gabrielmbmb HF staff commited on
Commit
b58c84d
1 Parent(s): 4449638

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: gabrielmbmb/Upcycled-Qwen1.5-MoE2.7B
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **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 0.10.0
adapter_config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "gabrielmbmb/Upcycled-Qwen1.5-MoE2.7B",
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": 64,
14
+ "lora_dropout": 0.0,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": [
18
+ "lm_head"
19
+ ],
20
+ "peft_type": "LORA",
21
+ "r": 32,
22
+ "rank_pattern": {},
23
+ "revision": null,
24
+ "target_modules": [
25
+ "up_proj",
26
+ "o_proj",
27
+ "k_proj",
28
+ "gate",
29
+ "q_proj",
30
+ "shared_expert_gate",
31
+ "v_proj",
32
+ "down_proj",
33
+ "gate_proj"
34
+ ],
35
+ "task_type": "CAUSAL_LM",
36
+ "use_dora": false,
37
+ "use_rslora": false
38
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc74711cb80cd2f368730278bbc66f0dccae7ceec53b0d92abd237ef174689b4
3
+ size 3272016504
added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "<|endoftext|>": 151643,
3
+ "<|im_end|>": 151645,
4
+ "<|im_start|>": 151644
5
+ }
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:c3e2166b49ce624fd811acb845fe3ff104a3739f4ab1201738da82b0c9e3f6fe
3
+ size 6549209908
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53ee4688496b0162130b060f83f318885b4d612c5e7e4e82a0bb98689df63eb3
3
+ size 1064
special_tokens_map.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>"
5
+ ],
6
+ "eos_token": {
7
+ "content": "<|endoftext|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "pad_token": {
14
+ "content": "<|endoftext|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ }
20
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ },
29
+ "additional_special_tokens": [
30
+ "<|im_start|>",
31
+ "<|im_end|>"
32
+ ],
33
+ "bos_token": null,
34
+ "chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ content }}{% elif message['role'] == 'assistant' %}{{ content + '\\n' }}{% endif %}{% endfor %}",
35
+ "clean_up_tokenization_spaces": false,
36
+ "eos_token": "<|endoftext|>",
37
+ "errors": "replace",
38
+ "model_max_length": 32768,
39
+ "pad_token": "<|endoftext|>",
40
+ "padding_side": "right",
41
+ "split_special_tokens": false,
42
+ "tokenizer_class": "Qwen2Tokenizer",
43
+ "unk_token": null
44
+ }
trainer_state.json ADDED
@@ -0,0 +1,1421 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.6666666666666666,
5
+ "eval_steps": 500,
6
+ "global_step": 2000,
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": 1.2757867574691772,
14
+ "learning_rate": 0.000499986292341378,
15
+ "loss": 5.9015,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.01,
20
+ "grad_norm": 0.7096672654151917,
21
+ "learning_rate": 0.0004999451708687113,
22
+ "loss": 3.9877,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.01,
27
+ "grad_norm": 0.6350783109664917,
28
+ "learning_rate": 0.0004998766400914329,
29
+ "loss": 3.7232,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.01,
34
+ "grad_norm": 0.5088619589805603,
35
+ "learning_rate": 0.0004997807075247146,
36
+ "loss": 3.552,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.02,
41
+ "grad_norm": 0.4739762842655182,
42
+ "learning_rate": 0.0004996573836886434,
43
+ "loss": 3.5127,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.02,
48
+ "grad_norm": 0.628942608833313,
49
+ "learning_rate": 0.0004995066821070679,
50
+ "loss": 3.3798,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.02,
55
+ "grad_norm": 0.5002753138542175,
56
+ "learning_rate": 0.0004993286193061145,
57
+ "loss": 3.3999,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.03,
62
+ "grad_norm": 0.4983285963535309,
63
+ "learning_rate": 0.0004991232148123761,
64
+ "loss": 3.3398,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.03,
69
+ "grad_norm": 0.4371359050273895,
70
+ "learning_rate": 0.00049889049115077,
71
+ "loss": 3.3405,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.03,
76
+ "grad_norm": 0.5125981569290161,
77
+ "learning_rate": 0.0004986304738420684,
78
+ "loss": 3.3053,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.04,
83
+ "grad_norm": 0.47835057973861694,
84
+ "learning_rate": 0.000498343191400099,
85
+ "loss": 3.2388,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.04,
90
+ "grad_norm": 0.4769553244113922,
91
+ "learning_rate": 0.0004980286753286195,
92
+ "loss": 3.2004,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.04,
97
+ "grad_norm": 0.44102832674980164,
98
+ "learning_rate": 0.0004976869601178609,
99
+ "loss": 3.2301,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.05,
104
+ "grad_norm": 0.44598281383514404,
105
+ "learning_rate": 0.0004973180832407472,
106
+ "loss": 3.2284,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.05,
111
+ "grad_norm": 0.5305857062339783,
112
+ "learning_rate": 0.0004969220851487844,
113
+ "loss": 3.1978,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.05,
118
+ "grad_norm": 0.5015985369682312,
119
+ "learning_rate": 0.0004964990092676262,
120
+ "loss": 3.198,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.06,
125
+ "grad_norm": 0.49595481157302856,
126
+ "learning_rate": 0.0004960489019923105,
127
+ "loss": 3.2582,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.06,
132
+ "grad_norm": 0.4686504602432251,
133
+ "learning_rate": 0.0004955718126821722,
134
+ "loss": 3.1974,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.06,
139
+ "grad_norm": 0.4878421425819397,
140
+ "learning_rate": 0.0004950677936554305,
141
+ "loss": 3.1467,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.07,
146
+ "grad_norm": 0.476806640625,
147
+ "learning_rate": 0.0004945369001834514,
148
+ "loss": 3.1321,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.07,
153
+ "grad_norm": 0.5151681900024414,
154
+ "learning_rate": 0.0004939791904846869,
155
+ "loss": 3.1478,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.07,
160
+ "grad_norm": 0.4726090133190155,
161
+ "learning_rate": 0.0004933947257182901,
162
+ "loss": 3.1757,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.08,
167
+ "grad_norm": 0.4868369698524475,
168
+ "learning_rate": 0.000492783569977409,
169
+ "loss": 3.1573,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.08,
174
+ "grad_norm": 0.4568879306316376,
175
+ "learning_rate": 0.0004921457902821578,
176
+ "loss": 3.2129,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.08,
181
+ "grad_norm": 0.45109352469444275,
182
+ "learning_rate": 0.0004914814565722671,
183
+ "loss": 3.1417,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.09,
188
+ "grad_norm": 0.5096346139907837,
189
+ "learning_rate": 0.0004907906416994146,
190
+ "loss": 3.1397,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.09,
195
+ "grad_norm": 0.44307172298431396,
196
+ "learning_rate": 0.0004900734214192358,
197
+ "loss": 3.1851,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.09,
202
+ "grad_norm": 0.469777375459671,
203
+ "learning_rate": 0.0004893298743830168,
204
+ "loss": 3.1117,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.1,
209
+ "grad_norm": 0.4518013596534729,
210
+ "learning_rate": 0.0004885600821290692,
211
+ "loss": 3.0941,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.1,
216
+ "grad_norm": 0.4657439589500427,
217
+ "learning_rate": 0.0004877641290737884,
218
+ "loss": 3.1936,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.1,
223
+ "grad_norm": 0.4461677372455597,
224
+ "learning_rate": 0.00048694210250239646,
225
+ "loss": 3.1158,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.11,
230
+ "grad_norm": 0.454722136259079,
231
+ "learning_rate": 0.0004860940925593703,
232
+ "loss": 3.0921,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.11,
237
+ "grad_norm": 0.4858105480670929,
238
+ "learning_rate": 0.0004852201922385564,
239
+ "loss": 3.1601,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.11,
244
+ "grad_norm": 0.4848730266094208,
245
+ "learning_rate": 0.0004843204973729729,
246
+ "loss": 3.1165,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.12,
251
+ "grad_norm": 0.5170342922210693,
252
+ "learning_rate": 0.00048339510662430044,
253
+ "loss": 3.0897,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.12,
258
+ "grad_norm": 0.4945329427719116,
259
+ "learning_rate": 0.00048244412147206283,
260
+ "loss": 3.0792,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.12,
265
+ "grad_norm": 0.4752379357814789,
266
+ "learning_rate": 0.0004814676462024987,
267
+ "loss": 3.035,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.13,
272
+ "grad_norm": 0.4935299754142761,
273
+ "learning_rate": 0.00048046578789712516,
274
+ "loss": 3.1129,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.13,
279
+ "grad_norm": 0.47018569707870483,
280
+ "learning_rate": 0.00047943865642099525,
281
+ "loss": 3.1255,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.13,
286
+ "grad_norm": 0.45771998167037964,
287
+ "learning_rate": 0.0004783863644106502,
288
+ "loss": 3.0546,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.14,
293
+ "grad_norm": 0.4871847927570343,
294
+ "learning_rate": 0.00047730902726176715,
295
+ "loss": 3.1176,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.14,
300
+ "grad_norm": 0.5023790001869202,
301
+ "learning_rate": 0.0004762067631165049,
302
+ "loss": 3.1396,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.14,
307
+ "grad_norm": 0.5331537127494812,
308
+ "learning_rate": 0.0004750796928505484,
309
+ "loss": 3.0541,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 0.15,
314
+ "grad_norm": 0.46206673979759216,
315
+ "learning_rate": 0.0004739279400598532,
316
+ "loss": 3.1429,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 0.15,
321
+ "grad_norm": 0.5062265992164612,
322
+ "learning_rate": 0.00047275163104709196,
323
+ "loss": 3.0668,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 0.15,
328
+ "grad_norm": 0.7376482486724854,
329
+ "learning_rate": 0.00047155089480780364,
330
+ "loss": 3.1377,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 0.16,
335
+ "grad_norm": 0.5349658727645874,
336
+ "learning_rate": 0.00047032586301624804,
337
+ "loss": 3.0838,
338
+ "step": 470
339
+ },
340
+ {
341
+ "epoch": 0.16,
342
+ "grad_norm": 0.49428579211235046,
343
+ "learning_rate": 0.0004690766700109659,
344
+ "loss": 3.1257,
345
+ "step": 480
346
+ },
347
+ {
348
+ "epoch": 0.16,
349
+ "grad_norm": 0.4835917353630066,
350
+ "learning_rate": 0.0004678034527800474,
351
+ "loss": 3.0709,
352
+ "step": 490
353
+ },
354
+ {
355
+ "epoch": 0.17,
356
+ "grad_norm": 0.5094427466392517,
357
+ "learning_rate": 0.00046650635094610973,
358
+ "loss": 3.0692,
359
+ "step": 500
360
+ },
361
+ {
362
+ "epoch": 0.17,
363
+ "grad_norm": 0.5574087500572205,
364
+ "learning_rate": 0.0004651855067509859,
365
+ "loss": 3.0667,
366
+ "step": 510
367
+ },
368
+ {
369
+ "epoch": 0.17,
370
+ "grad_norm": 0.5003999471664429,
371
+ "learning_rate": 0.0004638410650401267,
372
+ "loss": 3.0311,
373
+ "step": 520
374
+ },
375
+ {
376
+ "epoch": 0.18,
377
+ "grad_norm": 0.5170697569847107,
378
+ "learning_rate": 0.000462473173246716,
379
+ "loss": 3.1082,
380
+ "step": 530
381
+ },
382
+ {
383
+ "epoch": 0.18,
384
+ "grad_norm": 0.5004311800003052,
385
+ "learning_rate": 0.00046108198137550377,
386
+ "loss": 3.0825,
387
+ "step": 540
388
+ },
389
+ {
390
+ "epoch": 0.18,
391
+ "grad_norm": 0.49480965733528137,
392
+ "learning_rate": 0.00045966764198635603,
393
+ "loss": 3.0888,
394
+ "step": 550
395
+ },
396
+ {
397
+ "epoch": 0.19,
398
+ "grad_norm": 0.49261385202407837,
399
+ "learning_rate": 0.00045823031017752484,
400
+ "loss": 3.1568,
401
+ "step": 560
402
+ },
403
+ {
404
+ "epoch": 0.19,
405
+ "grad_norm": 0.4577986001968384,
406
+ "learning_rate": 0.00045677014356864043,
407
+ "loss": 3.0953,
408
+ "step": 570
409
+ },
410
+ {
411
+ "epoch": 0.19,
412
+ "grad_norm": 0.4814681112766266,
413
+ "learning_rate": 0.000455287302283426,
414
+ "loss": 3.0801,
415
+ "step": 580
416
+ },
417
+ {
418
+ "epoch": 0.2,
419
+ "grad_norm": 0.563042402267456,
420
+ "learning_rate": 0.00045378194893213854,
421
+ "loss": 3.0719,
422
+ "step": 590
423
+ },
424
+ {
425
+ "epoch": 0.2,
426
+ "grad_norm": 0.5507716536521912,
427
+ "learning_rate": 0.0004522542485937369,
428
+ "loss": 3.0724,
429
+ "step": 600
430
+ },
431
+ {
432
+ "epoch": 0.2,
433
+ "grad_norm": 0.5448073148727417,
434
+ "learning_rate": 0.0004507043687977787,
435
+ "loss": 3.0294,
436
+ "step": 610
437
+ },
438
+ {
439
+ "epoch": 0.21,
440
+ "grad_norm": 0.47773197293281555,
441
+ "learning_rate": 0.00044913247950604905,
442
+ "loss": 3.0682,
443
+ "step": 620
444
+ },
445
+ {
446
+ "epoch": 0.21,
447
+ "grad_norm": 0.4662880301475525,
448
+ "learning_rate": 0.0004475387530939226,
449
+ "loss": 3.0106,
450
+ "step": 630
451
+ },
452
+ {
453
+ "epoch": 0.21,
454
+ "grad_norm": 0.4735540747642517,
455
+ "learning_rate": 0.00044592336433145995,
456
+ "loss": 3.1345,
457
+ "step": 640
458
+ },
459
+ {
460
+ "epoch": 0.22,
461
+ "grad_norm": 0.4746765196323395,
462
+ "learning_rate": 0.0004442864903642427,
463
+ "loss": 3.0772,
464
+ "step": 650
465
+ },
466
+ {
467
+ "epoch": 0.22,
468
+ "grad_norm": 0.45668378472328186,
469
+ "learning_rate": 0.0004426283106939473,
470
+ "loss": 3.1174,
471
+ "step": 660
472
+ },
473
+ {
474
+ "epoch": 0.22,
475
+ "grad_norm": 0.4704893231391907,
476
+ "learning_rate": 0.0004409490071586606,
477
+ "loss": 3.0816,
478
+ "step": 670
479
+ },
480
+ {
481
+ "epoch": 0.23,
482
+ "grad_norm": 0.5290801525115967,
483
+ "learning_rate": 0.0004392487639129391,
484
+ "loss": 3.1089,
485
+ "step": 680
486
+ },
487
+ {
488
+ "epoch": 0.23,
489
+ "grad_norm": 0.47564446926116943,
490
+ "learning_rate": 0.0004375277674076149,
491
+ "loss": 3.082,
492
+ "step": 690
493
+ },
494
+ {
495
+ "epoch": 0.23,
496
+ "grad_norm": 0.4995107352733612,
497
+ "learning_rate": 0.00043578620636934855,
498
+ "loss": 3.1992,
499
+ "step": 700
500
+ },
501
+ {
502
+ "epoch": 0.24,
503
+ "grad_norm": 0.48856520652770996,
504
+ "learning_rate": 0.00043402427177993366,
505
+ "loss": 3.0598,
506
+ "step": 710
507
+ },
508
+ {
509
+ "epoch": 0.24,
510
+ "grad_norm": 0.4874037802219391,
511
+ "learning_rate": 0.00043224215685535287,
512
+ "loss": 3.0753,
513
+ "step": 720
514
+ },
515
+ {
516
+ "epoch": 0.24,
517
+ "grad_norm": 0.45193690061569214,
518
+ "learning_rate": 0.00043044005702459054,
519
+ "loss": 2.9601,
520
+ "step": 730
521
+ },
522
+ {
523
+ "epoch": 0.25,
524
+ "grad_norm": 0.46975770592689514,
525
+ "learning_rate": 0.00042861816990820087,
526
+ "loss": 3.0511,
527
+ "step": 740
528
+ },
529
+ {
530
+ "epoch": 0.25,
531
+ "grad_norm": 0.5442278981208801,
532
+ "learning_rate": 0.00042677669529663686,
533
+ "loss": 3.0898,
534
+ "step": 750
535
+ },
536
+ {
537
+ "epoch": 0.25,
538
+ "grad_norm": 0.5437372922897339,
539
+ "learning_rate": 0.00042491583512834137,
540
+ "loss": 3.0768,
541
+ "step": 760
542
+ },
543
+ {
544
+ "epoch": 0.26,
545
+ "grad_norm": 0.4911404848098755,
546
+ "learning_rate": 0.0004230357934676017,
547
+ "loss": 3.1239,
548
+ "step": 770
549
+ },
550
+ {
551
+ "epoch": 0.26,
552
+ "grad_norm": 0.4861234128475189,
553
+ "learning_rate": 0.0004211367764821722,
554
+ "loss": 3.0473,
555
+ "step": 780
556
+ },
557
+ {
558
+ "epoch": 0.26,
559
+ "grad_norm": 0.49302661418914795,
560
+ "learning_rate": 0.0004192189924206652,
561
+ "loss": 3.0874,
562
+ "step": 790
563
+ },
564
+ {
565
+ "epoch": 0.27,
566
+ "grad_norm": 0.4864264726638794,
567
+ "learning_rate": 0.0004172826515897146,
568
+ "loss": 3.0753,
569
+ "step": 800
570
+ },
571
+ {
572
+ "epoch": 0.27,
573
+ "grad_norm": 0.48708102107048035,
574
+ "learning_rate": 0.00041532796633091297,
575
+ "loss": 3.1403,
576
+ "step": 810
577
+ },
578
+ {
579
+ "epoch": 0.27,
580
+ "grad_norm": 0.5046274662017822,
581
+ "learning_rate": 0.0004133551509975264,
582
+ "loss": 3.0785,
583
+ "step": 820
584
+ },
585
+ {
586
+ "epoch": 0.28,
587
+ "grad_norm": 0.5404755473136902,
588
+ "learning_rate": 0.00041136442193098765,
589
+ "loss": 3.0104,
590
+ "step": 830
591
+ },
592
+ {
593
+ "epoch": 0.28,
594
+ "grad_norm": 0.5012314915657043,
595
+ "learning_rate": 0.00040935599743717243,
596
+ "loss": 3.0538,
597
+ "step": 840
598
+ },
599
+ {
600
+ "epoch": 0.28,
601
+ "grad_norm": 0.5044212937355042,
602
+ "learning_rate": 0.0004073300977624594,
603
+ "loss": 3.0975,
604
+ "step": 850
605
+ },
606
+ {
607
+ "epoch": 0.29,
608
+ "grad_norm": 0.5059216618537903,
609
+ "learning_rate": 0.0004052869450695776,
610
+ "loss": 3.1057,
611
+ "step": 860
612
+ },
613
+ {
614
+ "epoch": 0.29,
615
+ "grad_norm": 0.4804486930370331,
616
+ "learning_rate": 0.00040322676341324415,
617
+ "loss": 3.0492,
618
+ "step": 870
619
+ },
620
+ {
621
+ "epoch": 0.29,
622
+ "grad_norm": 0.5673746466636658,
623
+ "learning_rate": 0.00040114977871559375,
624
+ "loss": 2.9521,
625
+ "step": 880
626
+ },
627
+ {
628
+ "epoch": 0.3,
629
+ "grad_norm": 0.4696684181690216,
630
+ "learning_rate": 0.00039905621874140396,
631
+ "loss": 3.0136,
632
+ "step": 890
633
+ },
634
+ {
635
+ "epoch": 0.3,
636
+ "grad_norm": 0.5002209544181824,
637
+ "learning_rate": 0.0003969463130731183,
638
+ "loss": 3.0378,
639
+ "step": 900
640
+ },
641
+ {
642
+ "epoch": 0.3,
643
+ "grad_norm": 0.48504123091697693,
644
+ "learning_rate": 0.0003948202930856697,
645
+ "loss": 3.0458,
646
+ "step": 910
647
+ },
648
+ {
649
+ "epoch": 0.31,
650
+ "grad_norm": 0.48299267888069153,
651
+ "learning_rate": 0.000392678391921108,
652
+ "loss": 3.0699,
653
+ "step": 920
654
+ },
655
+ {
656
+ "epoch": 0.31,
657
+ "grad_norm": 0.5440784096717834,
658
+ "learning_rate": 0.00039052084446303264,
659
+ "loss": 3.044,
660
+ "step": 930
661
+ },
662
+ {
663
+ "epoch": 0.31,
664
+ "grad_norm": 0.498516321182251,
665
+ "learning_rate": 0.000388347887310836,
666
+ "loss": 3.0524,
667
+ "step": 940
668
+ },
669
+ {
670
+ "epoch": 0.32,
671
+ "grad_norm": 0.49369409680366516,
672
+ "learning_rate": 0.00038615975875375683,
673
+ "loss": 3.0511,
674
+ "step": 950
675
+ },
676
+ {
677
+ "epoch": 0.32,
678
+ "grad_norm": 0.5007414817810059,
679
+ "learning_rate": 0.00038395669874474915,
680
+ "loss": 3.0369,
681
+ "step": 960
682
+ },
683
+ {
684
+ "epoch": 0.32,
685
+ "grad_norm": 0.4814367890357971,
686
+ "learning_rate": 0.00038173894887416946,
687
+ "loss": 3.0965,
688
+ "step": 970
689
+ },
690
+ {
691
+ "epoch": 0.33,
692
+ "grad_norm": 0.5295039415359497,
693
+ "learning_rate": 0.00037950675234328256,
694
+ "loss": 3.0571,
695
+ "step": 980
696
+ },
697
+ {
698
+ "epoch": 0.33,
699
+ "grad_norm": 0.5096908211708069,
700
+ "learning_rate": 0.00037726035393759286,
701
+ "loss": 2.9924,
702
+ "step": 990
703
+ },
704
+ {
705
+ "epoch": 0.33,
706
+ "grad_norm": 0.49976101517677307,
707
+ "learning_rate": 0.000375,
708
+ "loss": 3.0523,
709
+ "step": 1000
710
+ },
711
+ {
712
+ "epoch": 0.34,
713
+ "grad_norm": 0.486150860786438,
714
+ "learning_rate": 0.0003727259384037852,
715
+ "loss": 3.0453,
716
+ "step": 1010
717
+ },
718
+ {
719
+ "epoch": 0.34,
720
+ "grad_norm": 0.4886365532875061,
721
+ "learning_rate": 0.0003704384185254288,
722
+ "loss": 3.0791,
723
+ "step": 1020
724
+ },
725
+ {
726
+ "epoch": 0.34,
727
+ "grad_norm": 0.4869343638420105,
728
+ "learning_rate": 0.00036813769121726354,
729
+ "loss": 3.0962,
730
+ "step": 1030
731
+ },
732
+ {
733
+ "epoch": 0.35,
734
+ "grad_norm": 0.47605258226394653,
735
+ "learning_rate": 0.00036582400877996547,
736
+ "loss": 3.087,
737
+ "step": 1040
738
+ },
739
+ {
740
+ "epoch": 0.35,
741
+ "grad_norm": 0.49207133054733276,
742
+ "learning_rate": 0.00036349762493488667,
743
+ "loss": 3.0406,
744
+ "step": 1050
745
+ },
746
+ {
747
+ "epoch": 0.35,
748
+ "grad_norm": 0.5010517835617065,
749
+ "learning_rate": 0.00036115879479623185,
750
+ "loss": 3.0638,
751
+ "step": 1060
752
+ },
753
+ {
754
+ "epoch": 0.36,
755
+ "grad_norm": 0.48435714840888977,
756
+ "learning_rate": 0.0003588077748430819,
757
+ "loss": 3.0325,
758
+ "step": 1070
759
+ },
760
+ {
761
+ "epoch": 0.36,
762
+ "grad_norm": 0.5021737813949585,
763
+ "learning_rate": 0.0003564448228912682,
764
+ "loss": 3.0115,
765
+ "step": 1080
766
+ },
767
+ {
768
+ "epoch": 0.36,
769
+ "grad_norm": 0.46703141927719116,
770
+ "learning_rate": 0.00035407019806510035,
771
+ "loss": 2.9539,
772
+ "step": 1090
773
+ },
774
+ {
775
+ "epoch": 0.37,
776
+ "grad_norm": 0.521730363368988,
777
+ "learning_rate": 0.0003516841607689501,
778
+ "loss": 3.0114,
779
+ "step": 1100
780
+ },
781
+ {
782
+ "epoch": 0.37,
783
+ "grad_norm": 0.4748888611793518,
784
+ "learning_rate": 0.00034928697265869515,
785
+ "loss": 3.0226,
786
+ "step": 1110
787
+ },
788
+ {
789
+ "epoch": 0.37,
790
+ "grad_norm": 0.4812580645084381,
791
+ "learning_rate": 0.00034687889661302575,
792
+ "loss": 3.0065,
793
+ "step": 1120
794
+ },
795
+ {
796
+ "epoch": 0.38,
797
+ "grad_norm": 0.5008811354637146,
798
+ "learning_rate": 0.00034446019670461683,
799
+ "loss": 3.027,
800
+ "step": 1130
801
+ },
802
+ {
803
+ "epoch": 0.38,
804
+ "grad_norm": 0.49032077193260193,
805
+ "learning_rate": 0.00034203113817116957,
806
+ "loss": 2.9933,
807
+ "step": 1140
808
+ },
809
+ {
810
+ "epoch": 0.38,
811
+ "grad_norm": 0.47988900542259216,
812
+ "learning_rate": 0.00033959198738632503,
813
+ "loss": 3.0474,
814
+ "step": 1150
815
+ },
816
+ {
817
+ "epoch": 0.39,
818
+ "grad_norm": 0.49220654368400574,
819
+ "learning_rate": 0.0003371430118304538,
820
+ "loss": 3.0226,
821
+ "step": 1160
822
+ },
823
+ {
824
+ "epoch": 0.39,
825
+ "grad_norm": 0.49873360991477966,
826
+ "learning_rate": 0.0003346844800613229,
827
+ "loss": 3.0082,
828
+ "step": 1170
829
+ },
830
+ {
831
+ "epoch": 0.39,
832
+ "grad_norm": 0.5125187039375305,
833
+ "learning_rate": 0.0003322166616846458,
834
+ "loss": 3.0468,
835
+ "step": 1180
836
+ },
837
+ {
838
+ "epoch": 0.4,
839
+ "grad_norm": 0.509082555770874,
840
+ "learning_rate": 0.0003297398273245175,
841
+ "loss": 3.1134,
842
+ "step": 1190
843
+ },
844
+ {
845
+ "epoch": 0.4,
846
+ "grad_norm": 0.45824429392814636,
847
+ "learning_rate": 0.00032725424859373687,
848
+ "loss": 3.0516,
849
+ "step": 1200
850
+ },
851
+ {
852
+ "epoch": 0.4,
853
+ "grad_norm": 0.49980753660202026,
854
+ "learning_rate": 0.0003247601980640217,
855
+ "loss": 2.9742,
856
+ "step": 1210
857
+ },
858
+ {
859
+ "epoch": 0.41,
860
+ "grad_norm": 0.48861539363861084,
861
+ "learning_rate": 0.0003222579492361179,
862
+ "loss": 3.004,
863
+ "step": 1220
864
+ },
865
+ {
866
+ "epoch": 0.41,
867
+ "grad_norm": 0.5454481840133667,
868
+ "learning_rate": 0.00031974777650980735,
869
+ "loss": 2.9608,
870
+ "step": 1230
871
+ },
872
+ {
873
+ "epoch": 0.41,
874
+ "grad_norm": 0.4744034707546234,
875
+ "learning_rate": 0.0003172299551538164,
876
+ "loss": 3.0384,
877
+ "step": 1240
878
+ },
879
+ {
880
+ "epoch": 0.42,
881
+ "grad_norm": 0.5317044854164124,
882
+ "learning_rate": 0.00031470476127563017,
883
+ "loss": 3.0209,
884
+ "step": 1250
885
+ },
886
+ {
887
+ "epoch": 0.42,
888
+ "grad_norm": 0.49222180247306824,
889
+ "learning_rate": 0.0003121724717912138,
890
+ "loss": 3.0135,
891
+ "step": 1260
892
+ },
893
+ {
894
+ "epoch": 0.42,
895
+ "grad_norm": 0.4853774309158325,
896
+ "learning_rate": 0.00030963336439464523,
897
+ "loss": 3.0235,
898
+ "step": 1270
899
+ },
900
+ {
901
+ "epoch": 0.43,
902
+ "grad_norm": 0.4858599603176117,
903
+ "learning_rate": 0.00030708771752766396,
904
+ "loss": 3.0256,
905
+ "step": 1280
906
+ },
907
+ {
908
+ "epoch": 0.43,
909
+ "grad_norm": 0.4980061948299408,
910
+ "learning_rate": 0.0003045358103491357,
911
+ "loss": 2.9718,
912
+ "step": 1290
913
+ },
914
+ {
915
+ "epoch": 0.43,
916
+ "grad_norm": 0.49256446957588196,
917
+ "learning_rate": 0.0003019779227044398,
918
+ "loss": 3.0288,
919
+ "step": 1300
920
+ },
921
+ {
922
+ "epoch": 0.44,
923
+ "grad_norm": 0.5088287591934204,
924
+ "learning_rate": 0.00029941433509478153,
925
+ "loss": 3.0268,
926
+ "step": 1310
927
+ },
928
+ {
929
+ "epoch": 0.44,
930
+ "grad_norm": 0.5106491446495056,
931
+ "learning_rate": 0.0002968453286464312,
932
+ "loss": 3.0032,
933
+ "step": 1320
934
+ },
935
+ {
936
+ "epoch": 0.44,
937
+ "grad_norm": 0.4999896287918091,
938
+ "learning_rate": 0.0002942711850798959,
939
+ "loss": 2.9407,
940
+ "step": 1330
941
+ },
942
+ {
943
+ "epoch": 0.45,
944
+ "grad_norm": 0.4718291163444519,
945
+ "learning_rate": 0.00029169218667902556,
946
+ "loss": 2.9313,
947
+ "step": 1340
948
+ },
949
+ {
950
+ "epoch": 0.45,
951
+ "grad_norm": 0.485334187746048,
952
+ "learning_rate": 0.00028910861626005774,
953
+ "loss": 2.9993,
954
+ "step": 1350
955
+ },
956
+ {
957
+ "epoch": 0.45,
958
+ "grad_norm": 0.47278451919555664,
959
+ "learning_rate": 0.00028652075714060294,
960
+ "loss": 3.0594,
961
+ "step": 1360
962
+ },
963
+ {
964
+ "epoch": 0.46,
965
+ "grad_norm": 0.4961351454257965,
966
+ "learning_rate": 0.0002839288931085761,
967
+ "loss": 2.9736,
968
+ "step": 1370
969
+ },
970
+ {
971
+ "epoch": 0.46,
972
+ "grad_norm": 0.48107197880744934,
973
+ "learning_rate": 0.00028133330839107606,
974
+ "loss": 2.9818,
975
+ "step": 1380
976
+ },
977
+ {
978
+ "epoch": 0.46,
979
+ "grad_norm": 0.5018859505653381,
980
+ "learning_rate": 0.0002787342876232167,
981
+ "loss": 2.9993,
982
+ "step": 1390
983
+ },
984
+ {
985
+ "epoch": 0.47,
986
+ "grad_norm": 0.5005733966827393,
987
+ "learning_rate": 0.0002761321158169134,
988
+ "loss": 2.971,
989
+ "step": 1400
990
+ },
991
+ {
992
+ "epoch": 0.47,
993
+ "grad_norm": 0.45412546396255493,
994
+ "learning_rate": 0.0002735270783296286,
995
+ "loss": 2.9343,
996
+ "step": 1410
997
+ },
998
+ {
999
+ "epoch": 0.47,
1000
+ "grad_norm": 0.49526095390319824,
1001
+ "learning_rate": 0.00027091946083307894,
1002
+ "loss": 3.0247,
1003
+ "step": 1420
1004
+ },
1005
+ {
1006
+ "epoch": 0.48,
1007
+ "grad_norm": 0.5004629492759705,
1008
+ "learning_rate": 0.00026830954928190793,
1009
+ "loss": 2.9386,
1010
+ "step": 1430
1011
+ },
1012
+ {
1013
+ "epoch": 0.48,
1014
+ "grad_norm": 0.5008641481399536,
1015
+ "learning_rate": 0.0002656976298823284,
1016
+ "loss": 2.9768,
1017
+ "step": 1440
1018
+ },
1019
+ {
1020
+ "epoch": 0.48,
1021
+ "grad_norm": 0.4870932698249817,
1022
+ "learning_rate": 0.000263083989060736,
1023
+ "loss": 2.9825,
1024
+ "step": 1450
1025
+ },
1026
+ {
1027
+ "epoch": 0.49,
1028
+ "grad_norm": 0.47083091735839844,
1029
+ "learning_rate": 0.0002604689134322999,
1030
+ "loss": 2.9694,
1031
+ "step": 1460
1032
+ },
1033
+ {
1034
+ "epoch": 0.49,
1035
+ "grad_norm": 0.4780152440071106,
1036
+ "learning_rate": 0.00025785268976953206,
1037
+ "loss": 3.0139,
1038
+ "step": 1470
1039
+ },
1040
+ {
1041
+ "epoch": 0.49,
1042
+ "grad_norm": 0.47919341921806335,
1043
+ "learning_rate": 0.00025523560497083924,
1044
+ "loss": 2.9558,
1045
+ "step": 1480
1046
+ },
1047
+ {
1048
+ "epoch": 0.5,
1049
+ "grad_norm": 0.4744253158569336,
1050
+ "learning_rate": 0.00025261794602906147,
1051
+ "loss": 2.9823,
1052
+ "step": 1490
1053
+ },
1054
+ {
1055
+ "epoch": 0.5,
1056
+ "grad_norm": 0.47770825028419495,
1057
+ "learning_rate": 0.00025,
1058
+ "loss": 2.976,
1059
+ "step": 1500
1060
+ },
1061
+ {
1062
+ "epoch": 0.5,
1063
+ "grad_norm": 0.535241961479187,
1064
+ "learning_rate": 0.00024738205397093865,
1065
+ "loss": 2.9404,
1066
+ "step": 1510
1067
+ },
1068
+ {
1069
+ "epoch": 0.51,
1070
+ "grad_norm": 0.5206143260002136,
1071
+ "learning_rate": 0.00024476439502916077,
1072
+ "loss": 2.9697,
1073
+ "step": 1520
1074
+ },
1075
+ {
1076
+ "epoch": 0.51,
1077
+ "grad_norm": 0.4685532748699188,
1078
+ "learning_rate": 0.00024214731023046793,
1079
+ "loss": 3.031,
1080
+ "step": 1530
1081
+ },
1082
+ {
1083
+ "epoch": 0.51,
1084
+ "grad_norm": 0.45759207010269165,
1085
+ "learning_rate": 0.00023953108656770016,
1086
+ "loss": 2.9371,
1087
+ "step": 1540
1088
+ },
1089
+ {
1090
+ "epoch": 0.52,
1091
+ "grad_norm": 0.47409725189208984,
1092
+ "learning_rate": 0.00023691601093926405,
1093
+ "loss": 2.9492,
1094
+ "step": 1550
1095
+ },
1096
+ {
1097
+ "epoch": 0.52,
1098
+ "grad_norm": 0.4723811149597168,
1099
+ "learning_rate": 0.00023430237011767165,
1100
+ "loss": 3.0055,
1101
+ "step": 1560
1102
+ },
1103
+ {
1104
+ "epoch": 0.52,
1105
+ "grad_norm": 0.5121801495552063,
1106
+ "learning_rate": 0.00023169045071809213,
1107
+ "loss": 2.9654,
1108
+ "step": 1570
1109
+ },
1110
+ {
1111
+ "epoch": 0.53,
1112
+ "grad_norm": 0.47900766134262085,
1113
+ "learning_rate": 0.00022908053916692117,
1114
+ "loss": 2.9665,
1115
+ "step": 1580
1116
+ },
1117
+ {
1118
+ "epoch": 0.53,
1119
+ "grad_norm": 0.47504156827926636,
1120
+ "learning_rate": 0.00022647292167037142,
1121
+ "loss": 2.9543,
1122
+ "step": 1590
1123
+ },
1124
+ {
1125
+ "epoch": 0.53,
1126
+ "grad_norm": 0.48130717873573303,
1127
+ "learning_rate": 0.00022386788418308668,
1128
+ "loss": 2.9948,
1129
+ "step": 1600
1130
+ },
1131
+ {
1132
+ "epoch": 0.54,
1133
+ "grad_norm": 0.4968855381011963,
1134
+ "learning_rate": 0.00022126571237678338,
1135
+ "loss": 3.0497,
1136
+ "step": 1610
1137
+ },
1138
+ {
1139
+ "epoch": 0.54,
1140
+ "grad_norm": 0.45493414998054504,
1141
+ "learning_rate": 0.00021866669160892392,
1142
+ "loss": 3.0211,
1143
+ "step": 1620
1144
+ },
1145
+ {
1146
+ "epoch": 0.54,
1147
+ "grad_norm": 0.46341362595558167,
1148
+ "learning_rate": 0.00021607110689142393,
1149
+ "loss": 2.9249,
1150
+ "step": 1630
1151
+ },
1152
+ {
1153
+ "epoch": 0.55,
1154
+ "grad_norm": 0.4598373472690582,
1155
+ "learning_rate": 0.00021347924285939712,
1156
+ "loss": 2.9306,
1157
+ "step": 1640
1158
+ },
1159
+ {
1160
+ "epoch": 0.55,
1161
+ "grad_norm": 0.5339600443840027,
1162
+ "learning_rate": 0.00021089138373994224,
1163
+ "loss": 2.9457,
1164
+ "step": 1650
1165
+ },
1166
+ {
1167
+ "epoch": 0.55,
1168
+ "grad_norm": 0.4766974449157715,
1169
+ "learning_rate": 0.00020830781332097445,
1170
+ "loss": 2.9573,
1171
+ "step": 1660
1172
+ },
1173
+ {
1174
+ "epoch": 0.56,
1175
+ "grad_norm": 0.45860227942466736,
1176
+ "learning_rate": 0.0002057288149201042,
1177
+ "loss": 2.9067,
1178
+ "step": 1670
1179
+ },
1180
+ {
1181
+ "epoch": 0.56,
1182
+ "grad_norm": 0.4715401530265808,
1183
+ "learning_rate": 0.0002031546713535688,
1184
+ "loss": 2.9373,
1185
+ "step": 1680
1186
+ },
1187
+ {
1188
+ "epoch": 0.56,
1189
+ "grad_norm": 0.4715852439403534,
1190
+ "learning_rate": 0.00020058566490521845,
1191
+ "loss": 2.9486,
1192
+ "step": 1690
1193
+ },
1194
+ {
1195
+ "epoch": 0.57,
1196
+ "grad_norm": 0.4740593731403351,
1197
+ "learning_rate": 0.0001980220772955602,
1198
+ "loss": 2.9672,
1199
+ "step": 1700
1200
+ },
1201
+ {
1202
+ "epoch": 0.57,
1203
+ "grad_norm": 0.5071026086807251,
1204
+ "learning_rate": 0.00019546418965086444,
1205
+ "loss": 2.9791,
1206
+ "step": 1710
1207
+ },
1208
+ {
1209
+ "epoch": 0.57,
1210
+ "grad_norm": 0.46667274832725525,
1211
+ "learning_rate": 0.00019291228247233605,
1212
+ "loss": 2.9517,
1213
+ "step": 1720
1214
+ },
1215
+ {
1216
+ "epoch": 0.58,
1217
+ "grad_norm": 0.5175219178199768,
1218
+ "learning_rate": 0.00019036663560535483,
1219
+ "loss": 2.9765,
1220
+ "step": 1730
1221
+ },
1222
+ {
1223
+ "epoch": 0.58,
1224
+ "grad_norm": 0.4796634018421173,
1225
+ "learning_rate": 0.00018782752820878634,
1226
+ "loss": 2.9258,
1227
+ "step": 1740
1228
+ },
1229
+ {
1230
+ "epoch": 0.58,
1231
+ "grad_norm": 0.4871932566165924,
1232
+ "learning_rate": 0.0001852952387243698,
1233
+ "loss": 2.9403,
1234
+ "step": 1750
1235
+ },
1236
+ {
1237
+ "epoch": 0.59,
1238
+ "grad_norm": 0.4641266167163849,
1239
+ "learning_rate": 0.00018277004484618358,
1240
+ "loss": 2.9058,
1241
+ "step": 1760
1242
+ },
1243
+ {
1244
+ "epoch": 0.59,
1245
+ "grad_norm": 0.4585517346858978,
1246
+ "learning_rate": 0.0001802522234901927,
1247
+ "loss": 2.9802,
1248
+ "step": 1770
1249
+ },
1250
+ {
1251
+ "epoch": 0.59,
1252
+ "grad_norm": 0.4525165855884552,
1253
+ "learning_rate": 0.00017774205076388205,
1254
+ "loss": 3.0241,
1255
+ "step": 1780
1256
+ },
1257
+ {
1258
+ "epoch": 0.6,
1259
+ "grad_norm": 0.4651874303817749,
1260
+ "learning_rate": 0.00017523980193597836,
1261
+ "loss": 2.9783,
1262
+ "step": 1790
1263
+ },
1264
+ {
1265
+ "epoch": 0.6,
1266
+ "grad_norm": 0.4655090868473053,
1267
+ "learning_rate": 0.00017274575140626317,
1268
+ "loss": 2.9115,
1269
+ "step": 1800
1270
+ },
1271
+ {
1272
+ "epoch": 0.6,
1273
+ "grad_norm": 0.44796276092529297,
1274
+ "learning_rate": 0.0001702601726754825,
1275
+ "loss": 2.9357,
1276
+ "step": 1810
1277
+ },
1278
+ {
1279
+ "epoch": 0.61,
1280
+ "grad_norm": 0.5139617323875427,
1281
+ "learning_rate": 0.00016778333831535418,
1282
+ "loss": 2.9124,
1283
+ "step": 1820
1284
+ },
1285
+ {
1286
+ "epoch": 0.61,
1287
+ "grad_norm": 0.4756507873535156,
1288
+ "learning_rate": 0.00016531551993867715,
1289
+ "loss": 2.9252,
1290
+ "step": 1830
1291
+ },
1292
+ {
1293
+ "epoch": 0.61,
1294
+ "grad_norm": 0.47321391105651855,
1295
+ "learning_rate": 0.00016285698816954626,
1296
+ "loss": 2.9801,
1297
+ "step": 1840
1298
+ },
1299
+ {
1300
+ "epoch": 0.62,
1301
+ "grad_norm": 0.4512488842010498,
1302
+ "learning_rate": 0.00016040801261367493,
1303
+ "loss": 3.0134,
1304
+ "step": 1850
1305
+ },
1306
+ {
1307
+ "epoch": 0.62,
1308
+ "grad_norm": 0.5047795176506042,
1309
+ "learning_rate": 0.00015796886182883053,
1310
+ "loss": 2.9549,
1311
+ "step": 1860
1312
+ },
1313
+ {
1314
+ "epoch": 0.62,
1315
+ "grad_norm": 0.4670908451080322,
1316
+ "learning_rate": 0.00015553980329538326,
1317
+ "loss": 2.9534,
1318
+ "step": 1870
1319
+ },
1320
+ {
1321
+ "epoch": 0.63,
1322
+ "grad_norm": 0.4596426784992218,
1323
+ "learning_rate": 0.00015312110338697426,
1324
+ "loss": 2.9802,
1325
+ "step": 1880
1326
+ },
1327
+ {
1328
+ "epoch": 0.63,
1329
+ "grad_norm": 0.45904773473739624,
1330
+ "learning_rate": 0.00015071302734130488,
1331
+ "loss": 2.9435,
1332
+ "step": 1890
1333
+ },
1334
+ {
1335
+ "epoch": 0.63,
1336
+ "grad_norm": 0.48870381712913513,
1337
+ "learning_rate": 0.00014831583923105,
1338
+ "loss": 2.9378,
1339
+ "step": 1900
1340
+ },
1341
+ {
1342
+ "epoch": 0.64,
1343
+ "grad_norm": 0.4705340564250946,
1344
+ "learning_rate": 0.00014592980193489974,
1345
+ "loss": 2.9716,
1346
+ "step": 1910
1347
+ },
1348
+ {
1349
+ "epoch": 0.64,
1350
+ "grad_norm": 0.45324671268463135,
1351
+ "learning_rate": 0.00014355517710873183,
1352
+ "loss": 2.9729,
1353
+ "step": 1920
1354
+ },
1355
+ {
1356
+ "epoch": 0.64,
1357
+ "grad_norm": 0.4573574662208557,
1358
+ "learning_rate": 0.00014119222515691815,
1359
+ "loss": 2.9286,
1360
+ "step": 1930
1361
+ },
1362
+ {
1363
+ "epoch": 0.65,
1364
+ "grad_norm": 0.48345670104026794,
1365
+ "learning_rate": 0.00013884120520376818,
1366
+ "loss": 3.0016,
1367
+ "step": 1940
1368
+ },
1369
+ {
1370
+ "epoch": 0.65,
1371
+ "grad_norm": 0.4590473175048828,
1372
+ "learning_rate": 0.00013650237506511331,
1373
+ "loss": 2.8464,
1374
+ "step": 1950
1375
+ },
1376
+ {
1377
+ "epoch": 0.65,
1378
+ "grad_norm": 0.7705239057540894,
1379
+ "learning_rate": 0.00013417599122003462,
1380
+ "loss": 3.007,
1381
+ "step": 1960
1382
+ },
1383
+ {
1384
+ "epoch": 0.66,
1385
+ "grad_norm": 0.4770728647708893,
1386
+ "learning_rate": 0.00013186230878273653,
1387
+ "loss": 2.9381,
1388
+ "step": 1970
1389
+ },
1390
+ {
1391
+ "epoch": 0.66,
1392
+ "grad_norm": 0.44512978196144104,
1393
+ "learning_rate": 0.00012956158147457115,
1394
+ "loss": 2.9813,
1395
+ "step": 1980
1396
+ },
1397
+ {
1398
+ "epoch": 0.66,
1399
+ "grad_norm": 0.4624728262424469,
1400
+ "learning_rate": 0.00012727406159621478,
1401
+ "loss": 2.9069,
1402
+ "step": 1990
1403
+ },
1404
+ {
1405
+ "epoch": 0.67,
1406
+ "grad_norm": 0.47390344738960266,
1407
+ "learning_rate": 0.00012500000000000006,
1408
+ "loss": 2.9868,
1409
+ "step": 2000
1410
+ }
1411
+ ],
1412
+ "logging_steps": 10,
1413
+ "max_steps": 3000,
1414
+ "num_input_tokens_seen": 0,
1415
+ "num_train_epochs": 9223372036854775807,
1416
+ "save_steps": 1000,
1417
+ "total_flos": 2.85480780300288e+18,
1418
+ "train_batch_size": 16,
1419
+ "trial_name": null,
1420
+ "trial_params": null
1421
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2220e9630781dc148b0f5bea27b08fb071f0652a6b90a0d5cc7e2519f0fa43fe
3
+ size 5112
vocab.json ADDED
The diff for this file is too large to render. See raw diff