yoonyoon commited on
Commit
2fb948a
1 Parent(s): c0e9801
README.md ADDED
@@ -0,0 +1,204 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: yanolja/EEVE-Korean-10.8B-v1.0
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 0.11.1
adapter_config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "yanolja/EEVE-Korean-10.8B-v1.0",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 32,
14
+ "lora_dropout": 0.1,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 32,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "up_proj",
24
+ "down_proj",
25
+ "v_proj",
26
+ "gate_proj",
27
+ "q_proj",
28
+ "k_proj",
29
+ "o_proj",
30
+ "embed_tokens",
31
+ "lm_head"
32
+ ],
33
+ "task_type": "CAUSAL_LM",
34
+ "use_dora": false,
35
+ "use_rslora": false
36
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f46b1d6d81a822cfaa1da0451e31837340edbf1972a20d048befbfd47baf15f7
3
+ size 928606504
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c50325107093d4f935fbc02f17f130bb69ac2b66c919f446206dc664bd45c7b9
3
+ size 515422398
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:083c822fd94b7d59c9691a46ff2e23259d93a507a877c4b33caad9798b513874
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca30ee67606a5f9d06f6491d96e43b765d984ad5dc56654eec323587de6857a4
3
+ size 1064
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": "<|im_end|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<unk>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "32000": {
30
+ "content": "<|im_end|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ }
37
+ },
38
+ "additional_special_tokens": [],
39
+ "bos_token": "<s>",
40
+ "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = 'You are a helpful assistant.' %}{% endif %}{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in loop_messages %}{% if loop.index0 == 0 %}{{'<|im_start|>system\n' + system_message + '<|im_end|>\n'}}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
41
+ "clean_up_tokenization_spaces": false,
42
+ "eos_token": "<|im_end|>",
43
+ "legacy": true,
44
+ "model_max_length": 1000000000000000019884624838656,
45
+ "pad_token": "<unk>",
46
+ "sp_model_kwargs": {},
47
+ "spaces_between_special_tokens": false,
48
+ "tokenizer_class": "LlamaTokenizer",
49
+ "trust_remote_code": false,
50
+ "unk_token": "<unk>",
51
+ "use_default_system_prompt": false,
52
+ "use_fast": true
53
+ }
trainer_state.json ADDED
@@ -0,0 +1,1281 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.016034691946843215,
5
+ "eval_steps": 500,
6
+ "global_step": 18000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0,
13
+ "grad_norm": 173.0,
14
+ "learning_rate": 4.4539461963299484e-07,
15
+ "loss": 2.153,
16
+ "step": 100
17
+ },
18
+ {
19
+ "epoch": 0.0,
20
+ "grad_norm": 40.5,
21
+ "learning_rate": 8.907892392659897e-07,
22
+ "loss": 2.398,
23
+ "step": 200
24
+ },
25
+ {
26
+ "epoch": 0.0,
27
+ "grad_norm": 223.0,
28
+ "learning_rate": 1.3361838588989846e-06,
29
+ "loss": 1.8912,
30
+ "step": 300
31
+ },
32
+ {
33
+ "epoch": 0.0,
34
+ "grad_norm": 95.5,
35
+ "learning_rate": 1.7815784785319793e-06,
36
+ "loss": 1.6403,
37
+ "step": 400
38
+ },
39
+ {
40
+ "epoch": 0.0,
41
+ "grad_norm": 600.0,
42
+ "learning_rate": 2.226973098164974e-06,
43
+ "loss": 1.4652,
44
+ "step": 500
45
+ },
46
+ {
47
+ "epoch": 0.0,
48
+ "grad_norm": 51.75,
49
+ "learning_rate": 2.672367717797969e-06,
50
+ "loss": 1.2489,
51
+ "step": 600
52
+ },
53
+ {
54
+ "epoch": 0.0,
55
+ "grad_norm": 290.0,
56
+ "learning_rate": 3.1177623374309637e-06,
57
+ "loss": 1.2421,
58
+ "step": 700
59
+ },
60
+ {
61
+ "epoch": 0.0,
62
+ "grad_norm": 27.75,
63
+ "learning_rate": 3.5631569570639587e-06,
64
+ "loss": 1.2188,
65
+ "step": 800
66
+ },
67
+ {
68
+ "epoch": 0.0,
69
+ "grad_norm": 13.0,
70
+ "learning_rate": 4.008551576696954e-06,
71
+ "loss": 1.123,
72
+ "step": 900
73
+ },
74
+ {
75
+ "epoch": 0.0,
76
+ "grad_norm": 39.75,
77
+ "learning_rate": 4.453946196329948e-06,
78
+ "loss": 1.0388,
79
+ "step": 1000
80
+ },
81
+ {
82
+ "epoch": 0.0,
83
+ "grad_norm": 21.375,
84
+ "learning_rate": 4.899340815962943e-06,
85
+ "loss": 1.3034,
86
+ "step": 1100
87
+ },
88
+ {
89
+ "epoch": 0.0,
90
+ "grad_norm": 36.75,
91
+ "learning_rate": 5.344735435595938e-06,
92
+ "loss": 1.2272,
93
+ "step": 1200
94
+ },
95
+ {
96
+ "epoch": 0.0,
97
+ "grad_norm": 71.5,
98
+ "learning_rate": 5.790130055228933e-06,
99
+ "loss": 1.1825,
100
+ "step": 1300
101
+ },
102
+ {
103
+ "epoch": 0.0,
104
+ "grad_norm": 54.5,
105
+ "learning_rate": 6.235524674861927e-06,
106
+ "loss": 1.3466,
107
+ "step": 1400
108
+ },
109
+ {
110
+ "epoch": 0.0,
111
+ "grad_norm": 169.0,
112
+ "learning_rate": 6.680919294494922e-06,
113
+ "loss": 1.0543,
114
+ "step": 1500
115
+ },
116
+ {
117
+ "epoch": 0.0,
118
+ "grad_norm": 47.75,
119
+ "learning_rate": 7.126313914127917e-06,
120
+ "loss": 1.1117,
121
+ "step": 1600
122
+ },
123
+ {
124
+ "epoch": 0.0,
125
+ "grad_norm": 9.5,
126
+ "learning_rate": 7.571708533760913e-06,
127
+ "loss": 1.1458,
128
+ "step": 1700
129
+ },
130
+ {
131
+ "epoch": 0.0,
132
+ "grad_norm": 119.0,
133
+ "learning_rate": 8.017103153393907e-06,
134
+ "loss": 1.1823,
135
+ "step": 1800
136
+ },
137
+ {
138
+ "epoch": 0.0,
139
+ "grad_norm": 31.0,
140
+ "learning_rate": 8.462497773026902e-06,
141
+ "loss": 1.2171,
142
+ "step": 1900
143
+ },
144
+ {
145
+ "epoch": 0.0,
146
+ "grad_norm": 57.25,
147
+ "learning_rate": 8.907892392659896e-06,
148
+ "loss": 1.16,
149
+ "step": 2000
150
+ },
151
+ {
152
+ "epoch": 0.0,
153
+ "grad_norm": 77.0,
154
+ "learning_rate": 9.353287012292893e-06,
155
+ "loss": 1.1243,
156
+ "step": 2100
157
+ },
158
+ {
159
+ "epoch": 0.0,
160
+ "grad_norm": 31.5,
161
+ "learning_rate": 9.798681631925886e-06,
162
+ "loss": 1.1218,
163
+ "step": 2200
164
+ },
165
+ {
166
+ "epoch": 0.0,
167
+ "grad_norm": 98.0,
168
+ "learning_rate": 1.0244076251558882e-05,
169
+ "loss": 1.1527,
170
+ "step": 2300
171
+ },
172
+ {
173
+ "epoch": 0.0,
174
+ "grad_norm": 32.25,
175
+ "learning_rate": 1.0689470871191876e-05,
176
+ "loss": 1.1042,
177
+ "step": 2400
178
+ },
179
+ {
180
+ "epoch": 0.0,
181
+ "grad_norm": 29.0,
182
+ "learning_rate": 1.1134865490824871e-05,
183
+ "loss": 1.0131,
184
+ "step": 2500
185
+ },
186
+ {
187
+ "epoch": 0.0,
188
+ "grad_norm": 50.0,
189
+ "learning_rate": 1.1580260110457866e-05,
190
+ "loss": 1.2544,
191
+ "step": 2600
192
+ },
193
+ {
194
+ "epoch": 0.0,
195
+ "grad_norm": 20.625,
196
+ "learning_rate": 1.2025654730090862e-05,
197
+ "loss": 1.1475,
198
+ "step": 2700
199
+ },
200
+ {
201
+ "epoch": 0.0,
202
+ "grad_norm": 23.375,
203
+ "learning_rate": 1.2471049349723855e-05,
204
+ "loss": 1.2345,
205
+ "step": 2800
206
+ },
207
+ {
208
+ "epoch": 0.0,
209
+ "grad_norm": 39.5,
210
+ "learning_rate": 1.2916443969356851e-05,
211
+ "loss": 1.269,
212
+ "step": 2900
213
+ },
214
+ {
215
+ "epoch": 0.0,
216
+ "grad_norm": 30.5,
217
+ "learning_rate": 1.3361838588989844e-05,
218
+ "loss": 1.1995,
219
+ "step": 3000
220
+ },
221
+ {
222
+ "epoch": 0.0,
223
+ "grad_norm": 17.875,
224
+ "learning_rate": 1.3807233208622842e-05,
225
+ "loss": 1.1367,
226
+ "step": 3100
227
+ },
228
+ {
229
+ "epoch": 0.0,
230
+ "grad_norm": 255.0,
231
+ "learning_rate": 1.4252627828255835e-05,
232
+ "loss": 1.1993,
233
+ "step": 3200
234
+ },
235
+ {
236
+ "epoch": 0.0,
237
+ "grad_norm": 73.5,
238
+ "learning_rate": 1.469802244788883e-05,
239
+ "loss": 1.039,
240
+ "step": 3300
241
+ },
242
+ {
243
+ "epoch": 0.0,
244
+ "grad_norm": 106.5,
245
+ "learning_rate": 1.5143417067521826e-05,
246
+ "loss": 1.2538,
247
+ "step": 3400
248
+ },
249
+ {
250
+ "epoch": 0.0,
251
+ "grad_norm": 153.0,
252
+ "learning_rate": 1.558881168715482e-05,
253
+ "loss": 1.156,
254
+ "step": 3500
255
+ },
256
+ {
257
+ "epoch": 0.0,
258
+ "grad_norm": 111.0,
259
+ "learning_rate": 1.6034206306787815e-05,
260
+ "loss": 1.2418,
261
+ "step": 3600
262
+ },
263
+ {
264
+ "epoch": 0.0,
265
+ "grad_norm": 20.25,
266
+ "learning_rate": 1.647960092642081e-05,
267
+ "loss": 1.0018,
268
+ "step": 3700
269
+ },
270
+ {
271
+ "epoch": 0.0,
272
+ "grad_norm": 68.0,
273
+ "learning_rate": 1.6924995546053804e-05,
274
+ "loss": 1.101,
275
+ "step": 3800
276
+ },
277
+ {
278
+ "epoch": 0.0,
279
+ "grad_norm": 79.5,
280
+ "learning_rate": 1.7370390165686802e-05,
281
+ "loss": 1.1538,
282
+ "step": 3900
283
+ },
284
+ {
285
+ "epoch": 0.0,
286
+ "grad_norm": 26.5,
287
+ "learning_rate": 1.7815784785319793e-05,
288
+ "loss": 1.176,
289
+ "step": 4000
290
+ },
291
+ {
292
+ "epoch": 0.0,
293
+ "grad_norm": 96.5,
294
+ "learning_rate": 1.8261179404952788e-05,
295
+ "loss": 0.9909,
296
+ "step": 4100
297
+ },
298
+ {
299
+ "epoch": 0.0,
300
+ "grad_norm": 45.75,
301
+ "learning_rate": 1.8706574024585786e-05,
302
+ "loss": 1.1521,
303
+ "step": 4200
304
+ },
305
+ {
306
+ "epoch": 0.0,
307
+ "grad_norm": 42.0,
308
+ "learning_rate": 1.915196864421878e-05,
309
+ "loss": 1.1438,
310
+ "step": 4300
311
+ },
312
+ {
313
+ "epoch": 0.0,
314
+ "grad_norm": 16.125,
315
+ "learning_rate": 1.959736326385177e-05,
316
+ "loss": 1.1887,
317
+ "step": 4400
318
+ },
319
+ {
320
+ "epoch": 0.0,
321
+ "grad_norm": 38.75,
322
+ "learning_rate": 2.004275788348477e-05,
323
+ "loss": 1.2946,
324
+ "step": 4500
325
+ },
326
+ {
327
+ "epoch": 0.0,
328
+ "grad_norm": 99.5,
329
+ "learning_rate": 2.0488152503117764e-05,
330
+ "loss": 1.2574,
331
+ "step": 4600
332
+ },
333
+ {
334
+ "epoch": 0.0,
335
+ "grad_norm": 65.5,
336
+ "learning_rate": 2.093354712275076e-05,
337
+ "loss": 1.1517,
338
+ "step": 4700
339
+ },
340
+ {
341
+ "epoch": 0.0,
342
+ "grad_norm": 79.5,
343
+ "learning_rate": 2.1378941742383753e-05,
344
+ "loss": 1.187,
345
+ "step": 4800
346
+ },
347
+ {
348
+ "epoch": 0.0,
349
+ "grad_norm": 162.0,
350
+ "learning_rate": 2.1824336362016748e-05,
351
+ "loss": 0.9974,
352
+ "step": 4900
353
+ },
354
+ {
355
+ "epoch": 0.0,
356
+ "grad_norm": 48.5,
357
+ "learning_rate": 2.2269730981649742e-05,
358
+ "loss": 1.2278,
359
+ "step": 5000
360
+ },
361
+ {
362
+ "epoch": 0.0,
363
+ "grad_norm": 0.09423828125,
364
+ "learning_rate": 2.271512560128274e-05,
365
+ "loss": 1.2128,
366
+ "step": 5100
367
+ },
368
+ {
369
+ "epoch": 0.0,
370
+ "grad_norm": 34.75,
371
+ "learning_rate": 2.316052022091573e-05,
372
+ "loss": 1.1712,
373
+ "step": 5200
374
+ },
375
+ {
376
+ "epoch": 0.0,
377
+ "grad_norm": 0.01483154296875,
378
+ "learning_rate": 2.3605914840548726e-05,
379
+ "loss": 0.9784,
380
+ "step": 5300
381
+ },
382
+ {
383
+ "epoch": 0.0,
384
+ "grad_norm": 89.0,
385
+ "learning_rate": 2.4051309460181724e-05,
386
+ "loss": 1.1382,
387
+ "step": 5400
388
+ },
389
+ {
390
+ "epoch": 0.0,
391
+ "grad_norm": 59.5,
392
+ "learning_rate": 2.449670407981472e-05,
393
+ "loss": 1.291,
394
+ "step": 5500
395
+ },
396
+ {
397
+ "epoch": 0.0,
398
+ "grad_norm": 29.5,
399
+ "learning_rate": 2.494209869944771e-05,
400
+ "loss": 1.1317,
401
+ "step": 5600
402
+ },
403
+ {
404
+ "epoch": 0.01,
405
+ "grad_norm": 24.125,
406
+ "learning_rate": 2.5387493319080707e-05,
407
+ "loss": 1.1689,
408
+ "step": 5700
409
+ },
410
+ {
411
+ "epoch": 0.01,
412
+ "grad_norm": 34.0,
413
+ "learning_rate": 2.5832887938713702e-05,
414
+ "loss": 1.2427,
415
+ "step": 5800
416
+ },
417
+ {
418
+ "epoch": 0.01,
419
+ "grad_norm": 34.5,
420
+ "learning_rate": 2.6278282558346697e-05,
421
+ "loss": 1.353,
422
+ "step": 5900
423
+ },
424
+ {
425
+ "epoch": 0.01,
426
+ "grad_norm": 32.25,
427
+ "learning_rate": 2.6723677177979688e-05,
428
+ "loss": 1.1593,
429
+ "step": 6000
430
+ },
431
+ {
432
+ "epoch": 0.01,
433
+ "grad_norm": 33.75,
434
+ "learning_rate": 2.716907179761269e-05,
435
+ "loss": 1.1391,
436
+ "step": 6100
437
+ },
438
+ {
439
+ "epoch": 0.01,
440
+ "grad_norm": 82.0,
441
+ "learning_rate": 2.7614466417245684e-05,
442
+ "loss": 1.1999,
443
+ "step": 6200
444
+ },
445
+ {
446
+ "epoch": 0.01,
447
+ "grad_norm": 25.375,
448
+ "learning_rate": 2.8059861036878675e-05,
449
+ "loss": 1.0865,
450
+ "step": 6300
451
+ },
452
+ {
453
+ "epoch": 0.01,
454
+ "grad_norm": 34.25,
455
+ "learning_rate": 2.850525565651167e-05,
456
+ "loss": 1.0761,
457
+ "step": 6400
458
+ },
459
+ {
460
+ "epoch": 0.01,
461
+ "grad_norm": 44.0,
462
+ "learning_rate": 2.8950650276144664e-05,
463
+ "loss": 1.1187,
464
+ "step": 6500
465
+ },
466
+ {
467
+ "epoch": 0.01,
468
+ "grad_norm": 38.25,
469
+ "learning_rate": 2.939604489577766e-05,
470
+ "loss": 1.0824,
471
+ "step": 6600
472
+ },
473
+ {
474
+ "epoch": 0.01,
475
+ "grad_norm": 49.75,
476
+ "learning_rate": 2.9841439515410657e-05,
477
+ "loss": 1.0826,
478
+ "step": 6700
479
+ },
480
+ {
481
+ "epoch": 0.01,
482
+ "grad_norm": 47.0,
483
+ "learning_rate": 3.028683413504365e-05,
484
+ "loss": 1.1387,
485
+ "step": 6800
486
+ },
487
+ {
488
+ "epoch": 0.01,
489
+ "grad_norm": 61.0,
490
+ "learning_rate": 3.073222875467664e-05,
491
+ "loss": 1.1661,
492
+ "step": 6900
493
+ },
494
+ {
495
+ "epoch": 0.01,
496
+ "grad_norm": 31.625,
497
+ "learning_rate": 3.117762337430964e-05,
498
+ "loss": 1.2022,
499
+ "step": 7000
500
+ },
501
+ {
502
+ "epoch": 0.01,
503
+ "grad_norm": 38.75,
504
+ "learning_rate": 3.162301799394263e-05,
505
+ "loss": 1.2461,
506
+ "step": 7100
507
+ },
508
+ {
509
+ "epoch": 0.01,
510
+ "grad_norm": 28.5,
511
+ "learning_rate": 3.206841261357563e-05,
512
+ "loss": 1.2583,
513
+ "step": 7200
514
+ },
515
+ {
516
+ "epoch": 0.01,
517
+ "grad_norm": 12.0,
518
+ "learning_rate": 3.251380723320863e-05,
519
+ "loss": 1.1094,
520
+ "step": 7300
521
+ },
522
+ {
523
+ "epoch": 0.01,
524
+ "grad_norm": 68.0,
525
+ "learning_rate": 3.295920185284162e-05,
526
+ "loss": 1.2244,
527
+ "step": 7400
528
+ },
529
+ {
530
+ "epoch": 0.01,
531
+ "grad_norm": 42.0,
532
+ "learning_rate": 3.3404596472474617e-05,
533
+ "loss": 1.1486,
534
+ "step": 7500
535
+ },
536
+ {
537
+ "epoch": 0.01,
538
+ "grad_norm": 344.0,
539
+ "learning_rate": 3.384999109210761e-05,
540
+ "loss": 1.2049,
541
+ "step": 7600
542
+ },
543
+ {
544
+ "epoch": 0.01,
545
+ "grad_norm": 11.6875,
546
+ "learning_rate": 3.42953857117406e-05,
547
+ "loss": 1.0226,
548
+ "step": 7700
549
+ },
550
+ {
551
+ "epoch": 0.01,
552
+ "grad_norm": 43.75,
553
+ "learning_rate": 3.4740780331373604e-05,
554
+ "loss": 1.2662,
555
+ "step": 7800
556
+ },
557
+ {
558
+ "epoch": 0.01,
559
+ "grad_norm": 51.5,
560
+ "learning_rate": 3.5186174951006595e-05,
561
+ "loss": 1.1029,
562
+ "step": 7900
563
+ },
564
+ {
565
+ "epoch": 0.01,
566
+ "grad_norm": 36.25,
567
+ "learning_rate": 3.5631569570639586e-05,
568
+ "loss": 1.1623,
569
+ "step": 8000
570
+ },
571
+ {
572
+ "epoch": 0.01,
573
+ "grad_norm": 32.75,
574
+ "learning_rate": 3.6076964190272584e-05,
575
+ "loss": 1.0682,
576
+ "step": 8100
577
+ },
578
+ {
579
+ "epoch": 0.01,
580
+ "grad_norm": 57.75,
581
+ "learning_rate": 3.6522358809905575e-05,
582
+ "loss": 1.1232,
583
+ "step": 8200
584
+ },
585
+ {
586
+ "epoch": 0.01,
587
+ "grad_norm": 27.125,
588
+ "learning_rate": 3.696775342953857e-05,
589
+ "loss": 1.1474,
590
+ "step": 8300
591
+ },
592
+ {
593
+ "epoch": 0.01,
594
+ "grad_norm": 93.0,
595
+ "learning_rate": 3.741314804917157e-05,
596
+ "loss": 1.0526,
597
+ "step": 8400
598
+ },
599
+ {
600
+ "epoch": 0.01,
601
+ "grad_norm": 20.125,
602
+ "learning_rate": 3.785854266880456e-05,
603
+ "loss": 1.2,
604
+ "step": 8500
605
+ },
606
+ {
607
+ "epoch": 0.01,
608
+ "grad_norm": 46.75,
609
+ "learning_rate": 3.830393728843756e-05,
610
+ "loss": 1.1716,
611
+ "step": 8600
612
+ },
613
+ {
614
+ "epoch": 0.01,
615
+ "grad_norm": 54.75,
616
+ "learning_rate": 3.874933190807055e-05,
617
+ "loss": 1.042,
618
+ "step": 8700
619
+ },
620
+ {
621
+ "epoch": 0.01,
622
+ "grad_norm": 51.0,
623
+ "learning_rate": 3.919472652770354e-05,
624
+ "loss": 1.1756,
625
+ "step": 8800
626
+ },
627
+ {
628
+ "epoch": 0.01,
629
+ "grad_norm": 48.25,
630
+ "learning_rate": 3.964012114733654e-05,
631
+ "loss": 1.2597,
632
+ "step": 8900
633
+ },
634
+ {
635
+ "epoch": 0.01,
636
+ "grad_norm": 14.75,
637
+ "learning_rate": 4.008551576696954e-05,
638
+ "loss": 1.0449,
639
+ "step": 9000
640
+ },
641
+ {
642
+ "epoch": 0.01,
643
+ "grad_norm": 18.25,
644
+ "learning_rate": 4.0530910386602536e-05,
645
+ "loss": 1.2163,
646
+ "step": 9100
647
+ },
648
+ {
649
+ "epoch": 0.01,
650
+ "grad_norm": 80.0,
651
+ "learning_rate": 4.097630500623553e-05,
652
+ "loss": 1.2302,
653
+ "step": 9200
654
+ },
655
+ {
656
+ "epoch": 0.01,
657
+ "grad_norm": 32.0,
658
+ "learning_rate": 4.142169962586852e-05,
659
+ "loss": 1.1843,
660
+ "step": 9300
661
+ },
662
+ {
663
+ "epoch": 0.01,
664
+ "grad_norm": 44.25,
665
+ "learning_rate": 4.186709424550152e-05,
666
+ "loss": 1.0384,
667
+ "step": 9400
668
+ },
669
+ {
670
+ "epoch": 0.01,
671
+ "grad_norm": 66.5,
672
+ "learning_rate": 4.231248886513451e-05,
673
+ "loss": 1.0315,
674
+ "step": 9500
675
+ },
676
+ {
677
+ "epoch": 0.01,
678
+ "grad_norm": 72.5,
679
+ "learning_rate": 4.2757883484767506e-05,
680
+ "loss": 1.1746,
681
+ "step": 9600
682
+ },
683
+ {
684
+ "epoch": 0.01,
685
+ "grad_norm": 37.5,
686
+ "learning_rate": 4.3203278104400504e-05,
687
+ "loss": 1.2093,
688
+ "step": 9700
689
+ },
690
+ {
691
+ "epoch": 0.01,
692
+ "grad_norm": 81.5,
693
+ "learning_rate": 4.3648672724033495e-05,
694
+ "loss": 1.3342,
695
+ "step": 9800
696
+ },
697
+ {
698
+ "epoch": 0.01,
699
+ "grad_norm": 88.5,
700
+ "learning_rate": 4.409406734366649e-05,
701
+ "loss": 1.1162,
702
+ "step": 9900
703
+ },
704
+ {
705
+ "epoch": 0.01,
706
+ "grad_norm": 356.0,
707
+ "learning_rate": 4.4539461963299484e-05,
708
+ "loss": 0.8431,
709
+ "step": 10000
710
+ },
711
+ {
712
+ "epoch": 0.01,
713
+ "grad_norm": 75.5,
714
+ "learning_rate": 4.498485658293248e-05,
715
+ "loss": 1.15,
716
+ "step": 10100
717
+ },
718
+ {
719
+ "epoch": 0.01,
720
+ "grad_norm": 51.0,
721
+ "learning_rate": 4.543025120256548e-05,
722
+ "loss": 1.1635,
723
+ "step": 10200
724
+ },
725
+ {
726
+ "epoch": 0.01,
727
+ "grad_norm": 136.0,
728
+ "learning_rate": 4.587564582219847e-05,
729
+ "loss": 1.1175,
730
+ "step": 10300
731
+ },
732
+ {
733
+ "epoch": 0.01,
734
+ "grad_norm": 180.0,
735
+ "learning_rate": 4.632104044183146e-05,
736
+ "loss": 1.0931,
737
+ "step": 10400
738
+ },
739
+ {
740
+ "epoch": 0.01,
741
+ "grad_norm": 107.5,
742
+ "learning_rate": 4.676643506146446e-05,
743
+ "loss": 1.3118,
744
+ "step": 10500
745
+ },
746
+ {
747
+ "epoch": 0.01,
748
+ "grad_norm": 34.0,
749
+ "learning_rate": 4.721182968109745e-05,
750
+ "loss": 1.0301,
751
+ "step": 10600
752
+ },
753
+ {
754
+ "epoch": 0.01,
755
+ "grad_norm": 33.75,
756
+ "learning_rate": 4.765722430073045e-05,
757
+ "loss": 0.9912,
758
+ "step": 10700
759
+ },
760
+ {
761
+ "epoch": 0.01,
762
+ "grad_norm": 48.5,
763
+ "learning_rate": 4.810261892036345e-05,
764
+ "loss": 1.1649,
765
+ "step": 10800
766
+ },
767
+ {
768
+ "epoch": 0.01,
769
+ "grad_norm": 88.5,
770
+ "learning_rate": 4.854801353999644e-05,
771
+ "loss": 1.4056,
772
+ "step": 10900
773
+ },
774
+ {
775
+ "epoch": 0.01,
776
+ "grad_norm": 143.0,
777
+ "learning_rate": 4.899340815962944e-05,
778
+ "loss": 1.1315,
779
+ "step": 11000
780
+ },
781
+ {
782
+ "epoch": 0.01,
783
+ "grad_norm": 26.5,
784
+ "learning_rate": 4.943880277926243e-05,
785
+ "loss": 1.231,
786
+ "step": 11100
787
+ },
788
+ {
789
+ "epoch": 0.01,
790
+ "grad_norm": 47.75,
791
+ "learning_rate": 4.988419739889542e-05,
792
+ "loss": 1.2519,
793
+ "step": 11200
794
+ },
795
+ {
796
+ "epoch": 0.01,
797
+ "grad_norm": 4.5625,
798
+ "learning_rate": 4.999667068583872e-05,
799
+ "loss": 1.1036,
800
+ "step": 11300
801
+ },
802
+ {
803
+ "epoch": 0.01,
804
+ "grad_norm": 72.5,
805
+ "learning_rate": 4.99921716126478e-05,
806
+ "loss": 1.0886,
807
+ "step": 11400
808
+ },
809
+ {
810
+ "epoch": 0.01,
811
+ "grad_norm": 102.5,
812
+ "learning_rate": 4.998767253945688e-05,
813
+ "loss": 1.1742,
814
+ "step": 11500
815
+ },
816
+ {
817
+ "epoch": 0.01,
818
+ "grad_norm": 127.0,
819
+ "learning_rate": 4.9983173466265954e-05,
820
+ "loss": 1.2533,
821
+ "step": 11600
822
+ },
823
+ {
824
+ "epoch": 0.01,
825
+ "grad_norm": 221.0,
826
+ "learning_rate": 4.997867439307503e-05,
827
+ "loss": 1.1356,
828
+ "step": 11700
829
+ },
830
+ {
831
+ "epoch": 0.01,
832
+ "grad_norm": 132.0,
833
+ "learning_rate": 4.997417531988411e-05,
834
+ "loss": 1.0534,
835
+ "step": 11800
836
+ },
837
+ {
838
+ "epoch": 0.01,
839
+ "grad_norm": 30.625,
840
+ "learning_rate": 4.996967624669318e-05,
841
+ "loss": 0.936,
842
+ "step": 11900
843
+ },
844
+ {
845
+ "epoch": 0.01,
846
+ "grad_norm": 56.5,
847
+ "learning_rate": 4.9965177173502256e-05,
848
+ "loss": 1.0134,
849
+ "step": 12000
850
+ },
851
+ {
852
+ "epoch": 0.01,
853
+ "grad_norm": 37.75,
854
+ "learning_rate": 4.996067810031134e-05,
855
+ "loss": 1.1623,
856
+ "step": 12100
857
+ },
858
+ {
859
+ "epoch": 0.01,
860
+ "grad_norm": 175.0,
861
+ "learning_rate": 4.995617902712041e-05,
862
+ "loss": 1.0928,
863
+ "step": 12200
864
+ },
865
+ {
866
+ "epoch": 0.01,
867
+ "grad_norm": 44.5,
868
+ "learning_rate": 4.9951679953929495e-05,
869
+ "loss": 1.2636,
870
+ "step": 12300
871
+ },
872
+ {
873
+ "epoch": 0.01,
874
+ "grad_norm": 20.625,
875
+ "learning_rate": 4.994718088073857e-05,
876
+ "loss": 1.07,
877
+ "step": 12400
878
+ },
879
+ {
880
+ "epoch": 0.01,
881
+ "grad_norm": 28.75,
882
+ "learning_rate": 4.9942681807547646e-05,
883
+ "loss": 0.9899,
884
+ "step": 12500
885
+ },
886
+ {
887
+ "epoch": 0.01,
888
+ "grad_norm": 132.0,
889
+ "learning_rate": 4.993818273435673e-05,
890
+ "loss": 1.1851,
891
+ "step": 12600
892
+ },
893
+ {
894
+ "epoch": 0.01,
895
+ "grad_norm": 133.0,
896
+ "learning_rate": 4.9933683661165803e-05,
897
+ "loss": 1.0886,
898
+ "step": 12700
899
+ },
900
+ {
901
+ "epoch": 0.01,
902
+ "grad_norm": 84.0,
903
+ "learning_rate": 4.992918458797488e-05,
904
+ "loss": 1.0992,
905
+ "step": 12800
906
+ },
907
+ {
908
+ "epoch": 0.01,
909
+ "grad_norm": 0.48046875,
910
+ "learning_rate": 4.992468551478396e-05,
911
+ "loss": 1.1081,
912
+ "step": 12900
913
+ },
914
+ {
915
+ "epoch": 0.01,
916
+ "grad_norm": 33.0,
917
+ "learning_rate": 4.9920186441593036e-05,
918
+ "loss": 1.3126,
919
+ "step": 13000
920
+ },
921
+ {
922
+ "epoch": 0.01,
923
+ "grad_norm": 27.5,
924
+ "learning_rate": 4.991568736840211e-05,
925
+ "loss": 1.1685,
926
+ "step": 13100
927
+ },
928
+ {
929
+ "epoch": 0.01,
930
+ "grad_norm": 53.25,
931
+ "learning_rate": 4.991118829521119e-05,
932
+ "loss": 1.118,
933
+ "step": 13200
934
+ },
935
+ {
936
+ "epoch": 0.01,
937
+ "grad_norm": 410.0,
938
+ "learning_rate": 4.990668922202026e-05,
939
+ "loss": 1.0968,
940
+ "step": 13300
941
+ },
942
+ {
943
+ "epoch": 0.01,
944
+ "grad_norm": 56.25,
945
+ "learning_rate": 4.9902190148829344e-05,
946
+ "loss": 1.1793,
947
+ "step": 13400
948
+ },
949
+ {
950
+ "epoch": 0.01,
951
+ "grad_norm": 25.75,
952
+ "learning_rate": 4.989769107563842e-05,
953
+ "loss": 1.1671,
954
+ "step": 13500
955
+ },
956
+ {
957
+ "epoch": 0.01,
958
+ "grad_norm": 26.25,
959
+ "learning_rate": 4.9893192002447495e-05,
960
+ "loss": 1.1825,
961
+ "step": 13600
962
+ },
963
+ {
964
+ "epoch": 0.01,
965
+ "grad_norm": 105.5,
966
+ "learning_rate": 4.988869292925658e-05,
967
+ "loss": 1.1509,
968
+ "step": 13700
969
+ },
970
+ {
971
+ "epoch": 0.01,
972
+ "grad_norm": 79.5,
973
+ "learning_rate": 4.988419385606565e-05,
974
+ "loss": 1.1337,
975
+ "step": 13800
976
+ },
977
+ {
978
+ "epoch": 0.01,
979
+ "grad_norm": 36.75,
980
+ "learning_rate": 4.987969478287473e-05,
981
+ "loss": 1.0261,
982
+ "step": 13900
983
+ },
984
+ {
985
+ "epoch": 0.01,
986
+ "grad_norm": 48.75,
987
+ "learning_rate": 4.987519570968381e-05,
988
+ "loss": 1.2461,
989
+ "step": 14000
990
+ },
991
+ {
992
+ "epoch": 0.01,
993
+ "grad_norm": 52.75,
994
+ "learning_rate": 4.9870696636492885e-05,
995
+ "loss": 1.1742,
996
+ "step": 14100
997
+ },
998
+ {
999
+ "epoch": 0.01,
1000
+ "grad_norm": 236.0,
1001
+ "learning_rate": 4.986619756330197e-05,
1002
+ "loss": 0.9742,
1003
+ "step": 14200
1004
+ },
1005
+ {
1006
+ "epoch": 0.01,
1007
+ "grad_norm": 402.0,
1008
+ "learning_rate": 4.986169849011104e-05,
1009
+ "loss": 1.2615,
1010
+ "step": 14300
1011
+ },
1012
+ {
1013
+ "epoch": 0.01,
1014
+ "grad_norm": 120.0,
1015
+ "learning_rate": 4.985719941692012e-05,
1016
+ "loss": 1.3339,
1017
+ "step": 14400
1018
+ },
1019
+ {
1020
+ "epoch": 0.01,
1021
+ "grad_norm": 66.0,
1022
+ "learning_rate": 4.9852700343729193e-05,
1023
+ "loss": 1.2984,
1024
+ "step": 14500
1025
+ },
1026
+ {
1027
+ "epoch": 0.01,
1028
+ "grad_norm": 37.5,
1029
+ "learning_rate": 4.984820127053827e-05,
1030
+ "loss": 0.9931,
1031
+ "step": 14600
1032
+ },
1033
+ {
1034
+ "epoch": 0.01,
1035
+ "grad_norm": 26.625,
1036
+ "learning_rate": 4.9843702197347344e-05,
1037
+ "loss": 1.1177,
1038
+ "step": 14700
1039
+ },
1040
+ {
1041
+ "epoch": 0.01,
1042
+ "grad_norm": 143.0,
1043
+ "learning_rate": 4.9839203124156426e-05,
1044
+ "loss": 1.1625,
1045
+ "step": 14800
1046
+ },
1047
+ {
1048
+ "epoch": 0.01,
1049
+ "grad_norm": 58.75,
1050
+ "learning_rate": 4.98347040509655e-05,
1051
+ "loss": 1.2321,
1052
+ "step": 14900
1053
+ },
1054
+ {
1055
+ "epoch": 0.01,
1056
+ "grad_norm": 27.625,
1057
+ "learning_rate": 4.9830204977774584e-05,
1058
+ "loss": 1.2545,
1059
+ "step": 15000
1060
+ },
1061
+ {
1062
+ "epoch": 0.01,
1063
+ "grad_norm": 40.75,
1064
+ "learning_rate": 4.982570590458366e-05,
1065
+ "loss": 1.1757,
1066
+ "step": 15100
1067
+ },
1068
+ {
1069
+ "epoch": 0.01,
1070
+ "grad_norm": 44.5,
1071
+ "learning_rate": 4.9821206831392734e-05,
1072
+ "loss": 1.1684,
1073
+ "step": 15200
1074
+ },
1075
+ {
1076
+ "epoch": 0.01,
1077
+ "grad_norm": 31.0,
1078
+ "learning_rate": 4.9816707758201816e-05,
1079
+ "loss": 1.2152,
1080
+ "step": 15300
1081
+ },
1082
+ {
1083
+ "epoch": 0.01,
1084
+ "grad_norm": 56.5,
1085
+ "learning_rate": 4.981220868501089e-05,
1086
+ "loss": 1.2536,
1087
+ "step": 15400
1088
+ },
1089
+ {
1090
+ "epoch": 0.01,
1091
+ "grad_norm": 93.0,
1092
+ "learning_rate": 4.980770961181997e-05,
1093
+ "loss": 1.2398,
1094
+ "step": 15500
1095
+ },
1096
+ {
1097
+ "epoch": 0.01,
1098
+ "grad_norm": 63.5,
1099
+ "learning_rate": 4.980321053862905e-05,
1100
+ "loss": 1.0495,
1101
+ "step": 15600
1102
+ },
1103
+ {
1104
+ "epoch": 0.01,
1105
+ "grad_norm": 294.0,
1106
+ "learning_rate": 4.9798711465438125e-05,
1107
+ "loss": 1.2303,
1108
+ "step": 15700
1109
+ },
1110
+ {
1111
+ "epoch": 0.01,
1112
+ "grad_norm": 97.0,
1113
+ "learning_rate": 4.97942123922472e-05,
1114
+ "loss": 1.0398,
1115
+ "step": 15800
1116
+ },
1117
+ {
1118
+ "epoch": 0.01,
1119
+ "grad_norm": 30.125,
1120
+ "learning_rate": 4.9789713319056275e-05,
1121
+ "loss": 1.2357,
1122
+ "step": 15900
1123
+ },
1124
+ {
1125
+ "epoch": 0.01,
1126
+ "grad_norm": 64.0,
1127
+ "learning_rate": 4.978521424586535e-05,
1128
+ "loss": 1.1963,
1129
+ "step": 16000
1130
+ },
1131
+ {
1132
+ "epoch": 0.01,
1133
+ "grad_norm": 69.0,
1134
+ "learning_rate": 4.978071517267443e-05,
1135
+ "loss": 1.1217,
1136
+ "step": 16100
1137
+ },
1138
+ {
1139
+ "epoch": 0.01,
1140
+ "grad_norm": 73.0,
1141
+ "learning_rate": 4.977621609948351e-05,
1142
+ "loss": 1.3172,
1143
+ "step": 16200
1144
+ },
1145
+ {
1146
+ "epoch": 0.01,
1147
+ "grad_norm": 6.4375,
1148
+ "learning_rate": 4.977171702629258e-05,
1149
+ "loss": 1.0252,
1150
+ "step": 16300
1151
+ },
1152
+ {
1153
+ "epoch": 0.01,
1154
+ "grad_norm": 13.5625,
1155
+ "learning_rate": 4.9767217953101666e-05,
1156
+ "loss": 1.0254,
1157
+ "step": 16400
1158
+ },
1159
+ {
1160
+ "epoch": 0.01,
1161
+ "grad_norm": 28.375,
1162
+ "learning_rate": 4.976271887991074e-05,
1163
+ "loss": 1.116,
1164
+ "step": 16500
1165
+ },
1166
+ {
1167
+ "epoch": 0.01,
1168
+ "grad_norm": 664.0,
1169
+ "learning_rate": 4.9758219806719816e-05,
1170
+ "loss": 1.1861,
1171
+ "step": 16600
1172
+ },
1173
+ {
1174
+ "epoch": 0.01,
1175
+ "grad_norm": 157.0,
1176
+ "learning_rate": 4.97537207335289e-05,
1177
+ "loss": 1.1762,
1178
+ "step": 16700
1179
+ },
1180
+ {
1181
+ "epoch": 0.01,
1182
+ "grad_norm": 42.75,
1183
+ "learning_rate": 4.9749221660337974e-05,
1184
+ "loss": 1.2372,
1185
+ "step": 16800
1186
+ },
1187
+ {
1188
+ "epoch": 0.02,
1189
+ "grad_norm": 2.578125,
1190
+ "learning_rate": 4.974472258714705e-05,
1191
+ "loss": 1.1629,
1192
+ "step": 16900
1193
+ },
1194
+ {
1195
+ "epoch": 0.02,
1196
+ "grad_norm": 196.0,
1197
+ "learning_rate": 4.974022351395613e-05,
1198
+ "loss": 1.1746,
1199
+ "step": 17000
1200
+ },
1201
+ {
1202
+ "epoch": 0.02,
1203
+ "grad_norm": 43.5,
1204
+ "learning_rate": 4.97357244407652e-05,
1205
+ "loss": 1.1731,
1206
+ "step": 17100
1207
+ },
1208
+ {
1209
+ "epoch": 0.02,
1210
+ "grad_norm": 22.375,
1211
+ "learning_rate": 4.973122536757428e-05,
1212
+ "loss": 1.0003,
1213
+ "step": 17200
1214
+ },
1215
+ {
1216
+ "epoch": 0.02,
1217
+ "grad_norm": 44.75,
1218
+ "learning_rate": 4.972672629438336e-05,
1219
+ "loss": 1.0736,
1220
+ "step": 17300
1221
+ },
1222
+ {
1223
+ "epoch": 0.02,
1224
+ "grad_norm": 2.5625,
1225
+ "learning_rate": 4.972222722119243e-05,
1226
+ "loss": 1.2785,
1227
+ "step": 17400
1228
+ },
1229
+ {
1230
+ "epoch": 0.02,
1231
+ "grad_norm": 31.5,
1232
+ "learning_rate": 4.9717728148001515e-05,
1233
+ "loss": 1.0953,
1234
+ "step": 17500
1235
+ },
1236
+ {
1237
+ "epoch": 0.02,
1238
+ "grad_norm": 83.5,
1239
+ "learning_rate": 4.971322907481059e-05,
1240
+ "loss": 1.1549,
1241
+ "step": 17600
1242
+ },
1243
+ {
1244
+ "epoch": 0.02,
1245
+ "grad_norm": 54.0,
1246
+ "learning_rate": 4.970873000161967e-05,
1247
+ "loss": 1.3649,
1248
+ "step": 17700
1249
+ },
1250
+ {
1251
+ "epoch": 0.02,
1252
+ "grad_norm": 182.0,
1253
+ "learning_rate": 4.970423092842875e-05,
1254
+ "loss": 1.109,
1255
+ "step": 17800
1256
+ },
1257
+ {
1258
+ "epoch": 0.02,
1259
+ "grad_norm": 233.0,
1260
+ "learning_rate": 4.969973185523782e-05,
1261
+ "loss": 1.1443,
1262
+ "step": 17900
1263
+ },
1264
+ {
1265
+ "epoch": 0.02,
1266
+ "grad_norm": 65.5,
1267
+ "learning_rate": 4.9695232782046905e-05,
1268
+ "loss": 1.1159,
1269
+ "step": 18000
1270
+ }
1271
+ ],
1272
+ "logging_steps": 100,
1273
+ "max_steps": 1122566,
1274
+ "num_input_tokens_seen": 0,
1275
+ "num_train_epochs": 1,
1276
+ "save_steps": 6000,
1277
+ "total_flos": 2.850501750362112e+17,
1278
+ "train_batch_size": 1,
1279
+ "trial_name": null,
1280
+ "trial_params": null
1281
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc90d48f9fc00eb358455da48f83dbece53038ef6a15b000e4fbd16f503ba0e6
3
+ size 4856