cc42b36467ce5a51506
3
+ size 75471860
rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f468eb3bda29235a22e50a1d4a93f0e73d6e9156f3c92e06cc5b7020cd46bbb
3
+ size 15024
rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9742577ecbe5367851a3be372592dbb9dbb3b2dabf655c60e5813491c5f50d9
3
+ size 15024
rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35cd17226cf768d6137d8b72e50c382bb6f3d514c5a45a8e5a0b33ef7e9aa7a6
3
+ size 15024
rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14c110ee99d870159422e4b5c03e9aab5e722d210c9c33de767b837376711e45
3
+ size 15024
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0738320863223ebbb3380cfe5a102839731d45856d40da34875ee4eb29904cd
3
+ size 1064
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88a3a6fcb80132f76da8aa40cdc3fccd7e5d8468ef15421f5b0c2715e85217d2
3
+ size 11420538
tokenizer_config.json ADDED
@@ -0,0 +1,145 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "151643": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "151644": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "151645": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "151646": {
29
+ "content": "<|object_ref_start|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "151647": {
37
+ "content": "<|object_ref_end|>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "151648": {
45
+ "content": "<|box_start|>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "151649": {
53
+ "content": "<|box_end|>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "151650": {
61
+ "content": "<|quad_start|>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "151651": {
69
+ "content": "<|quad_end|>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "151652": {
77
+ "content": "<|vision_start|>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "151653": {
85
+ "content": "<|vision_end|>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "151654": {
93
+ "content": "<|vision_pad|>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "151655": {
101
+ "content": "<|image_pad|>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "151656": {
109
+ "content": "<|video_pad|>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ }
116
+ },
117
+ "additional_special_tokens": [
118
+ "<|im_start|>",
119
+ "<|im_end|>",
120
+ "<|object_ref_start|>",
121
+ "<|object_ref_end|>",
122
+ "<|box_start|>",
123
+ "<|box_end|>",
124
+ "<|quad_start|>",
125
+ "<|quad_end|>",
126
+ "<|vision_start|>",
127
+ "<|vision_end|>",
128
+ "<|vision_pad|>",
129
+ "<|image_pad|>",
130
+ "<|video_pad|>"
131
+ ],
132
+ "bos_token": null,
133
+ "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
134
+ "clean_up_tokenization_spaces": false,
135
+ "eos_token": "<|im_end|>",
136
+ "errors": "replace",
137
+ "extra_special_tokens": {},
138
+ "model_max_length": 32768,
139
+ "pad_token": "<|endoftext|>",
140
+ "padding_side": "left",
141
+ "processor_class": "Qwen2VLProcessor",
142
+ "split_special_tokens": false,
143
+ "tokenizer_class": "Qwen2Tokenizer",
144
+ "unk_token": null
145
+ }
trainer_state.json ADDED
@@ -0,0 +1,1133 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 157,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.006369426751592357,
14
+ "grad_norm": 0.4737717807292938,
15
+ "learning_rate": 0.0,
16
+ "loss": 2.4387,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.012738853503184714,
21
+ "grad_norm": 0.4696364402770996,
22
+ "learning_rate": 1.3333333333333333e-05,
23
+ "loss": 2.4216,
24
+ "step": 2
25
+ },
26
+ {
27
+ "epoch": 0.01910828025477707,
28
+ "grad_norm": 0.46825963258743286,
29
+ "learning_rate": 2.6666666666666667e-05,
30
+ "loss": 2.4473,
31
+ "step": 3
32
+ },
33
+ {
34
+ "epoch": 0.025477707006369428,
35
+ "grad_norm": 0.4676540195941925,
36
+ "learning_rate": 4e-05,
37
+ "loss": 2.4151,
38
+ "step": 4
39
+ },
40
+ {
41
+ "epoch": 0.03184713375796178,
42
+ "grad_norm": 0.4555565416812897,
43
+ "learning_rate": 5.333333333333333e-05,
44
+ "loss": 2.3768,
45
+ "step": 5
46
+ },
47
+ {
48
+ "epoch": 0.03821656050955414,
49
+ "grad_norm": 0.4768979549407959,
50
+ "learning_rate": 6.666666666666667e-05,
51
+ "loss": 2.3961,
52
+ "step": 6
53
+ },
54
+ {
55
+ "epoch": 0.044585987261146494,
56
+ "grad_norm": 0.4434276521205902,
57
+ "learning_rate": 8e-05,
58
+ "loss": 2.3393,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 0.050955414012738856,
63
+ "grad_norm": 0.41826605796813965,
64
+ "learning_rate": 9.333333333333334e-05,
65
+ "loss": 2.2803,
66
+ "step": 8
67
+ },
68
+ {
69
+ "epoch": 0.05732484076433121,
70
+ "grad_norm": 0.38292792439460754,
71
+ "learning_rate": 0.00010666666666666667,
72
+ "loss": 2.2154,
73
+ "step": 9
74
+ },
75
+ {
76
+ "epoch": 0.06369426751592357,
77
+ "grad_norm": 0.35984838008880615,
78
+ "learning_rate": 0.00012,
79
+ "loss": 2.1313,
80
+ "step": 10
81
+ },
82
+ {
83
+ "epoch": 0.07006369426751592,
84
+ "grad_norm": 0.36338669061660767,
85
+ "learning_rate": 0.00013333333333333334,
86
+ "loss": 2.0336,
87
+ "step": 11
88
+ },
89
+ {
90
+ "epoch": 0.07643312101910828,
91
+ "grad_norm": 0.32774657011032104,
92
+ "learning_rate": 0.00014666666666666666,
93
+ "loss": 1.9673,
94
+ "step": 12
95
+ },
96
+ {
97
+ "epoch": 0.08280254777070063,
98
+ "grad_norm": 0.30120769143104553,
99
+ "learning_rate": 0.00016,
100
+ "loss": 1.9096,
101
+ "step": 13
102
+ },
103
+ {
104
+ "epoch": 0.08917197452229299,
105
+ "grad_norm": 0.3341425359249115,
106
+ "learning_rate": 0.00017333333333333334,
107
+ "loss": 1.8116,
108
+ "step": 14
109
+ },
110
+ {
111
+ "epoch": 0.09554140127388536,
112
+ "grad_norm": 0.3417530357837677,
113
+ "learning_rate": 0.0001866666666666667,
114
+ "loss": 1.7509,
115
+ "step": 15
116
+ },
117
+ {
118
+ "epoch": 0.10191082802547771,
119
+ "grad_norm": 0.3540063798427582,
120
+ "learning_rate": 0.0002,
121
+ "loss": 1.6482,
122
+ "step": 16
123
+ },
124
+ {
125
+ "epoch": 0.10828025477707007,
126
+ "grad_norm": 0.46677955985069275,
127
+ "learning_rate": 0.00019997552766852432,
128
+ "loss": 1.5641,
129
+ "step": 17
130
+ },
131
+ {
132
+ "epoch": 0.11464968152866242,
133
+ "grad_norm": 0.4193592369556427,
134
+ "learning_rate": 0.00019990212265199738,
135
+ "loss": 1.5238,
136
+ "step": 18
137
+ },
138
+ {
139
+ "epoch": 0.12101910828025478,
140
+ "grad_norm": 0.3629758358001709,
141
+ "learning_rate": 0.00019977982087825713,
142
+ "loss": 1.393,
143
+ "step": 19
144
+ },
145
+ {
146
+ "epoch": 0.12738853503184713,
147
+ "grad_norm": 0.37026986479759216,
148
+ "learning_rate": 0.00019960868220749448,
149
+ "loss": 1.3252,
150
+ "step": 20
151
+ },
152
+ {
153
+ "epoch": 0.1337579617834395,
154
+ "grad_norm": 0.44961684942245483,
155
+ "learning_rate": 0.00019938879040295508,
156
+ "loss": 1.2826,
157
+ "step": 21
158
+ },
159
+ {
160
+ "epoch": 0.14012738853503184,
161
+ "grad_norm": 0.31476661562919617,
162
+ "learning_rate": 0.00019912025308994148,
163
+ "loss": 1.2013,
164
+ "step": 22
165
+ },
166
+ {
167
+ "epoch": 0.1464968152866242,
168
+ "grad_norm": 0.25825104117393494,
169
+ "learning_rate": 0.0001988032017031364,
170
+ "loss": 1.1777,
171
+ "step": 23
172
+ },
173
+ {
174
+ "epoch": 0.15286624203821655,
175
+ "grad_norm": 0.230068638920784,
176
+ "learning_rate": 0.00019843779142227256,
177
+ "loss": 1.1182,
178
+ "step": 24
179
+ },
180
+ {
181
+ "epoch": 0.1592356687898089,
182
+ "grad_norm": 0.21921853721141815,
183
+ "learning_rate": 0.0001980242010961803,
184
+ "loss": 1.103,
185
+ "step": 25
186
+ },
187
+ {
188
+ "epoch": 0.16560509554140126,
189
+ "grad_norm": 0.2058652639389038,
190
+ "learning_rate": 0.0001975626331552507,
191
+ "loss": 1.1107,
192
+ "step": 26
193
+ },
194
+ {
195
+ "epoch": 0.17197452229299362,
196
+ "grad_norm": 0.19609420001506805,
197
+ "learning_rate": 0.00019705331351235674,
198
+ "loss": 1.0931,
199
+ "step": 27
200
+ },
201
+ {
202
+ "epoch": 0.17834394904458598,
203
+ "grad_norm": 0.20052394270896912,
204
+ "learning_rate": 0.00019649649145228102,
205
+ "loss": 1.0617,
206
+ "step": 28
207
+ },
208
+ {
209
+ "epoch": 0.18471337579617833,
210
+ "grad_norm": 0.20906223356723785,
211
+ "learning_rate": 0.00019589243950970402,
212
+ "loss": 1.0567,
213
+ "step": 29
214
+ },
215
+ {
216
+ "epoch": 0.1910828025477707,
217
+ "grad_norm": 0.2615731656551361,
218
+ "learning_rate": 0.00019524145333581317,
219
+ "loss": 1.0118,
220
+ "step": 30
221
+ },
222
+ {
223
+ "epoch": 0.19745222929936307,
224
+ "grad_norm": 0.29617559909820557,
225
+ "learning_rate": 0.00019454385155359702,
226
+ "loss": 1.0332,
227
+ "step": 31
228
+ },
229
+ {
230
+ "epoch": 0.20382165605095542,
231
+ "grad_norm": 0.15338869392871857,
232
+ "learning_rate": 0.00019379997560189675,
233
+ "loss": 1.0087,
234
+ "step": 32
235
+ },
236
+ {
237
+ "epoch": 0.21019108280254778,
238
+ "grad_norm": 0.15214228630065918,
239
+ "learning_rate": 0.00019301018956828964,
240
+ "loss": 0.9625,
241
+ "step": 33
242
+ },
243
+ {
244
+ "epoch": 0.21656050955414013,
245
+ "grad_norm": 0.14021392166614532,
246
+ "learning_rate": 0.00019217488001088784,
247
+ "loss": 0.9786,
248
+ "step": 34
249
+ },
250
+ {
251
+ "epoch": 0.2229299363057325,
252
+ "grad_norm": 0.13724100589752197,
253
+ "learning_rate": 0.00019129445576913888,
254
+ "loss": 0.9617,
255
+ "step": 35
256
+ },
257
+ {
258
+ "epoch": 0.22929936305732485,
259
+ "grad_norm": 0.14516188204288483,
260
+ "learning_rate": 0.0001903693477637204,
261
+ "loss": 0.9436,
262
+ "step": 36
263
+ },
264
+ {
265
+ "epoch": 0.2356687898089172,
266
+ "grad_norm": 0.16043990850448608,
267
+ "learning_rate": 0.00018940000878562758,
268
+ "loss": 0.9361,
269
+ "step": 37
270
+ },
271
+ {
272
+ "epoch": 0.24203821656050956,
273
+ "grad_norm": 0.16804192960262299,
274
+ "learning_rate": 0.0001883869132745561,
275
+ "loss": 0.9318,
276
+ "step": 38
277
+ },
278
+ {
279
+ "epoch": 0.2484076433121019,
280
+ "grad_norm": 0.1397908627986908,
281
+ "learning_rate": 0.00018733055708668926,
282
+ "loss": 0.9509,
283
+ "step": 39
284
+ },
285
+ {
286
+ "epoch": 0.25477707006369427,
287
+ "grad_norm": 0.1381651759147644,
288
+ "learning_rate": 0.00018623145725200278,
289
+ "loss": 0.9048,
290
+ "step": 40
291
+ },
292
+ {
293
+ "epoch": 0.2611464968152866,
294
+ "grad_norm": 0.14483928680419922,
295
+ "learning_rate": 0.00018509015172120621,
296
+ "loss": 0.8873,
297
+ "step": 41
298
+ },
299
+ {
300
+ "epoch": 0.267515923566879,
301
+ "grad_norm": 0.13835562765598297,
302
+ "learning_rate": 0.00018390719910244487,
303
+ "loss": 0.8715,
304
+ "step": 42
305
+ },
306
+ {
307
+ "epoch": 0.27388535031847133,
308
+ "grad_norm": 0.1395685374736786,
309
+ "learning_rate": 0.00018268317838789088,
310
+ "loss": 0.9215,
311
+ "step": 43
312
+ },
313
+ {
314
+ "epoch": 0.2802547770700637,
315
+ "grad_norm": 0.12839213013648987,
316
+ "learning_rate": 0.00018141868867035745,
317
+ "loss": 0.857,
318
+ "step": 44
319
+ },
320
+ {
321
+ "epoch": 0.28662420382165604,
322
+ "grad_norm": 0.13072729110717773,
323
+ "learning_rate": 0.00018011434885007482,
324
+ "loss": 0.8962,
325
+ "step": 45
326
+ },
327
+ {
328
+ "epoch": 0.2929936305732484,
329
+ "grad_norm": 0.12887758016586304,
330
+ "learning_rate": 0.00017877079733177184,
331
+ "loss": 0.8788,
332
+ "step": 46
333
+ },
334
+ {
335
+ "epoch": 0.29936305732484075,
336
+ "grad_norm": 0.13233087956905365,
337
+ "learning_rate": 0.00017738869171221068,
338
+ "loss": 0.8521,
339
+ "step": 47
340
+ },
341
+ {
342
+ "epoch": 0.3057324840764331,
343
+ "grad_norm": 0.12415429204702377,
344
+ "learning_rate": 0.0001759687084583285,
345
+ "loss": 0.8319,
346
+ "step": 48
347
+ },
348
+ {
349
+ "epoch": 0.31210191082802546,
350
+ "grad_norm": 0.13997192680835724,
351
+ "learning_rate": 0.00017451154257614287,
352
+ "loss": 0.8506,
353
+ "step": 49
354
+ },
355
+ {
356
+ "epoch": 0.3184713375796178,
357
+ "grad_norm": 0.1296936273574829,
358
+ "learning_rate": 0.00017301790727058345,
359
+ "loss": 0.8495,
360
+ "step": 50
361
+ },
362
+ {
363
+ "epoch": 0.3248407643312102,
364
+ "grad_norm": 0.1260387897491455,
365
+ "learning_rate": 0.00017148853359641626,
366
+ "loss": 0.8714,
367
+ "step": 51
368
+ },
369
+ {
370
+ "epoch": 0.33121019108280253,
371
+ "grad_norm": 0.14483502507209778,
372
+ "learning_rate": 0.00016992417010043142,
373
+ "loss": 0.8284,
374
+ "step": 52
375
+ },
376
+ {
377
+ "epoch": 0.3375796178343949,
378
+ "grad_norm": 0.13002006709575653,
379
+ "learning_rate": 0.00016832558245506935,
380
+ "loss": 0.8478,
381
+ "step": 53
382
+ },
383
+ {
384
+ "epoch": 0.34394904458598724,
385
+ "grad_norm": 0.12996485829353333,
386
+ "learning_rate": 0.0001666935530836651,
387
+ "loss": 0.8351,
388
+ "step": 54
389
+ },
390
+ {
391
+ "epoch": 0.3503184713375796,
392
+ "grad_norm": 0.13534753024578094,
393
+ "learning_rate": 0.0001650288807774937,
394
+ "loss": 0.8092,
395
+ "step": 55
396
+ },
397
+ {
398
+ "epoch": 0.35668789808917195,
399
+ "grad_norm": 0.12969057261943817,
400
+ "learning_rate": 0.0001633323803048047,
401
+ "loss": 0.8425,
402
+ "step": 56
403
+ },
404
+ {
405
+ "epoch": 0.3630573248407643,
406
+ "grad_norm": 0.12496688216924667,
407
+ "learning_rate": 0.00016160488201203644,
408
+ "loss": 0.8313,
409
+ "step": 57
410
+ },
411
+ {
412
+ "epoch": 0.36942675159235666,
413
+ "grad_norm": 0.12409767508506775,
414
+ "learning_rate": 0.00015984723141740576,
415
+ "loss": 0.8226,
416
+ "step": 58
417
+ },
418
+ {
419
+ "epoch": 0.37579617834394907,
420
+ "grad_norm": 0.13024461269378662,
421
+ "learning_rate": 0.0001580602887970721,
422
+ "loss": 0.8281,
423
+ "step": 59
424
+ },
425
+ {
426
+ "epoch": 0.3821656050955414,
427
+ "grad_norm": 0.13077828288078308,
428
+ "learning_rate": 0.0001562449287640781,
429
+ "loss": 0.7939,
430
+ "step": 60
431
+ },
432
+ {
433
+ "epoch": 0.3885350318471338,
434
+ "grad_norm": 0.13101692497730255,
435
+ "learning_rate": 0.00015440203984027324,
436
+ "loss": 0.8085,
437
+ "step": 61
438
+ },
439
+ {
440
+ "epoch": 0.39490445859872614,
441
+ "grad_norm": 0.13003262877464294,
442
+ "learning_rate": 0.00015253252402142988,
443
+ "loss": 0.8179,
444
+ "step": 62
445
+ },
446
+ {
447
+ "epoch": 0.4012738853503185,
448
+ "grad_norm": 0.13072040677070618,
449
+ "learning_rate": 0.0001506372963357644,
450
+ "loss": 0.7945,
451
+ "step": 63
452
+ },
453
+ {
454
+ "epoch": 0.40764331210191085,
455
+ "grad_norm": 0.11719010770320892,
456
+ "learning_rate": 0.00014871728439607966,
457
+ "loss": 0.8202,
458
+ "step": 64
459
+ },
460
+ {
461
+ "epoch": 0.4140127388535032,
462
+ "grad_norm": 0.12282049655914307,
463
+ "learning_rate": 0.00014677342794574817,
464
+ "loss": 0.7987,
465
+ "step": 65
466
+ },
467
+ {
468
+ "epoch": 0.42038216560509556,
469
+ "grad_norm": 0.11916442960500717,
470
+ "learning_rate": 0.00014480667839875786,
471
+ "loss": 0.7963,
472
+ "step": 66
473
+ },
474
+ {
475
+ "epoch": 0.4267515923566879,
476
+ "grad_norm": 0.13636524975299835,
477
+ "learning_rate": 0.00014281799837404552,
478
+ "loss": 0.808,
479
+ "step": 67
480
+ },
481
+ {
482
+ "epoch": 0.43312101910828027,
483
+ "grad_norm": 0.12172853946685791,
484
+ "learning_rate": 0.0001408083612243465,
485
+ "loss": 0.7889,
486
+ "step": 68
487
+ },
488
+ {
489
+ "epoch": 0.4394904458598726,
490
+ "grad_norm": 0.12408412247896194,
491
+ "learning_rate": 0.00013877875055979023,
492
+ "loss": 0.8145,
493
+ "step": 69
494
+ },
495
+ {
496
+ "epoch": 0.445859872611465,
497
+ "grad_norm": 0.1280149221420288,
498
+ "learning_rate": 0.00013673015976647568,
499
+ "loss": 0.796,
500
+ "step": 70
501
+ },
502
+ {
503
+ "epoch": 0.45222929936305734,
504
+ "grad_norm": 0.13267850875854492,
505
+ "learning_rate": 0.00013466359152026195,
506
+ "loss": 0.7928,
507
+ "step": 71
508
+ },
509
+ {
510
+ "epoch": 0.4585987261146497,
511
+ "grad_norm": 0.12811611592769623,
512
+ "learning_rate": 0.00013258005729601177,
513
+ "loss": 0.781,
514
+ "step": 72
515
+ },
516
+ {
517
+ "epoch": 0.46496815286624205,
518
+ "grad_norm": 0.1286015510559082,
519
+ "learning_rate": 0.00013048057687252865,
520
+ "loss": 0.7603,
521
+ "step": 73
522
+ },
523
+ {
524
+ "epoch": 0.4713375796178344,
525
+ "grad_norm": 0.14502450823783875,
526
+ "learning_rate": 0.0001283661778334297,
527
+ "loss": 0.7862,
528
+ "step": 74
529
+ },
530
+ {
531
+ "epoch": 0.47770700636942676,
532
+ "grad_norm": 0.15144243836402893,
533
+ "learning_rate": 0.0001262378950641979,
534
+ "loss": 0.8128,
535
+ "step": 75
536
+ },
537
+ {
538
+ "epoch": 0.4840764331210191,
539
+ "grad_norm": 0.14334194362163544,
540
+ "learning_rate": 0.00012409677024566144,
541
+ "loss": 0.7535,
542
+ "step": 76
543
+ },
544
+ {
545
+ "epoch": 0.49044585987261147,
546
+ "grad_norm": 0.13474944233894348,
547
+ "learning_rate": 0.00012194385134414608,
548
+ "loss": 0.8058,
549
+ "step": 77
550
+ },
551
+ {
552
+ "epoch": 0.4968152866242038,
553
+ "grad_norm": 0.13721239566802979,
554
+ "learning_rate": 0.00011978019209855174,
555
+ "loss": 0.7731,
556
+ "step": 78
557
+ },
558
+ {
559
+ "epoch": 0.5031847133757962,
560
+ "grad_norm": 0.1446215659379959,
561
+ "learning_rate": 0.00011760685150460362,
562
+ "loss": 0.7494,
563
+ "step": 79
564
+ },
565
+ {
566
+ "epoch": 0.5095541401273885,
567
+ "grad_norm": 0.14299342036247253,
568
+ "learning_rate": 0.00011542489329653024,
569
+ "loss": 0.7749,
570
+ "step": 80
571
+ },
572
+ {
573
+ "epoch": 0.5159235668789809,
574
+ "grad_norm": 0.13673968613147736,
575
+ "learning_rate": 0.00011323538542642227,
576
+ "loss": 0.7402,
577
+ "step": 81
578
+ },
579
+ {
580
+ "epoch": 0.5222929936305732,
581
+ "grad_norm": 0.13603895902633667,
582
+ "learning_rate": 0.000111039399541527,
583
+ "loss": 0.7651,
584
+ "step": 82
585
+ },
586
+ {
587
+ "epoch": 0.5286624203821656,
588
+ "grad_norm": 0.13204550743103027,
589
+ "learning_rate": 0.00010883801045973425,
590
+ "loss": 0.7432,
591
+ "step": 83
592
+ },
593
+ {
594
+ "epoch": 0.535031847133758,
595
+ "grad_norm": 0.14662222564220428,
596
+ "learning_rate": 0.00010663229564351041,
597
+ "loss": 0.7648,
598
+ "step": 84
599
+ },
600
+ {
601
+ "epoch": 0.5414012738853503,
602
+ "grad_norm": 0.14292187988758087,
603
+ "learning_rate": 0.00010442333467253789,
604
+ "loss": 0.758,
605
+ "step": 85
606
+ },
607
+ {
608
+ "epoch": 0.5477707006369427,
609
+ "grad_norm": 0.13865429162979126,
610
+ "learning_rate": 0.00010221220871531869,
611
+ "loss": 0.7427,
612
+ "step": 86
613
+ },
614
+ {
615
+ "epoch": 0.554140127388535,
616
+ "grad_norm": 0.13653217256069183,
617
+ "learning_rate": 0.0001,
618
+ "loss": 0.7466,
619
+ "step": 87
620
+ },
621
+ {
622
+ "epoch": 0.5605095541401274,
623
+ "grad_norm": 0.1345141977071762,
624
+ "learning_rate": 9.778779128468132e-05,
625
+ "loss": 0.7842,
626
+ "step": 88
627
+ },
628
+ {
629
+ "epoch": 0.5668789808917197,
630
+ "grad_norm": 0.13763494789600372,
631
+ "learning_rate": 9.557666532746213e-05,
632
+ "loss": 0.7757,
633
+ "step": 89
634
+ },
635
+ {
636
+ "epoch": 0.5732484076433121,
637
+ "grad_norm": 0.14381903409957886,
638
+ "learning_rate": 9.336770435648964e-05,
639
+ "loss": 0.7413,
640
+ "step": 90
641
+ },
642
+ {
643
+ "epoch": 0.5796178343949044,
644
+ "grad_norm": 0.15023089945316315,
645
+ "learning_rate": 9.116198954026577e-05,
646
+ "loss": 0.7528,
647
+ "step": 91
648
+ },
649
+ {
650
+ "epoch": 0.5859872611464968,
651
+ "grad_norm": 0.13393183052539825,
652
+ "learning_rate": 8.896060045847304e-05,
653
+ "loss": 0.7356,
654
+ "step": 92
655
+ },
656
+ {
657
+ "epoch": 0.5923566878980892,
658
+ "grad_norm": 0.14455927908420563,
659
+ "learning_rate": 8.676461457357776e-05,
660
+ "loss": 0.7661,
661
+ "step": 93
662
+ },
663
+ {
664
+ "epoch": 0.5987261146496815,
665
+ "grad_norm": 0.1516951471567154,
666
+ "learning_rate": 8.457510670346976e-05,
667
+ "loss": 0.7611,
668
+ "step": 94
669
+ },
670
+ {
671
+ "epoch": 0.6050955414012739,
672
+ "grad_norm": 0.15287864208221436,
673
+ "learning_rate": 8.239314849539638e-05,
674
+ "loss": 0.7751,
675
+ "step": 95
676
+ },
677
+ {
678
+ "epoch": 0.6114649681528662,
679
+ "grad_norm": 0.13344816863536835,
680
+ "learning_rate": 8.021980790144827e-05,
681
+ "loss": 0.7555,
682
+ "step": 96
683
+ },
684
+ {
685
+ "epoch": 0.6178343949044586,
686
+ "grad_norm": 0.12972086668014526,
687
+ "learning_rate": 7.805614865585396e-05,
688
+ "loss": 0.744,
689
+ "step": 97
690
+ },
691
+ {
692
+ "epoch": 0.6242038216560509,
693
+ "grad_norm": 0.13361124694347382,
694
+ "learning_rate": 7.590322975433857e-05,
695
+ "loss": 0.7616,
696
+ "step": 98
697
+ },
698
+ {
699
+ "epoch": 0.6305732484076433,
700
+ "grad_norm": 0.14594393968582153,
701
+ "learning_rate": 7.376210493580212e-05,
702
+ "loss": 0.7778,
703
+ "step": 99
704
+ },
705
+ {
706
+ "epoch": 0.6369426751592356,
707
+ "grad_norm": 0.14642472565174103,
708
+ "learning_rate": 7.163382216657034e-05,
709
+ "loss": 0.7516,
710
+ "step": 100
711
+ },
712
+ {
713
+ "epoch": 0.643312101910828,
714
+ "grad_norm": 0.1501522958278656,
715
+ "learning_rate": 6.951942312747134e-05,
716
+ "loss": 0.7631,
717
+ "step": 101
718
+ },
719
+ {
720
+ "epoch": 0.6496815286624203,
721
+ "grad_norm": 0.1488322615623474,
722
+ "learning_rate": 6.741994270398826e-05,
723
+ "loss": 0.7446,
724
+ "step": 102
725
+ },
726
+ {
727
+ "epoch": 0.6560509554140127,
728
+ "grad_norm": 0.13777847588062286,
729
+ "learning_rate": 6.533640847973808e-05,
730
+ "loss": 0.7726,
731
+ "step": 103
732
+ },
733
+ {
734
+ "epoch": 0.6624203821656051,
735
+ "grad_norm": 0.15372638404369354,
736
+ "learning_rate": 6.326984023352435e-05,
737
+ "loss": 0.7472,
738
+ "step": 104
739
+ },
740
+ {
741
+ "epoch": 0.6687898089171974,
742
+ "grad_norm": 0.1486649364233017,
743
+ "learning_rate": 6.122124944020977e-05,
744
+ "loss": 0.779,
745
+ "step": 105
746
+ },
747
+ {
748
+ "epoch": 0.6751592356687898,
749
+ "grad_norm": 0.15514899790287018,
750
+ "learning_rate": 5.91916387756535e-05,
751
+ "loss": 0.7297,
752
+ "step": 106
753
+ },
754
+ {
755
+ "epoch": 0.6815286624203821,
756
+ "grad_norm": 0.14487750828266144,
757
+ "learning_rate": 5.718200162595449e-05,
758
+ "loss": 0.7044,
759
+ "step": 107
760
+ },
761
+ {
762
+ "epoch": 0.6878980891719745,
763
+ "grad_norm": 0.1558275818824768,
764
+ "learning_rate": 5.5193321601242156e-05,
765
+ "loss": 0.7442,
766
+ "step": 108
767
+ },
768
+ {
769
+ "epoch": 0.6942675159235668,
770
+ "grad_norm": 0.14666889607906342,
771
+ "learning_rate": 5.322657205425183e-05,
772
+ "loss": 0.7321,
773
+ "step": 109
774
+ },
775
+ {
776
+ "epoch": 0.7006369426751592,
777
+ "grad_norm": 0.1434071809053421,
778
+ "learning_rate": 5.1282715603920374e-05,
779
+ "loss": 0.749,
780
+ "step": 110
781
+ },
782
+ {
783
+ "epoch": 0.7070063694267515,
784
+ "grad_norm": 0.13561522960662842,
785
+ "learning_rate": 4.936270366423563e-05,
786
+ "loss": 0.7085,
787
+ "step": 111
788
+ },
789
+ {
790
+ "epoch": 0.7133757961783439,
791
+ "grad_norm": 0.15304827690124512,
792
+ "learning_rate": 4.746747597857014e-05,
793
+ "loss": 0.6975,
794
+ "step": 112
795
+ },
796
+ {
797
+ "epoch": 0.7197452229299363,
798
+ "grad_norm": 0.14578115940093994,
799
+ "learning_rate": 4.559796015972677e-05,
800
+ "loss": 0.7282,
801
+ "step": 113
802
+ },
803
+ {
804
+ "epoch": 0.7261146496815286,
805
+ "grad_norm": 0.14384236931800842,
806
+ "learning_rate": 4.375507123592194e-05,
807
+ "loss": 0.7241,
808
+ "step": 114
809
+ },
810
+ {
811
+ "epoch": 0.732484076433121,
812
+ "grad_norm": 0.16036854684352875,
813
+ "learning_rate": 4.1939711202927936e-05,
814
+ "loss": 0.7581,
815
+ "step": 115
816
+ },
817
+ {
818
+ "epoch": 0.7388535031847133,
819
+ "grad_norm": 0.1477956473827362,
820
+ "learning_rate": 4.015276858259427e-05,
821
+ "loss": 0.7372,
822
+ "step": 116
823
+ },
824
+ {
825
+ "epoch": 0.7452229299363057,
826
+ "grad_norm": 0.13899311423301697,
827
+ "learning_rate": 3.839511798796357e-05,
828
+ "loss": 0.7358,
829
+ "step": 117
830
+ },
831
+ {
832
+ "epoch": 0.7515923566878981,
833
+ "grad_norm": 0.14456766843795776,
834
+ "learning_rate": 3.6667619695195285e-05,
835
+ "loss": 0.7386,
836
+ "step": 118
837
+ },
838
+ {
839
+ "epoch": 0.7579617834394905,
840
+ "grad_norm": 0.13479867577552795,
841
+ "learning_rate": 3.49711192225063e-05,
842
+ "loss": 0.7083,
843
+ "step": 119
844
+ },
845
+ {
846
+ "epoch": 0.7643312101910829,
847
+ "grad_norm": 0.15040116012096405,
848
+ "learning_rate": 3.330644691633492e-05,
849
+ "loss": 0.7387,
850
+ "step": 120
851
+ },
852
+ {
853
+ "epoch": 0.7707006369426752,
854
+ "grad_norm": 0.13942091166973114,
855
+ "learning_rate": 3.167441754493066e-05,
856
+ "loss": 0.7583,
857
+ "step": 121
858
+ },
859
+ {
860
+ "epoch": 0.7770700636942676,
861
+ "grad_norm": 0.1347065269947052,
862
+ "learning_rate": 3.0075829899568597e-05,
863
+ "loss": 0.7298,
864
+ "step": 122
865
+ },
866
+ {
867
+ "epoch": 0.7834394904458599,
868
+ "grad_norm": 0.13468332588672638,
869
+ "learning_rate": 2.8511466403583766e-05,
870
+ "loss": 0.7437,
871
+ "step": 123
872
+ },
873
+ {
874
+ "epoch": 0.7898089171974523,
875
+ "grad_norm": 0.13734403252601624,
876
+ "learning_rate": 2.6982092729416587e-05,
877
+ "loss": 0.7262,
878
+ "step": 124
879
+ },
880
+ {
881
+ "epoch": 0.7961783439490446,
882
+ "grad_norm": 0.13269653916358948,
883
+ "learning_rate": 2.548845742385717e-05,
884
+ "loss": 0.7228,
885
+ "step": 125
886
+ },
887
+ {
888
+ "epoch": 0.802547770700637,
889
+ "grad_norm": 0.13551217317581177,
890
+ "learning_rate": 2.403129154167153e-05,
891
+ "loss": 0.7317,
892
+ "step": 126
893
+ },
894
+ {
895
+ "epoch": 0.8089171974522293,
896
+ "grad_norm": 0.13381463289260864,
897
+ "learning_rate": 2.2611308287789344e-05,
898
+ "loss": 0.7263,
899
+ "step": 127
900
+ },
901
+ {
902
+ "epoch": 0.8152866242038217,
903
+ "grad_norm": 0.1421995759010315,
904
+ "learning_rate": 2.1229202668228197e-05,
905
+ "loss": 0.7302,
906
+ "step": 128
907
+ },
908
+ {
909
+ "epoch": 0.821656050955414,
910
+ "grad_norm": 0.13885881006717682,
911
+ "learning_rate": 1.988565114992519e-05,
912
+ "loss": 0.7597,
913
+ "step": 129
914
+ },
915
+ {
916
+ "epoch": 0.8280254777070064,
917
+ "grad_norm": 0.1440562754869461,
918
+ "learning_rate": 1.858131132964259e-05,
919
+ "loss": 0.7532,
920
+ "step": 130
921
+ },
922
+ {
923
+ "epoch": 0.8343949044585988,
924
+ "grad_norm": 0.13995864987373352,
925
+ "learning_rate": 1.7316821612109136e-05,
926
+ "loss": 0.7205,
927
+ "step": 131
928
+ },
929
+ {
930
+ "epoch": 0.8407643312101911,
931
+ "grad_norm": 0.1380428522825241,
932
+ "learning_rate": 1.609280089755515e-05,
933
+ "loss": 0.7176,
934
+ "step": 132
935
+ },
936
+ {
937
+ "epoch": 0.8471337579617835,
938
+ "grad_norm": 0.12905895709991455,
939
+ "learning_rate": 1.4909848278793782e-05,
940
+ "loss": 0.7404,
941
+ "step": 133
942
+ },
943
+ {
944
+ "epoch": 0.8535031847133758,
945
+ "grad_norm": 0.15510842204093933,
946
+ "learning_rate": 1.3768542747997215e-05,
947
+ "loss": 0.7249,
948
+ "step": 134
949
+ },
950
+ {
951
+ "epoch": 0.8598726114649682,
952
+ "grad_norm": 0.13218414783477783,
953
+ "learning_rate": 1.2669442913310725e-05,
954
+ "loss": 0.719,
955
+ "step": 135
956
+ },
957
+ {
958
+ "epoch": 0.8662420382165605,
959
+ "grad_norm": 0.1409848928451538,
960
+ "learning_rate": 1.161308672544389e-05,
961
+ "loss": 0.705,
962
+ "step": 136
963
+ },
964
+ {
965
+ "epoch": 0.8726114649681529,
966
+ "grad_norm": 0.13037748634815216,
967
+ "learning_rate": 1.059999121437244e-05,
968
+ "loss": 0.7165,
969
+ "step": 137
970
+ },
971
+ {
972
+ "epoch": 0.8789808917197452,
973
+ "grad_norm": 0.139460951089859,
974
+ "learning_rate": 9.630652236279625e-06,
975
+ "loss": 0.69,
976
+ "step": 138
977
+ },
978
+ {
979
+ "epoch": 0.8853503184713376,
980
+ "grad_norm": 0.14767377078533173,
981
+ "learning_rate": 8.70554423086114e-06,
982
+ "loss": 0.7517,
983
+ "step": 139
984
+ },
985
+ {
986
+ "epoch": 0.89171974522293,
987
+ "grad_norm": 0.13341829180717468,
988
+ "learning_rate": 7.825119989112173e-06,
989
+ "loss": 0.7135,
990
+ "step": 140
991
+ },
992
+ {
993
+ "epoch": 0.8980891719745223,
994
+ "grad_norm": 0.12980401515960693,
995
+ "learning_rate": 6.989810431710375e-06,
996
+ "loss": 0.6892,
997
+ "step": 141
998
+ },
999
+ {
1000
+ "epoch": 0.9044585987261147,
1001
+ "grad_norm": 0.13363727927207947,
1002
+ "learning_rate": 6.200024398103255e-06,
1003
+ "loss": 0.7217,
1004
+ "step": 142
1005
+ },
1006
+ {
1007
+ "epoch": 0.910828025477707,
1008
+ "grad_norm": 0.14944419264793396,
1009
+ "learning_rate": 5.456148446402976e-06,
1010
+ "loss": 0.742,
1011
+ "step": 143
1012
+ },
1013
+ {
1014
+ "epoch": 0.9171974522292994,
1015
+ "grad_norm": 0.134084090590477,
1016
+ "learning_rate": 4.758546664186869e-06,
1017
+ "loss": 0.735,
1018
+ "step": 144
1019
+ },
1020
+ {
1021
+ "epoch": 0.9235668789808917,
1022
+ "grad_norm": 0.1409689486026764,
1023
+ "learning_rate": 4.107560490295992e-06,
1024
+ "loss": 0.7192,
1025
+ "step": 145
1026
+ },
1027
+ {
1028
+ "epoch": 0.9299363057324841,
1029
+ "grad_norm": 0.13256186246871948,
1030
+ "learning_rate": 3.5035085477190143e-06,
1031
+ "loss": 0.6932,
1032
+ "step": 146
1033
+ },
1034
+ {
1035
+ "epoch": 0.9363057324840764,
1036
+ "grad_norm": 0.1366000920534134,
1037
+ "learning_rate": 2.94668648764328e-06,
1038
+ "loss": 0.7295,
1039
+ "step": 147
1040
+ },
1041
+ {
1042
+ "epoch": 0.9426751592356688,
1043
+ "grad_norm": 0.13672901690006256,
1044
+ "learning_rate": 2.4373668447493224e-06,
1045
+ "loss": 0.7059,
1046
+ "step": 148
1047
+ },
1048
+ {
1049
+ "epoch": 0.9490445859872612,
1050
+ "grad_norm": 0.13341008126735687,
1051
+ "learning_rate": 1.9757989038197146e-06,
1052
+ "loss": 0.7184,
1053
+ "step": 149
1054
+ },
1055
+ {
1056
+ "epoch": 0.9554140127388535,
1057
+ "grad_norm": 0.13967232406139374,
1058
+ "learning_rate": 1.562208577727442e-06,
1059
+ "loss": 0.7264,
1060
+ "step": 150
1061
+ },
1062
+ {
1063
+ "epoch": 0.9617834394904459,
1064
+ "grad_norm": 0.1259932667016983,
1065
+ "learning_rate": 1.1967982968635993e-06,
1066
+ "loss": 0.7352,
1067
+ "step": 151
1068
+ },
1069
+ {
1070
+ "epoch": 0.9681528662420382,
1071
+ "grad_norm": 0.14053477346897125,
1072
+ "learning_rate": 8.797469100585431e-07,
1073
+ "loss": 0.7145,
1074
+ "step": 152
1075
+ },
1076
+ {
1077
+ "epoch": 0.9745222929936306,
1078
+ "grad_norm": 0.12578168511390686,
1079
+ "learning_rate": 6.11209597044926e-07,
1080
+ "loss": 0.7092,
1081
+ "step": 153
1082
+ },
1083
+ {
1084
+ "epoch": 0.9808917197452229,
1085
+ "grad_norm": 0.14532066881656647,
1086
+ "learning_rate": 3.913177925055189e-07,
1087
+ "loss": 0.7048,
1088
+ "step": 154
1089
+ },
1090
+ {
1091
+ "epoch": 0.9872611464968153,
1092
+ "grad_norm": 0.13926520943641663,
1093
+ "learning_rate": 2.201791217428917e-07,
1094
+ "loss": 0.7192,
1095
+ "step": 155
1096
+ },
1097
+ {
1098
+ "epoch": 0.9936305732484076,
1099
+ "grad_norm": 0.1295260787010193,
1100
+ "learning_rate": 9.78773480026396e-08,
1101
+ "loss": 0.7363,
1102
+ "step": 156
1103
+ },
1104
+ {
1105
+ "epoch": 1.0,
1106
+ "grad_norm": 0.13316026329994202,
1107
+ "learning_rate": 2.447233147570005e-08,
1108
+ "loss": 0.7182,
1109
+ "step": 157
1110
+ }
1111
+ ],
1112
+ "logging_steps": 1,
1113
+ "max_steps": 157,
1114
+ "num_input_tokens_seen": 0,
1115
+ "num_train_epochs": 1,
1116
+ "save_steps": 500,
1117
+ "stateful_callbacks": {
1118
+ "TrainerControl": {
1119
+ "args": {
1120
+ "should_epoch_stop": false,
1121
+ "should_evaluate": false,
1122
+ "should_log": false,
1123
+ "should_save": true,
1124
+ "should_training_stop": true
1125
+ },
1126
+ "attributes": {}
1127
+ }
1128
+ },
1129
+ "total_flos": 8.999866416811213e+16,
1130
+ "train_batch_size": 16,
1131
+ "trial_name": null,
1132
+ "trial_params": null
1133
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e7ad3a5846e8dba34f7faf3c5820de1c903cd66cafe879846f0b6dc5f79affd
3
+ size 7672
vocab.json ADDED
The diff for this file is too large to render. See raw diff