Upload folder using huggingface_hub
Browse files- README.md +209 -0
- adapter_config.json +54 -0
- adapter_model.safetensors +3 -0
- chat_template.jinja +9 -0
- optimizer.pt +3 -0
- rng_state_0.pth +3 -0
- rng_state_1.pth +3 -0
- rng_state_2.pth +3 -0
- rng_state_3.pth +3 -0
- scheduler.pt +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +15 -0
- trainer_state.json +2034 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,209 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: allenai/OLMoE-1B-7B-0125-Instruct
|
| 3 |
+
library_name: peft
|
| 4 |
+
pipeline_tag: text-generation
|
| 5 |
+
tags:
|
| 6 |
+
- base_model:adapter:allenai/OLMoE-1B-7B-0125-Instruct
|
| 7 |
+
- lora
|
| 8 |
+
- sft
|
| 9 |
+
- transformers
|
| 10 |
+
- trl
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
# Model Card for Model ID
|
| 14 |
+
|
| 15 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
## Model Details
|
| 20 |
+
|
| 21 |
+
### Model Description
|
| 22 |
+
|
| 23 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 24 |
+
|
| 25 |
+
|
| 26 |
+
|
| 27 |
+
- **Developed by:** [More Information Needed]
|
| 28 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 29 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 30 |
+
- **Model type:** [More Information Needed]
|
| 31 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 32 |
+
- **License:** [More Information Needed]
|
| 33 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 34 |
+
|
| 35 |
+
### Model Sources [optional]
|
| 36 |
+
|
| 37 |
+
<!-- Provide the basic links for the model. -->
|
| 38 |
+
|
| 39 |
+
- **Repository:** [More Information Needed]
|
| 40 |
+
- **Paper [optional]:** [More Information Needed]
|
| 41 |
+
- **Demo [optional]:** [More Information Needed]
|
| 42 |
+
|
| 43 |
+
## Uses
|
| 44 |
+
|
| 45 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 46 |
+
|
| 47 |
+
### Direct Use
|
| 48 |
+
|
| 49 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 50 |
+
|
| 51 |
+
[More Information Needed]
|
| 52 |
+
|
| 53 |
+
### Downstream Use [optional]
|
| 54 |
+
|
| 55 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 56 |
+
|
| 57 |
+
[More Information Needed]
|
| 58 |
+
|
| 59 |
+
### Out-of-Scope Use
|
| 60 |
+
|
| 61 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 62 |
+
|
| 63 |
+
[More Information Needed]
|
| 64 |
+
|
| 65 |
+
## Bias, Risks, and Limitations
|
| 66 |
+
|
| 67 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 68 |
+
|
| 69 |
+
[More Information Needed]
|
| 70 |
+
|
| 71 |
+
### Recommendations
|
| 72 |
+
|
| 73 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 74 |
+
|
| 75 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 76 |
+
|
| 77 |
+
## How to Get Started with the Model
|
| 78 |
+
|
| 79 |
+
Use the code below to get started with the model.
|
| 80 |
+
|
| 81 |
+
[More Information Needed]
|
| 82 |
+
|
| 83 |
+
## Training Details
|
| 84 |
+
|
| 85 |
+
### Training Data
|
| 86 |
+
|
| 87 |
+
<!-- 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. -->
|
| 88 |
+
|
| 89 |
+
[More Information Needed]
|
| 90 |
+
|
| 91 |
+
### Training Procedure
|
| 92 |
+
|
| 93 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 94 |
+
|
| 95 |
+
#### Preprocessing [optional]
|
| 96 |
+
|
| 97 |
+
[More Information Needed]
|
| 98 |
+
|
| 99 |
+
|
| 100 |
+
#### Training Hyperparameters
|
| 101 |
+
|
| 102 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 103 |
+
|
| 104 |
+
#### Speeds, Sizes, Times [optional]
|
| 105 |
+
|
| 106 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 107 |
+
|
| 108 |
+
[More Information Needed]
|
| 109 |
+
|
| 110 |
+
## Evaluation
|
| 111 |
+
|
| 112 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 113 |
+
|
| 114 |
+
### Testing Data, Factors & Metrics
|
| 115 |
+
|
| 116 |
+
#### Testing Data
|
| 117 |
+
|
| 118 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 119 |
+
|
| 120 |
+
[More Information Needed]
|
| 121 |
+
|
| 122 |
+
#### Factors
|
| 123 |
+
|
| 124 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 125 |
+
|
| 126 |
+
[More Information Needed]
|
| 127 |
+
|
| 128 |
+
#### Metrics
|
| 129 |
+
|
| 130 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 131 |
+
|
| 132 |
+
[More Information Needed]
|
| 133 |
+
|
| 134 |
+
### Results
|
| 135 |
+
|
| 136 |
+
[More Information Needed]
|
| 137 |
+
|
| 138 |
+
#### Summary
|
| 139 |
+
|
| 140 |
+
|
| 141 |
+
|
| 142 |
+
## Model Examination [optional]
|
| 143 |
+
|
| 144 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 145 |
+
|
| 146 |
+
[More Information Needed]
|
| 147 |
+
|
| 148 |
+
## Environmental Impact
|
| 149 |
+
|
| 150 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 151 |
+
|
| 152 |
+
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).
|
| 153 |
+
|
| 154 |
+
- **Hardware Type:** [More Information Needed]
|
| 155 |
+
- **Hours used:** [More Information Needed]
|
| 156 |
+
- **Cloud Provider:** [More Information Needed]
|
| 157 |
+
- **Compute Region:** [More Information Needed]
|
| 158 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 159 |
+
|
| 160 |
+
## Technical Specifications [optional]
|
| 161 |
+
|
| 162 |
+
### Model Architecture and Objective
|
| 163 |
+
|
| 164 |
+
[More Information Needed]
|
| 165 |
+
|
| 166 |
+
### Compute Infrastructure
|
| 167 |
+
|
| 168 |
+
[More Information Needed]
|
| 169 |
+
|
| 170 |
+
#### Hardware
|
| 171 |
+
|
| 172 |
+
[More Information Needed]
|
| 173 |
+
|
| 174 |
+
#### Software
|
| 175 |
+
|
| 176 |
+
[More Information Needed]
|
| 177 |
+
|
| 178 |
+
## Citation [optional]
|
| 179 |
+
|
| 180 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 181 |
+
|
| 182 |
+
**BibTeX:**
|
| 183 |
+
|
| 184 |
+
[More Information Needed]
|
| 185 |
+
|
| 186 |
+
**APA:**
|
| 187 |
+
|
| 188 |
+
[More Information Needed]
|
| 189 |
+
|
| 190 |
+
## Glossary [optional]
|
| 191 |
+
|
| 192 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 193 |
+
|
| 194 |
+
[More Information Needed]
|
| 195 |
+
|
| 196 |
+
## More Information [optional]
|
| 197 |
+
|
| 198 |
+
[More Information Needed]
|
| 199 |
+
|
| 200 |
+
## Model Card Authors [optional]
|
| 201 |
+
|
| 202 |
+
[More Information Needed]
|
| 203 |
+
|
| 204 |
+
## Model Card Contact
|
| 205 |
+
|
| 206 |
+
[More Information Needed]
|
| 207 |
+
### Framework versions
|
| 208 |
+
|
| 209 |
+
- PEFT 0.19.1
|
adapter_config.json
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alora_invocation_tokens": null,
|
| 3 |
+
"alpha_pattern": {
|
| 4 |
+
".*\\.gate_up_proj": 64
|
| 5 |
+
},
|
| 6 |
+
"arrow_config": null,
|
| 7 |
+
"auto_mapping": null,
|
| 8 |
+
"base_model_name_or_path": "allenai/OLMoE-1B-7B-0125-Instruct",
|
| 9 |
+
"bias": "none",
|
| 10 |
+
"corda_config": null,
|
| 11 |
+
"ensure_weight_tying": false,
|
| 12 |
+
"eva_config": null,
|
| 13 |
+
"exclude_modules": null,
|
| 14 |
+
"fan_in_fan_out": false,
|
| 15 |
+
"inference_mode": true,
|
| 16 |
+
"init_lora_weights": true,
|
| 17 |
+
"layer_replication": null,
|
| 18 |
+
"layers_pattern": null,
|
| 19 |
+
"layers_to_transform": null,
|
| 20 |
+
"loftq_config": {},
|
| 21 |
+
"lora_alpha": 32,
|
| 22 |
+
"lora_bias": false,
|
| 23 |
+
"lora_dropout": 0.0,
|
| 24 |
+
"lora_ga_config": null,
|
| 25 |
+
"megatron_config": null,
|
| 26 |
+
"megatron_core": "megatron.core",
|
| 27 |
+
"modules_to_save": null,
|
| 28 |
+
"peft_type": "LORA",
|
| 29 |
+
"peft_version": "0.19.1",
|
| 30 |
+
"qalora_group_size": 16,
|
| 31 |
+
"r": 16,
|
| 32 |
+
"rank_pattern": {
|
| 33 |
+
".*\\.gate_up_proj": 32
|
| 34 |
+
},
|
| 35 |
+
"revision": null,
|
| 36 |
+
"target_modules": [
|
| 37 |
+
"q_proj",
|
| 38 |
+
"v_proj",
|
| 39 |
+
"o_proj",
|
| 40 |
+
"router",
|
| 41 |
+
"k_proj"
|
| 42 |
+
],
|
| 43 |
+
"target_parameters": [
|
| 44 |
+
"down_proj",
|
| 45 |
+
"gate.weight",
|
| 46 |
+
"gate_up_proj"
|
| 47 |
+
],
|
| 48 |
+
"task_type": "CAUSAL_LM",
|
| 49 |
+
"trainable_token_indices": null,
|
| 50 |
+
"use_bdlora": null,
|
| 51 |
+
"use_dora": false,
|
| 52 |
+
"use_qalora": false,
|
| 53 |
+
"use_rslora": false
|
| 54 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f7c042cde71ceaf9c10aea02dab189c65ded006712c4a4d3c900eb9964d11935
|
| 3 |
+
size 757167808
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{{ bos_token }}{% for message in messages %}{% if message['role'] == 'system' %}{{ '<|system|>
|
| 2 |
+
' + message['content'] + '
|
| 3 |
+
' }}{% elif message['role'] == 'user' %}{{ '<|user|>
|
| 4 |
+
' + message['content'] + '
|
| 5 |
+
' }}{% elif message['role'] == 'assistant' %}{% if not loop.last %}{{ '<|assistant|>
|
| 6 |
+
' + message['content'] + eos_token + '
|
| 7 |
+
' }}{% else %}{{ '<|assistant|>
|
| 8 |
+
' + message['content'] + eos_token }}{% endif %}{% endif %}{% if loop.last and add_generation_prompt %}{{ '<|assistant|>
|
| 9 |
+
' }}{% endif %}{% endfor %}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e5117623518dbda13b5a63cc60377ae3c9cede255aedf9754253934bf54bb098
|
| 3 |
+
size 1514466827
|
rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6dc21751f56a807ad2a7d09eea3bbe867a0c8e0f3d829004cfe097808a8a849d
|
| 3 |
+
size 15429
|
rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:69adbd9997461473344beb9c44d2e496e24fbc4d6fe69245ab0bd127882efd96
|
| 3 |
+
size 15429
|
rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:baaf7026d9e588ca2ba5b4de8768a379982b7530f39e0b88fa44af9bef8e8bc9
|
| 3 |
+
size 15429
|
rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1ec81cbdf599c90b49fb13998f6e46e2492b55345216231b6ce078f88cf04eae
|
| 3 |
+
size 15429
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4dcd0fcafdf0cac56c6781c9554680e5d2ba9bfee0d823975791d1d648a00172
|
| 3 |
+
size 1465
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": "|||IP_ADDRESS|||",
|
| 5 |
+
"clean_up_tokenization_spaces": false,
|
| 6 |
+
"eos_token": "|||IP_ADDRESS|||",
|
| 7 |
+
"errors": "replace",
|
| 8 |
+
"is_local": false,
|
| 9 |
+
"local_files_only": true,
|
| 10 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 11 |
+
"pad_token": "<pad>",
|
| 12 |
+
"tokenizer_class": "GPTNeoXTokenizer",
|
| 13 |
+
"trim_offsets": true,
|
| 14 |
+
"unk_token": null
|
| 15 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2034 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 4.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 200,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"entropy": 0.699141651391983,
|
| 14 |
+
"epoch": 0.02,
|
| 15 |
+
"grad_norm": 1.7043750286102295,
|
| 16 |
+
"learning_rate": 0.0,
|
| 17 |
+
"loss": 1.5967991352081299,
|
| 18 |
+
"mean_token_accuracy": 0.665926069021225,
|
| 19 |
+
"num_tokens": 74699.0,
|
| 20 |
+
"step": 1
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"entropy": 0.6601996421813965,
|
| 24 |
+
"epoch": 0.04,
|
| 25 |
+
"grad_norm": 1.6597099304199219,
|
| 26 |
+
"learning_rate": 1e-05,
|
| 27 |
+
"loss": 1.5338245630264282,
|
| 28 |
+
"mean_token_accuracy": 0.6820768415927887,
|
| 29 |
+
"num_tokens": 138614.0,
|
| 30 |
+
"step": 2
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"entropy": 0.7289904654026031,
|
| 34 |
+
"epoch": 0.06,
|
| 35 |
+
"grad_norm": 1.796127438545227,
|
| 36 |
+
"learning_rate": 2e-05,
|
| 37 |
+
"loss": 1.6285251379013062,
|
| 38 |
+
"mean_token_accuracy": 0.6539906561374664,
|
| 39 |
+
"num_tokens": 209509.0,
|
| 40 |
+
"step": 3
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"entropy": 0.7412302494049072,
|
| 44 |
+
"epoch": 0.08,
|
| 45 |
+
"grad_norm": 1.4846091270446777,
|
| 46 |
+
"learning_rate": 3e-05,
|
| 47 |
+
"loss": 1.5454721450805664,
|
| 48 |
+
"mean_token_accuracy": 0.6691758334636688,
|
| 49 |
+
"num_tokens": 283751.0,
|
| 50 |
+
"step": 4
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"entropy": 0.7322555780410767,
|
| 54 |
+
"epoch": 0.1,
|
| 55 |
+
"grad_norm": 1.4136911630630493,
|
| 56 |
+
"learning_rate": 4e-05,
|
| 57 |
+
"loss": 1.5077476501464844,
|
| 58 |
+
"mean_token_accuracy": 0.6744928658008575,
|
| 59 |
+
"num_tokens": 354066.0,
|
| 60 |
+
"step": 5
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"entropy": 0.7739330530166626,
|
| 64 |
+
"epoch": 0.12,
|
| 65 |
+
"grad_norm": 0.9657893180847168,
|
| 66 |
+
"learning_rate": 5e-05,
|
| 67 |
+
"loss": 1.43147611618042,
|
| 68 |
+
"mean_token_accuracy": 0.6826294660568237,
|
| 69 |
+
"num_tokens": 422170.0,
|
| 70 |
+
"step": 6
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"entropy": 0.8858513236045837,
|
| 74 |
+
"epoch": 0.14,
|
| 75 |
+
"grad_norm": 0.7331474423408508,
|
| 76 |
+
"learning_rate": 6e-05,
|
| 77 |
+
"loss": 1.450822353363037,
|
| 78 |
+
"mean_token_accuracy": 0.6648280322551727,
|
| 79 |
+
"num_tokens": 494040.0,
|
| 80 |
+
"step": 7
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"entropy": 0.9634815156459808,
|
| 84 |
+
"epoch": 0.16,
|
| 85 |
+
"grad_norm": 0.5526663661003113,
|
| 86 |
+
"learning_rate": 7e-05,
|
| 87 |
+
"loss": 1.3808112144470215,
|
| 88 |
+
"mean_token_accuracy": 0.6719212830066681,
|
| 89 |
+
"num_tokens": 566616.0,
|
| 90 |
+
"step": 8
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"entropy": 1.0627405643463135,
|
| 94 |
+
"epoch": 0.18,
|
| 95 |
+
"grad_norm": 0.48948273062705994,
|
| 96 |
+
"learning_rate": 8e-05,
|
| 97 |
+
"loss": 1.3656816482543945,
|
| 98 |
+
"mean_token_accuracy": 0.663449615240097,
|
| 99 |
+
"num_tokens": 637093.0,
|
| 100 |
+
"step": 9
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"entropy": 1.1328747868537903,
|
| 104 |
+
"epoch": 0.2,
|
| 105 |
+
"grad_norm": 0.37054377794265747,
|
| 106 |
+
"learning_rate": 9e-05,
|
| 107 |
+
"loss": 1.2878801822662354,
|
| 108 |
+
"mean_token_accuracy": 0.6749334335327148,
|
| 109 |
+
"num_tokens": 701945.0,
|
| 110 |
+
"step": 10
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"entropy": 1.2100302577018738,
|
| 114 |
+
"epoch": 0.22,
|
| 115 |
+
"grad_norm": 0.3048469126224518,
|
| 116 |
+
"learning_rate": 0.0001,
|
| 117 |
+
"loss": 1.236545443534851,
|
| 118 |
+
"mean_token_accuracy": 0.6853303909301758,
|
| 119 |
+
"num_tokens": 774533.0,
|
| 120 |
+
"step": 11
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"entropy": 1.2940571904182434,
|
| 124 |
+
"epoch": 0.24,
|
| 125 |
+
"grad_norm": 0.3031807243824005,
|
| 126 |
+
"learning_rate": 0.0001,
|
| 127 |
+
"loss": 1.211038589477539,
|
| 128 |
+
"mean_token_accuracy": 0.6858378350734711,
|
| 129 |
+
"num_tokens": 847636.0,
|
| 130 |
+
"step": 12
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"entropy": 1.299929440021515,
|
| 134 |
+
"epoch": 0.26,
|
| 135 |
+
"grad_norm": 0.2886947691440582,
|
| 136 |
+
"learning_rate": 0.0001,
|
| 137 |
+
"loss": 1.197202205657959,
|
| 138 |
+
"mean_token_accuracy": 0.6924754083156586,
|
| 139 |
+
"num_tokens": 923420.0,
|
| 140 |
+
"step": 13
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"entropy": 1.252187728881836,
|
| 144 |
+
"epoch": 0.28,
|
| 145 |
+
"grad_norm": 0.25853437185287476,
|
| 146 |
+
"learning_rate": 0.0001,
|
| 147 |
+
"loss": 1.1612238883972168,
|
| 148 |
+
"mean_token_accuracy": 0.6976969540119171,
|
| 149 |
+
"num_tokens": 992109.0,
|
| 150 |
+
"step": 14
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"entropy": 1.220507800579071,
|
| 154 |
+
"epoch": 0.3,
|
| 155 |
+
"grad_norm": 0.24553938210010529,
|
| 156 |
+
"learning_rate": 0.0001,
|
| 157 |
+
"loss": 1.1456246376037598,
|
| 158 |
+
"mean_token_accuracy": 0.6981014311313629,
|
| 159 |
+
"num_tokens": 1065114.0,
|
| 160 |
+
"step": 15
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"entropy": 1.198462724685669,
|
| 164 |
+
"epoch": 0.32,
|
| 165 |
+
"grad_norm": 0.24306544661521912,
|
| 166 |
+
"learning_rate": 0.0001,
|
| 167 |
+
"loss": 1.1577763557434082,
|
| 168 |
+
"mean_token_accuracy": 0.6941779851913452,
|
| 169 |
+
"num_tokens": 1136722.0,
|
| 170 |
+
"step": 16
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"entropy": 1.1386296153068542,
|
| 174 |
+
"epoch": 0.34,
|
| 175 |
+
"grad_norm": 0.22727081179618835,
|
| 176 |
+
"learning_rate": 0.0001,
|
| 177 |
+
"loss": 1.0986605882644653,
|
| 178 |
+
"mean_token_accuracy": 0.7019487023353577,
|
| 179 |
+
"num_tokens": 1209030.0,
|
| 180 |
+
"step": 17
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"entropy": 1.117907702922821,
|
| 184 |
+
"epoch": 0.36,
|
| 185 |
+
"grad_norm": 0.21270814538002014,
|
| 186 |
+
"learning_rate": 0.0001,
|
| 187 |
+
"loss": 1.110465407371521,
|
| 188 |
+
"mean_token_accuracy": 0.701825737953186,
|
| 189 |
+
"num_tokens": 1276624.0,
|
| 190 |
+
"step": 18
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"entropy": 1.1316577792167664,
|
| 194 |
+
"epoch": 0.38,
|
| 195 |
+
"grad_norm": 0.1995684653520584,
|
| 196 |
+
"learning_rate": 0.0001,
|
| 197 |
+
"loss": 1.1611299514770508,
|
| 198 |
+
"mean_token_accuracy": 0.6892036497592926,
|
| 199 |
+
"num_tokens": 1348478.0,
|
| 200 |
+
"step": 19
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"entropy": 1.0270569920539856,
|
| 204 |
+
"epoch": 0.4,
|
| 205 |
+
"grad_norm": 0.18478907644748688,
|
| 206 |
+
"learning_rate": 0.0001,
|
| 207 |
+
"loss": 1.04264235496521,
|
| 208 |
+
"mean_token_accuracy": 0.7172180116176605,
|
| 209 |
+
"num_tokens": 1421488.0,
|
| 210 |
+
"step": 20
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"entropy": 1.01737579703331,
|
| 214 |
+
"epoch": 0.42,
|
| 215 |
+
"grad_norm": 0.19284074008464813,
|
| 216 |
+
"learning_rate": 0.0001,
|
| 217 |
+
"loss": 1.0274319648742676,
|
| 218 |
+
"mean_token_accuracy": 0.718668669462204,
|
| 219 |
+
"num_tokens": 1488403.0,
|
| 220 |
+
"step": 21
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"entropy": 1.0264459252357483,
|
| 224 |
+
"epoch": 0.44,
|
| 225 |
+
"grad_norm": 0.1576310396194458,
|
| 226 |
+
"learning_rate": 0.0001,
|
| 227 |
+
"loss": 1.0518046617507935,
|
| 228 |
+
"mean_token_accuracy": 0.7142763733863831,
|
| 229 |
+
"num_tokens": 1564657.0,
|
| 230 |
+
"step": 22
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"entropy": 1.059712529182434,
|
| 234 |
+
"epoch": 0.46,
|
| 235 |
+
"grad_norm": 0.15488146245479584,
|
| 236 |
+
"learning_rate": 0.0001,
|
| 237 |
+
"loss": 1.082923412322998,
|
| 238 |
+
"mean_token_accuracy": 0.7053070664405823,
|
| 239 |
+
"num_tokens": 1633972.0,
|
| 240 |
+
"step": 23
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"entropy": 1.0438059866428375,
|
| 244 |
+
"epoch": 0.48,
|
| 245 |
+
"grad_norm": 0.15164747834205627,
|
| 246 |
+
"learning_rate": 0.0001,
|
| 247 |
+
"loss": 1.0578590631484985,
|
| 248 |
+
"mean_token_accuracy": 0.7133743166923523,
|
| 249 |
+
"num_tokens": 1700893.0,
|
| 250 |
+
"step": 24
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"entropy": 0.9979909062385559,
|
| 254 |
+
"epoch": 0.5,
|
| 255 |
+
"grad_norm": 0.14712916314601898,
|
| 256 |
+
"learning_rate": 0.0001,
|
| 257 |
+
"loss": 1.0294842720031738,
|
| 258 |
+
"mean_token_accuracy": 0.7216654419898987,
|
| 259 |
+
"num_tokens": 1767721.0,
|
| 260 |
+
"step": 25
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"entropy": 1.0120922327041626,
|
| 264 |
+
"epoch": 0.52,
|
| 265 |
+
"grad_norm": 0.1360112428665161,
|
| 266 |
+
"learning_rate": 0.0001,
|
| 267 |
+
"loss": 1.0354883670806885,
|
| 268 |
+
"mean_token_accuracy": 0.7223899960517883,
|
| 269 |
+
"num_tokens": 1835156.0,
|
| 270 |
+
"step": 26
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"entropy": 0.9896539449691772,
|
| 274 |
+
"epoch": 0.54,
|
| 275 |
+
"grad_norm": 0.12824475765228271,
|
| 276 |
+
"learning_rate": 0.0001,
|
| 277 |
+
"loss": 1.0203971862792969,
|
| 278 |
+
"mean_token_accuracy": 0.7212119996547699,
|
| 279 |
+
"num_tokens": 1910430.0,
|
| 280 |
+
"step": 27
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"entropy": 0.9603240489959717,
|
| 284 |
+
"epoch": 0.56,
|
| 285 |
+
"grad_norm": 0.1179676204919815,
|
| 286 |
+
"learning_rate": 0.0001,
|
| 287 |
+
"loss": 0.9597353339195251,
|
| 288 |
+
"mean_token_accuracy": 0.7346547842025757,
|
| 289 |
+
"num_tokens": 1985373.0,
|
| 290 |
+
"step": 28
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"entropy": 1.0493255257606506,
|
| 294 |
+
"epoch": 0.58,
|
| 295 |
+
"grad_norm": 0.12462859600782394,
|
| 296 |
+
"learning_rate": 0.0001,
|
| 297 |
+
"loss": 1.0499563217163086,
|
| 298 |
+
"mean_token_accuracy": 0.7120701968669891,
|
| 299 |
+
"num_tokens": 2054409.0,
|
| 300 |
+
"step": 29
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"entropy": 1.0497854351997375,
|
| 304 |
+
"epoch": 0.6,
|
| 305 |
+
"grad_norm": 0.11791805922985077,
|
| 306 |
+
"learning_rate": 0.0001,
|
| 307 |
+
"loss": 1.0524396896362305,
|
| 308 |
+
"mean_token_accuracy": 0.7136416733264923,
|
| 309 |
+
"num_tokens": 2122893.0,
|
| 310 |
+
"step": 30
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"entropy": 1.0638166069984436,
|
| 314 |
+
"epoch": 0.62,
|
| 315 |
+
"grad_norm": 0.12578116357326508,
|
| 316 |
+
"learning_rate": 0.0001,
|
| 317 |
+
"loss": 1.067002534866333,
|
| 318 |
+
"mean_token_accuracy": 0.7095249891281128,
|
| 319 |
+
"num_tokens": 2194755.0,
|
| 320 |
+
"step": 31
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"entropy": 1.099778175354004,
|
| 324 |
+
"epoch": 0.64,
|
| 325 |
+
"grad_norm": 0.12349284440279007,
|
| 326 |
+
"learning_rate": 0.0001,
|
| 327 |
+
"loss": 1.0939478874206543,
|
| 328 |
+
"mean_token_accuracy": 0.7056429386138916,
|
| 329 |
+
"num_tokens": 2262214.0,
|
| 330 |
+
"step": 32
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"entropy": 1.0646151900291443,
|
| 334 |
+
"epoch": 0.66,
|
| 335 |
+
"grad_norm": 0.12846575677394867,
|
| 336 |
+
"learning_rate": 0.0001,
|
| 337 |
+
"loss": 1.0653318166732788,
|
| 338 |
+
"mean_token_accuracy": 0.7122560441493988,
|
| 339 |
+
"num_tokens": 2331419.0,
|
| 340 |
+
"step": 33
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"entropy": 1.0158570408821106,
|
| 344 |
+
"epoch": 0.68,
|
| 345 |
+
"grad_norm": 0.11879603564739227,
|
| 346 |
+
"learning_rate": 0.0001,
|
| 347 |
+
"loss": 1.0267729759216309,
|
| 348 |
+
"mean_token_accuracy": 0.7170567810535431,
|
| 349 |
+
"num_tokens": 2403814.0,
|
| 350 |
+
"step": 34
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"entropy": 1.0103608667850494,
|
| 354 |
+
"epoch": 0.7,
|
| 355 |
+
"grad_norm": 0.12001688033342361,
|
| 356 |
+
"learning_rate": 0.0001,
|
| 357 |
+
"loss": 1.0078749656677246,
|
| 358 |
+
"mean_token_accuracy": 0.7219332754611969,
|
| 359 |
+
"num_tokens": 2474066.0,
|
| 360 |
+
"step": 35
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"entropy": 1.0085046291351318,
|
| 364 |
+
"epoch": 0.72,
|
| 365 |
+
"grad_norm": 0.11229556053876877,
|
| 366 |
+
"learning_rate": 0.0001,
|
| 367 |
+
"loss": 1.015348196029663,
|
| 368 |
+
"mean_token_accuracy": 0.7219782471656799,
|
| 369 |
+
"num_tokens": 2547283.0,
|
| 370 |
+
"step": 36
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"entropy": 1.0116952955722809,
|
| 374 |
+
"epoch": 0.74,
|
| 375 |
+
"grad_norm": 0.12163597345352173,
|
| 376 |
+
"learning_rate": 0.0001,
|
| 377 |
+
"loss": 1.0121233463287354,
|
| 378 |
+
"mean_token_accuracy": 0.7187064588069916,
|
| 379 |
+
"num_tokens": 2613331.0,
|
| 380 |
+
"step": 37
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"entropy": 0.9940676093101501,
|
| 384 |
+
"epoch": 0.76,
|
| 385 |
+
"grad_norm": 0.11075941473245621,
|
| 386 |
+
"learning_rate": 0.0001,
|
| 387 |
+
"loss": 0.992800235748291,
|
| 388 |
+
"mean_token_accuracy": 0.7255141139030457,
|
| 389 |
+
"num_tokens": 2683528.0,
|
| 390 |
+
"step": 38
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"entropy": 1.0126079320907593,
|
| 394 |
+
"epoch": 0.78,
|
| 395 |
+
"grad_norm": 0.11469519883394241,
|
| 396 |
+
"learning_rate": 0.0001,
|
| 397 |
+
"loss": 0.9988532066345215,
|
| 398 |
+
"mean_token_accuracy": 0.7211731672286987,
|
| 399 |
+
"num_tokens": 2750069.0,
|
| 400 |
+
"step": 39
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"entropy": 0.9906446635723114,
|
| 404 |
+
"epoch": 0.8,
|
| 405 |
+
"grad_norm": 0.11193952709436417,
|
| 406 |
+
"learning_rate": 0.0001,
|
| 407 |
+
"loss": 0.9900511503219604,
|
| 408 |
+
"mean_token_accuracy": 0.722189337015152,
|
| 409 |
+
"num_tokens": 2821887.0,
|
| 410 |
+
"step": 40
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"entropy": 0.9898229837417603,
|
| 414 |
+
"epoch": 0.82,
|
| 415 |
+
"grad_norm": 0.11920945346355438,
|
| 416 |
+
"learning_rate": 0.0001,
|
| 417 |
+
"loss": 0.9936800599098206,
|
| 418 |
+
"mean_token_accuracy": 0.7267130017280579,
|
| 419 |
+
"num_tokens": 2885811.0,
|
| 420 |
+
"step": 41
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"entropy": 0.9716921448707581,
|
| 424 |
+
"epoch": 0.84,
|
| 425 |
+
"grad_norm": 0.11293631792068481,
|
| 426 |
+
"learning_rate": 0.0001,
|
| 427 |
+
"loss": 0.9800352454185486,
|
| 428 |
+
"mean_token_accuracy": 0.7265651822090149,
|
| 429 |
+
"num_tokens": 2955201.0,
|
| 430 |
+
"step": 42
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"entropy": 0.9296073317527771,
|
| 434 |
+
"epoch": 0.86,
|
| 435 |
+
"grad_norm": 0.11454292386770248,
|
| 436 |
+
"learning_rate": 0.0001,
|
| 437 |
+
"loss": 0.9429284334182739,
|
| 438 |
+
"mean_token_accuracy": 0.734944611787796,
|
| 439 |
+
"num_tokens": 3019665.0,
|
| 440 |
+
"step": 43
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"entropy": 0.9590237438678741,
|
| 444 |
+
"epoch": 0.88,
|
| 445 |
+
"grad_norm": 0.1102190762758255,
|
| 446 |
+
"learning_rate": 0.0001,
|
| 447 |
+
"loss": 0.9501940011978149,
|
| 448 |
+
"mean_token_accuracy": 0.7321249544620514,
|
| 449 |
+
"num_tokens": 3093335.0,
|
| 450 |
+
"step": 44
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"entropy": 0.9053312838077545,
|
| 454 |
+
"epoch": 0.9,
|
| 455 |
+
"grad_norm": 0.11164271831512451,
|
| 456 |
+
"learning_rate": 0.0001,
|
| 457 |
+
"loss": 0.9103053212165833,
|
| 458 |
+
"mean_token_accuracy": 0.7460834383964539,
|
| 459 |
+
"num_tokens": 3159757.0,
|
| 460 |
+
"step": 45
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"entropy": 0.9606629908084869,
|
| 464 |
+
"epoch": 0.92,
|
| 465 |
+
"grad_norm": 0.11079204827547073,
|
| 466 |
+
"learning_rate": 0.0001,
|
| 467 |
+
"loss": 0.9644097089767456,
|
| 468 |
+
"mean_token_accuracy": 0.7342032492160797,
|
| 469 |
+
"num_tokens": 3230892.0,
|
| 470 |
+
"step": 46
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"entropy": 0.943544864654541,
|
| 474 |
+
"epoch": 0.94,
|
| 475 |
+
"grad_norm": 0.11624015867710114,
|
| 476 |
+
"learning_rate": 0.0001,
|
| 477 |
+
"loss": 0.9410842061042786,
|
| 478 |
+
"mean_token_accuracy": 0.7351740300655365,
|
| 479 |
+
"num_tokens": 3299869.0,
|
| 480 |
+
"step": 47
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"entropy": 0.9592801034450531,
|
| 484 |
+
"epoch": 0.96,
|
| 485 |
+
"grad_norm": 0.11560477316379547,
|
| 486 |
+
"learning_rate": 0.0001,
|
| 487 |
+
"loss": 0.975141704082489,
|
| 488 |
+
"mean_token_accuracy": 0.7269536554813385,
|
| 489 |
+
"num_tokens": 3371272.0,
|
| 490 |
+
"step": 48
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"entropy": 0.9194359481334686,
|
| 494 |
+
"epoch": 0.98,
|
| 495 |
+
"grad_norm": 0.11588755995035172,
|
| 496 |
+
"learning_rate": 0.0001,
|
| 497 |
+
"loss": 0.9375251531600952,
|
| 498 |
+
"mean_token_accuracy": 0.7386307418346405,
|
| 499 |
+
"num_tokens": 3439636.0,
|
| 500 |
+
"step": 49
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"entropy": 0.9375229477882385,
|
| 504 |
+
"epoch": 1.0,
|
| 505 |
+
"grad_norm": 0.10675432533025742,
|
| 506 |
+
"learning_rate": 0.0001,
|
| 507 |
+
"loss": 0.9375709891319275,
|
| 508 |
+
"mean_token_accuracy": 0.7371015846729279,
|
| 509 |
+
"num_tokens": 3515643.0,
|
| 510 |
+
"step": 50
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"entropy": 0.9784637987613678,
|
| 514 |
+
"epoch": 1.02,
|
| 515 |
+
"grad_norm": 0.12157473713159561,
|
| 516 |
+
"learning_rate": 0.0001,
|
| 517 |
+
"loss": 0.9589431881904602,
|
| 518 |
+
"mean_token_accuracy": 0.7312025725841522,
|
| 519 |
+
"num_tokens": 3579936.0,
|
| 520 |
+
"step": 51
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"entropy": 0.9976795613765717,
|
| 524 |
+
"epoch": 1.04,
|
| 525 |
+
"grad_norm": 0.1218739002943039,
|
| 526 |
+
"learning_rate": 0.0001,
|
| 527 |
+
"loss": 0.9651644825935364,
|
| 528 |
+
"mean_token_accuracy": 0.7295917272567749,
|
| 529 |
+
"num_tokens": 3645097.0,
|
| 530 |
+
"step": 52
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"entropy": 0.9457567930221558,
|
| 534 |
+
"epoch": 1.06,
|
| 535 |
+
"grad_norm": 0.11789195984601974,
|
| 536 |
+
"learning_rate": 0.0001,
|
| 537 |
+
"loss": 0.924875020980835,
|
| 538 |
+
"mean_token_accuracy": 0.7387276589870453,
|
| 539 |
+
"num_tokens": 3722386.0,
|
| 540 |
+
"step": 53
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"entropy": 0.9368592202663422,
|
| 544 |
+
"epoch": 1.08,
|
| 545 |
+
"grad_norm": 0.11367881298065186,
|
| 546 |
+
"learning_rate": 0.0001,
|
| 547 |
+
"loss": 0.9108861088752747,
|
| 548 |
+
"mean_token_accuracy": 0.7435753047466278,
|
| 549 |
+
"num_tokens": 3795107.0,
|
| 550 |
+
"step": 54
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"entropy": 0.9856767952442169,
|
| 554 |
+
"epoch": 1.1,
|
| 555 |
+
"grad_norm": 0.1143391951918602,
|
| 556 |
+
"learning_rate": 0.0001,
|
| 557 |
+
"loss": 0.9522716999053955,
|
| 558 |
+
"mean_token_accuracy": 0.7351356148719788,
|
| 559 |
+
"num_tokens": 3863645.0,
|
| 560 |
+
"step": 55
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"entropy": 0.9017468690872192,
|
| 564 |
+
"epoch": 1.12,
|
| 565 |
+
"grad_norm": 0.11213760077953339,
|
| 566 |
+
"learning_rate": 0.0001,
|
| 567 |
+
"loss": 0.890508770942688,
|
| 568 |
+
"mean_token_accuracy": 0.75059974193573,
|
| 569 |
+
"num_tokens": 3933157.0,
|
| 570 |
+
"step": 56
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"entropy": 0.9076333045959473,
|
| 574 |
+
"epoch": 1.1400000000000001,
|
| 575 |
+
"grad_norm": 0.10830755531787872,
|
| 576 |
+
"learning_rate": 0.0001,
|
| 577 |
+
"loss": 0.8893829584121704,
|
| 578 |
+
"mean_token_accuracy": 0.7474276721477509,
|
| 579 |
+
"num_tokens": 4002549.0,
|
| 580 |
+
"step": 57
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"entropy": 0.9090627431869507,
|
| 584 |
+
"epoch": 1.16,
|
| 585 |
+
"grad_norm": 0.11783402413129807,
|
| 586 |
+
"learning_rate": 0.0001,
|
| 587 |
+
"loss": 0.9097412824630737,
|
| 588 |
+
"mean_token_accuracy": 0.7423691749572754,
|
| 589 |
+
"num_tokens": 4068026.0,
|
| 590 |
+
"step": 58
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"entropy": 0.928420215845108,
|
| 594 |
+
"epoch": 1.18,
|
| 595 |
+
"grad_norm": 0.11873085796833038,
|
| 596 |
+
"learning_rate": 0.0001,
|
| 597 |
+
"loss": 0.9404212236404419,
|
| 598 |
+
"mean_token_accuracy": 0.7362638711929321,
|
| 599 |
+
"num_tokens": 4136948.0,
|
| 600 |
+
"step": 59
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"entropy": 0.9221147298812866,
|
| 604 |
+
"epoch": 1.2,
|
| 605 |
+
"grad_norm": 0.11550325155258179,
|
| 606 |
+
"learning_rate": 0.0001,
|
| 607 |
+
"loss": 0.924960732460022,
|
| 608 |
+
"mean_token_accuracy": 0.7427571713924408,
|
| 609 |
+
"num_tokens": 4204112.0,
|
| 610 |
+
"step": 60
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"entropy": 0.9216603636741638,
|
| 614 |
+
"epoch": 1.22,
|
| 615 |
+
"grad_norm": 0.11623509228229523,
|
| 616 |
+
"learning_rate": 0.0001,
|
| 617 |
+
"loss": 0.9106500148773193,
|
| 618 |
+
"mean_token_accuracy": 0.7429015040397644,
|
| 619 |
+
"num_tokens": 4272140.0,
|
| 620 |
+
"step": 61
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"entropy": 0.9455150067806244,
|
| 624 |
+
"epoch": 1.24,
|
| 625 |
+
"grad_norm": 0.11591103672981262,
|
| 626 |
+
"learning_rate": 0.0001,
|
| 627 |
+
"loss": 0.9491208791732788,
|
| 628 |
+
"mean_token_accuracy": 0.7350127100944519,
|
| 629 |
+
"num_tokens": 4346769.0,
|
| 630 |
+
"step": 62
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"entropy": 0.8898249566555023,
|
| 634 |
+
"epoch": 1.26,
|
| 635 |
+
"grad_norm": 0.11488021910190582,
|
| 636 |
+
"learning_rate": 0.0001,
|
| 637 |
+
"loss": 0.8970361351966858,
|
| 638 |
+
"mean_token_accuracy": 0.7481776773929596,
|
| 639 |
+
"num_tokens": 4418760.0,
|
| 640 |
+
"step": 63
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"entropy": 0.8663885295391083,
|
| 644 |
+
"epoch": 1.28,
|
| 645 |
+
"grad_norm": 0.1245160847902298,
|
| 646 |
+
"learning_rate": 0.0001,
|
| 647 |
+
"loss": 0.8572047352790833,
|
| 648 |
+
"mean_token_accuracy": 0.7511683106422424,
|
| 649 |
+
"num_tokens": 4483453.0,
|
| 650 |
+
"step": 64
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"entropy": 0.9115520715713501,
|
| 654 |
+
"epoch": 1.3,
|
| 655 |
+
"grad_norm": 0.12362005561590195,
|
| 656 |
+
"learning_rate": 0.0001,
|
| 657 |
+
"loss": 0.9021918773651123,
|
| 658 |
+
"mean_token_accuracy": 0.7433571219444275,
|
| 659 |
+
"num_tokens": 4553398.0,
|
| 660 |
+
"step": 65
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"entropy": 0.9173152148723602,
|
| 664 |
+
"epoch": 1.32,
|
| 665 |
+
"grad_norm": 0.11844731867313385,
|
| 666 |
+
"learning_rate": 0.0001,
|
| 667 |
+
"loss": 0.9107658863067627,
|
| 668 |
+
"mean_token_accuracy": 0.7352526783943176,
|
| 669 |
+
"num_tokens": 4626227.0,
|
| 670 |
+
"step": 66
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"entropy": 0.849992573261261,
|
| 674 |
+
"epoch": 1.34,
|
| 675 |
+
"grad_norm": 0.11784010380506516,
|
| 676 |
+
"learning_rate": 0.0001,
|
| 677 |
+
"loss": 0.8525710105895996,
|
| 678 |
+
"mean_token_accuracy": 0.7550307512283325,
|
| 679 |
+
"num_tokens": 4701977.0,
|
| 680 |
+
"step": 67
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"entropy": 0.9553567171096802,
|
| 684 |
+
"epoch": 1.3599999999999999,
|
| 685 |
+
"grad_norm": 0.1190195307135582,
|
| 686 |
+
"learning_rate": 0.0001,
|
| 687 |
+
"loss": 0.9455575346946716,
|
| 688 |
+
"mean_token_accuracy": 0.7316735982894897,
|
| 689 |
+
"num_tokens": 4774545.0,
|
| 690 |
+
"step": 68
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"entropy": 0.8593668639659882,
|
| 694 |
+
"epoch": 1.38,
|
| 695 |
+
"grad_norm": 0.11937589198350906,
|
| 696 |
+
"learning_rate": 0.0001,
|
| 697 |
+
"loss": 0.8549792170524597,
|
| 698 |
+
"mean_token_accuracy": 0.7569719552993774,
|
| 699 |
+
"num_tokens": 4847366.0,
|
| 700 |
+
"step": 69
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"entropy": 0.9686211943626404,
|
| 704 |
+
"epoch": 1.4,
|
| 705 |
+
"grad_norm": 0.12214019149541855,
|
| 706 |
+
"learning_rate": 0.0001,
|
| 707 |
+
"loss": 0.9648027420043945,
|
| 708 |
+
"mean_token_accuracy": 0.7249570488929749,
|
| 709 |
+
"num_tokens": 4923060.0,
|
| 710 |
+
"step": 70
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"entropy": 0.867369145154953,
|
| 714 |
+
"epoch": 1.42,
|
| 715 |
+
"grad_norm": 0.11730711907148361,
|
| 716 |
+
"learning_rate": 0.0001,
|
| 717 |
+
"loss": 0.8510935306549072,
|
| 718 |
+
"mean_token_accuracy": 0.7553304731845856,
|
| 719 |
+
"num_tokens": 4996176.0,
|
| 720 |
+
"step": 71
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"entropy": 0.9160025417804718,
|
| 724 |
+
"epoch": 1.44,
|
| 725 |
+
"grad_norm": 0.12190750241279602,
|
| 726 |
+
"learning_rate": 0.0001,
|
| 727 |
+
"loss": 0.9096644520759583,
|
| 728 |
+
"mean_token_accuracy": 0.7384364008903503,
|
| 729 |
+
"num_tokens": 5068522.0,
|
| 730 |
+
"step": 72
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"entropy": 0.9069952070713043,
|
| 734 |
+
"epoch": 1.46,
|
| 735 |
+
"grad_norm": 0.13640820980072021,
|
| 736 |
+
"learning_rate": 0.0001,
|
| 737 |
+
"loss": 0.8875448703765869,
|
| 738 |
+
"mean_token_accuracy": 0.7457329034805298,
|
| 739 |
+
"num_tokens": 5137623.0,
|
| 740 |
+
"step": 73
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"entropy": 0.9026708900928497,
|
| 744 |
+
"epoch": 1.48,
|
| 745 |
+
"grad_norm": 0.12538853287696838,
|
| 746 |
+
"learning_rate": 0.0001,
|
| 747 |
+
"loss": 0.8914889097213745,
|
| 748 |
+
"mean_token_accuracy": 0.7435721457004547,
|
| 749 |
+
"num_tokens": 5208737.0,
|
| 750 |
+
"step": 74
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"entropy": 0.9324445724487305,
|
| 754 |
+
"epoch": 1.5,
|
| 755 |
+
"grad_norm": 0.13337835669517517,
|
| 756 |
+
"learning_rate": 0.0001,
|
| 757 |
+
"loss": 0.9412592649459839,
|
| 758 |
+
"mean_token_accuracy": 0.7320683300495148,
|
| 759 |
+
"num_tokens": 5279457.0,
|
| 760 |
+
"step": 75
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"entropy": 0.8831305801868439,
|
| 764 |
+
"epoch": 1.52,
|
| 765 |
+
"grad_norm": 0.1287890523672104,
|
| 766 |
+
"learning_rate": 0.0001,
|
| 767 |
+
"loss": 0.890162467956543,
|
| 768 |
+
"mean_token_accuracy": 0.7474140524864197,
|
| 769 |
+
"num_tokens": 5344457.0,
|
| 770 |
+
"step": 76
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"entropy": 0.8844259679317474,
|
| 774 |
+
"epoch": 1.54,
|
| 775 |
+
"grad_norm": 0.12595458328723907,
|
| 776 |
+
"learning_rate": 0.0001,
|
| 777 |
+
"loss": 0.8862929940223694,
|
| 778 |
+
"mean_token_accuracy": 0.7448306679725647,
|
| 779 |
+
"num_tokens": 5416486.0,
|
| 780 |
+
"step": 77
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"entropy": 0.9768937230110168,
|
| 784 |
+
"epoch": 1.56,
|
| 785 |
+
"grad_norm": 0.13385823369026184,
|
| 786 |
+
"learning_rate": 0.0001,
|
| 787 |
+
"loss": 0.9855270981788635,
|
| 788 |
+
"mean_token_accuracy": 0.7242069244384766,
|
| 789 |
+
"num_tokens": 5488930.0,
|
| 790 |
+
"step": 78
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"entropy": 0.8970398604869843,
|
| 794 |
+
"epoch": 1.58,
|
| 795 |
+
"grad_norm": 0.12776781618595123,
|
| 796 |
+
"learning_rate": 0.0001,
|
| 797 |
+
"loss": 0.9010695219039917,
|
| 798 |
+
"mean_token_accuracy": 0.7380562722682953,
|
| 799 |
+
"num_tokens": 5558044.0,
|
| 800 |
+
"step": 79
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"entropy": 0.8510560393333435,
|
| 804 |
+
"epoch": 1.6,
|
| 805 |
+
"grad_norm": 0.12845851480960846,
|
| 806 |
+
"learning_rate": 0.0001,
|
| 807 |
+
"loss": 0.8674848675727844,
|
| 808 |
+
"mean_token_accuracy": 0.7530980706214905,
|
| 809 |
+
"num_tokens": 5630814.0,
|
| 810 |
+
"step": 80
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"entropy": 0.9194655120372772,
|
| 814 |
+
"epoch": 1.62,
|
| 815 |
+
"grad_norm": 0.12733094394207,
|
| 816 |
+
"learning_rate": 0.0001,
|
| 817 |
+
"loss": 0.9001493453979492,
|
| 818 |
+
"mean_token_accuracy": 0.7473941147327423,
|
| 819 |
+
"num_tokens": 5696496.0,
|
| 820 |
+
"step": 81
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"entropy": 0.9078547358512878,
|
| 824 |
+
"epoch": 1.6400000000000001,
|
| 825 |
+
"grad_norm": 0.12357509136199951,
|
| 826 |
+
"learning_rate": 0.0001,
|
| 827 |
+
"loss": 0.9031519889831543,
|
| 828 |
+
"mean_token_accuracy": 0.7443413436412811,
|
| 829 |
+
"num_tokens": 5765578.0,
|
| 830 |
+
"step": 82
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"entropy": 0.9426756799221039,
|
| 834 |
+
"epoch": 1.6600000000000001,
|
| 835 |
+
"grad_norm": 0.12899024784564972,
|
| 836 |
+
"learning_rate": 0.0001,
|
| 837 |
+
"loss": 0.9363412857055664,
|
| 838 |
+
"mean_token_accuracy": 0.7349725663661957,
|
| 839 |
+
"num_tokens": 5831979.0,
|
| 840 |
+
"step": 83
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"entropy": 0.9146726131439209,
|
| 844 |
+
"epoch": 1.6800000000000002,
|
| 845 |
+
"grad_norm": 0.12931226193904877,
|
| 846 |
+
"learning_rate": 0.0001,
|
| 847 |
+
"loss": 0.9105992317199707,
|
| 848 |
+
"mean_token_accuracy": 0.7388072907924652,
|
| 849 |
+
"num_tokens": 5905661.0,
|
| 850 |
+
"step": 84
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"entropy": 0.9316370487213135,
|
| 854 |
+
"epoch": 1.7,
|
| 855 |
+
"grad_norm": 0.13409629464149475,
|
| 856 |
+
"learning_rate": 0.0001,
|
| 857 |
+
"loss": 0.9174567461013794,
|
| 858 |
+
"mean_token_accuracy": 0.7437045872211456,
|
| 859 |
+
"num_tokens": 5973162.0,
|
| 860 |
+
"step": 85
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"entropy": 0.9444582164287567,
|
| 864 |
+
"epoch": 1.72,
|
| 865 |
+
"grad_norm": 0.13663342595100403,
|
| 866 |
+
"learning_rate": 0.0001,
|
| 867 |
+
"loss": 0.9291839599609375,
|
| 868 |
+
"mean_token_accuracy": 0.7356755137443542,
|
| 869 |
+
"num_tokens": 6040751.0,
|
| 870 |
+
"step": 86
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"entropy": 0.8949260711669922,
|
| 874 |
+
"epoch": 1.74,
|
| 875 |
+
"grad_norm": 0.12818805873394012,
|
| 876 |
+
"learning_rate": 0.0001,
|
| 877 |
+
"loss": 0.8870834112167358,
|
| 878 |
+
"mean_token_accuracy": 0.7440982460975647,
|
| 879 |
+
"num_tokens": 6112173.0,
|
| 880 |
+
"step": 87
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"entropy": 0.9360968768596649,
|
| 884 |
+
"epoch": 1.76,
|
| 885 |
+
"grad_norm": 0.14662906527519226,
|
| 886 |
+
"learning_rate": 0.0001,
|
| 887 |
+
"loss": 0.9298614859580994,
|
| 888 |
+
"mean_token_accuracy": 0.7370602786540985,
|
| 889 |
+
"num_tokens": 6179601.0,
|
| 890 |
+
"step": 88
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"entropy": 0.8710778653621674,
|
| 894 |
+
"epoch": 1.78,
|
| 895 |
+
"grad_norm": 0.13221921026706696,
|
| 896 |
+
"learning_rate": 0.0001,
|
| 897 |
+
"loss": 0.8649511337280273,
|
| 898 |
+
"mean_token_accuracy": 0.7522627413272858,
|
| 899 |
+
"num_tokens": 6246710.0,
|
| 900 |
+
"step": 89
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"entropy": 0.8752692639827728,
|
| 904 |
+
"epoch": 1.8,
|
| 905 |
+
"grad_norm": 0.14055795967578888,
|
| 906 |
+
"learning_rate": 0.0001,
|
| 907 |
+
"loss": 0.8573565483093262,
|
| 908 |
+
"mean_token_accuracy": 0.754420816898346,
|
| 909 |
+
"num_tokens": 6319796.0,
|
| 910 |
+
"step": 90
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"entropy": 0.779484897851944,
|
| 914 |
+
"epoch": 1.8199999999999998,
|
| 915 |
+
"grad_norm": 0.12845420837402344,
|
| 916 |
+
"learning_rate": 0.0001,
|
| 917 |
+
"loss": 0.7835309505462646,
|
| 918 |
+
"mean_token_accuracy": 0.7740673124790192,
|
| 919 |
+
"num_tokens": 6389425.0,
|
| 920 |
+
"step": 91
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"entropy": 0.8905294835567474,
|
| 924 |
+
"epoch": 1.8399999999999999,
|
| 925 |
+
"grad_norm": 0.1387389600276947,
|
| 926 |
+
"learning_rate": 0.0001,
|
| 927 |
+
"loss": 0.8962739706039429,
|
| 928 |
+
"mean_token_accuracy": 0.7440564632415771,
|
| 929 |
+
"num_tokens": 6460606.0,
|
| 930 |
+
"step": 92
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"entropy": 0.8370858132839203,
|
| 934 |
+
"epoch": 1.8599999999999999,
|
| 935 |
+
"grad_norm": 0.13243098556995392,
|
| 936 |
+
"learning_rate": 0.0001,
|
| 937 |
+
"loss": 0.8395211696624756,
|
| 938 |
+
"mean_token_accuracy": 0.7600894570350647,
|
| 939 |
+
"num_tokens": 6532762.0,
|
| 940 |
+
"step": 93
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"entropy": 0.9130788445472717,
|
| 944 |
+
"epoch": 1.88,
|
| 945 |
+
"grad_norm": 0.13279658555984497,
|
| 946 |
+
"learning_rate": 0.0001,
|
| 947 |
+
"loss": 0.9157933592796326,
|
| 948 |
+
"mean_token_accuracy": 0.7389859557151794,
|
| 949 |
+
"num_tokens": 6601952.0,
|
| 950 |
+
"step": 94
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"entropy": 0.889918178319931,
|
| 954 |
+
"epoch": 1.9,
|
| 955 |
+
"grad_norm": 0.134121835231781,
|
| 956 |
+
"learning_rate": 0.0001,
|
| 957 |
+
"loss": 0.8863574266433716,
|
| 958 |
+
"mean_token_accuracy": 0.7509450018405914,
|
| 959 |
+
"num_tokens": 6667993.0,
|
| 960 |
+
"step": 95
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"entropy": 0.8806619942188263,
|
| 964 |
+
"epoch": 1.92,
|
| 965 |
+
"grad_norm": 0.1342441886663437,
|
| 966 |
+
"learning_rate": 0.0001,
|
| 967 |
+
"loss": 0.8897389769554138,
|
| 968 |
+
"mean_token_accuracy": 0.751017302274704,
|
| 969 |
+
"num_tokens": 6741003.0,
|
| 970 |
+
"step": 96
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"entropy": 0.8719884157180786,
|
| 974 |
+
"epoch": 1.94,
|
| 975 |
+
"grad_norm": 0.13280296325683594,
|
| 976 |
+
"learning_rate": 0.0001,
|
| 977 |
+
"loss": 0.8737912178039551,
|
| 978 |
+
"mean_token_accuracy": 0.748961865901947,
|
| 979 |
+
"num_tokens": 6814733.0,
|
| 980 |
+
"step": 97
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"entropy": 0.9378086924552917,
|
| 984 |
+
"epoch": 1.96,
|
| 985 |
+
"grad_norm": 0.142800435423851,
|
| 986 |
+
"learning_rate": 0.0001,
|
| 987 |
+
"loss": 0.928570032119751,
|
| 988 |
+
"mean_token_accuracy": 0.7347837388515472,
|
| 989 |
+
"num_tokens": 6887723.0,
|
| 990 |
+
"step": 98
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"entropy": 0.8699579238891602,
|
| 994 |
+
"epoch": 1.98,
|
| 995 |
+
"grad_norm": 0.13884496688842773,
|
| 996 |
+
"learning_rate": 0.0001,
|
| 997 |
+
"loss": 0.8652123808860779,
|
| 998 |
+
"mean_token_accuracy": 0.7550584077835083,
|
| 999 |
+
"num_tokens": 6957156.0,
|
| 1000 |
+
"step": 99
|
| 1001 |
+
},
|
| 1002 |
+
{
|
| 1003 |
+
"entropy": 0.8680048286914825,
|
| 1004 |
+
"epoch": 2.0,
|
| 1005 |
+
"grad_norm": 0.13625894486904144,
|
| 1006 |
+
"learning_rate": 0.0001,
|
| 1007 |
+
"loss": 0.8566628694534302,
|
| 1008 |
+
"mean_token_accuracy": 0.7550990581512451,
|
| 1009 |
+
"num_tokens": 7030824.0,
|
| 1010 |
+
"step": 100
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"entropy": 0.8759163916110992,
|
| 1014 |
+
"epoch": 2.02,
|
| 1015 |
+
"grad_norm": 0.13642925024032593,
|
| 1016 |
+
"learning_rate": 0.0001,
|
| 1017 |
+
"loss": 0.8173877596855164,
|
| 1018 |
+
"mean_token_accuracy": 0.7642171382904053,
|
| 1019 |
+
"num_tokens": 7099794.0,
|
| 1020 |
+
"step": 101
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"entropy": 0.872030109167099,
|
| 1024 |
+
"epoch": 2.04,
|
| 1025 |
+
"grad_norm": 0.13444599509239197,
|
| 1026 |
+
"learning_rate": 0.0001,
|
| 1027 |
+
"loss": 0.8315644860267639,
|
| 1028 |
+
"mean_token_accuracy": 0.7598301768302917,
|
| 1029 |
+
"num_tokens": 7168851.0,
|
| 1030 |
+
"step": 102
|
| 1031 |
+
},
|
| 1032 |
+
{
|
| 1033 |
+
"entropy": 0.8999165594577789,
|
| 1034 |
+
"epoch": 2.06,
|
| 1035 |
+
"grad_norm": 0.14029845595359802,
|
| 1036 |
+
"learning_rate": 0.0001,
|
| 1037 |
+
"loss": 0.8543646335601807,
|
| 1038 |
+
"mean_token_accuracy": 0.7513293921947479,
|
| 1039 |
+
"num_tokens": 7239717.0,
|
| 1040 |
+
"step": 103
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"entropy": 0.8488370180130005,
|
| 1044 |
+
"epoch": 2.08,
|
| 1045 |
+
"grad_norm": 0.13906973600387573,
|
| 1046 |
+
"learning_rate": 0.0001,
|
| 1047 |
+
"loss": 0.8071736097335815,
|
| 1048 |
+
"mean_token_accuracy": 0.768627405166626,
|
| 1049 |
+
"num_tokens": 7310897.0,
|
| 1050 |
+
"step": 104
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"entropy": 0.8458687663078308,
|
| 1054 |
+
"epoch": 2.1,
|
| 1055 |
+
"grad_norm": 0.14410872757434845,
|
| 1056 |
+
"learning_rate": 0.0001,
|
| 1057 |
+
"loss": 0.8336784243583679,
|
| 1058 |
+
"mean_token_accuracy": 0.7576306164264679,
|
| 1059 |
+
"num_tokens": 7381044.0,
|
| 1060 |
+
"step": 105
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"entropy": 0.8117028772830963,
|
| 1064 |
+
"epoch": 2.12,
|
| 1065 |
+
"grad_norm": 0.15016138553619385,
|
| 1066 |
+
"learning_rate": 0.0001,
|
| 1067 |
+
"loss": 0.8016491532325745,
|
| 1068 |
+
"mean_token_accuracy": 0.761463850736618,
|
| 1069 |
+
"num_tokens": 7448539.0,
|
| 1070 |
+
"step": 106
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"entropy": 0.8423402607440948,
|
| 1074 |
+
"epoch": 2.14,
|
| 1075 |
+
"grad_norm": 0.14620108902454376,
|
| 1076 |
+
"learning_rate": 0.0001,
|
| 1077 |
+
"loss": 0.8520156145095825,
|
| 1078 |
+
"mean_token_accuracy": 0.7559936344623566,
|
| 1079 |
+
"num_tokens": 7523326.0,
|
| 1080 |
+
"step": 107
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"entropy": 0.7789672613143921,
|
| 1084 |
+
"epoch": 2.16,
|
| 1085 |
+
"grad_norm": 0.14582377672195435,
|
| 1086 |
+
"learning_rate": 0.0001,
|
| 1087 |
+
"loss": 0.7745522260665894,
|
| 1088 |
+
"mean_token_accuracy": 0.7746096849441528,
|
| 1089 |
+
"num_tokens": 7589964.0,
|
| 1090 |
+
"step": 108
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"entropy": 0.8252202570438385,
|
| 1094 |
+
"epoch": 2.18,
|
| 1095 |
+
"grad_norm": 0.15269358456134796,
|
| 1096 |
+
"learning_rate": 0.0001,
|
| 1097 |
+
"loss": 0.8253834247589111,
|
| 1098 |
+
"mean_token_accuracy": 0.760587066411972,
|
| 1099 |
+
"num_tokens": 7663822.0,
|
| 1100 |
+
"step": 109
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"entropy": 0.8460159599781036,
|
| 1104 |
+
"epoch": 2.2,
|
| 1105 |
+
"grad_norm": 0.15312956273555756,
|
| 1106 |
+
"learning_rate": 0.0001,
|
| 1107 |
+
"loss": 0.834621012210846,
|
| 1108 |
+
"mean_token_accuracy": 0.7548129558563232,
|
| 1109 |
+
"num_tokens": 7736094.0,
|
| 1110 |
+
"step": 110
|
| 1111 |
+
},
|
| 1112 |
+
{
|
| 1113 |
+
"entropy": 0.8546044528484344,
|
| 1114 |
+
"epoch": 2.22,
|
| 1115 |
+
"grad_norm": 0.1496986299753189,
|
| 1116 |
+
"learning_rate": 0.0001,
|
| 1117 |
+
"loss": 0.8300120830535889,
|
| 1118 |
+
"mean_token_accuracy": 0.759436160326004,
|
| 1119 |
+
"num_tokens": 7812027.0,
|
| 1120 |
+
"step": 111
|
| 1121 |
+
},
|
| 1122 |
+
{
|
| 1123 |
+
"entropy": 0.754067599773407,
|
| 1124 |
+
"epoch": 2.24,
|
| 1125 |
+
"grad_norm": 0.1404401957988739,
|
| 1126 |
+
"learning_rate": 0.0001,
|
| 1127 |
+
"loss": 0.7299779653549194,
|
| 1128 |
+
"mean_token_accuracy": 0.7858331501483917,
|
| 1129 |
+
"num_tokens": 7881889.0,
|
| 1130 |
+
"step": 112
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"entropy": 0.8271636366844177,
|
| 1134 |
+
"epoch": 2.26,
|
| 1135 |
+
"grad_norm": 0.15130330622196198,
|
| 1136 |
+
"learning_rate": 0.0001,
|
| 1137 |
+
"loss": 0.8026934862136841,
|
| 1138 |
+
"mean_token_accuracy": 0.7606152594089508,
|
| 1139 |
+
"num_tokens": 7958772.0,
|
| 1140 |
+
"step": 113
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"entropy": 0.8311681747436523,
|
| 1144 |
+
"epoch": 2.2800000000000002,
|
| 1145 |
+
"grad_norm": 0.15545408427715302,
|
| 1146 |
+
"learning_rate": 0.0001,
|
| 1147 |
+
"loss": 0.8179649114608765,
|
| 1148 |
+
"mean_token_accuracy": 0.7627213597297668,
|
| 1149 |
+
"num_tokens": 8029445.0,
|
| 1150 |
+
"step": 114
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"entropy": 0.8371923565864563,
|
| 1154 |
+
"epoch": 2.3,
|
| 1155 |
+
"grad_norm": 0.15620867908000946,
|
| 1156 |
+
"learning_rate": 0.0001,
|
| 1157 |
+
"loss": 0.8322392106056213,
|
| 1158 |
+
"mean_token_accuracy": 0.7557950615882874,
|
| 1159 |
+
"num_tokens": 8100496.0,
|
| 1160 |
+
"step": 115
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"entropy": 0.8774853646755219,
|
| 1164 |
+
"epoch": 2.32,
|
| 1165 |
+
"grad_norm": 0.16020546853542328,
|
| 1166 |
+
"learning_rate": 0.0001,
|
| 1167 |
+
"loss": 0.8756296634674072,
|
| 1168 |
+
"mean_token_accuracy": 0.7484939396381378,
|
| 1169 |
+
"num_tokens": 8172797.0,
|
| 1170 |
+
"step": 116
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"entropy": 0.7841235101222992,
|
| 1174 |
+
"epoch": 2.34,
|
| 1175 |
+
"grad_norm": 0.16341933608055115,
|
| 1176 |
+
"learning_rate": 0.0001,
|
| 1177 |
+
"loss": 0.7845247387886047,
|
| 1178 |
+
"mean_token_accuracy": 0.7680597603321075,
|
| 1179 |
+
"num_tokens": 8239973.0,
|
| 1180 |
+
"step": 117
|
| 1181 |
+
},
|
| 1182 |
+
{
|
| 1183 |
+
"entropy": 0.8059554100036621,
|
| 1184 |
+
"epoch": 2.36,
|
| 1185 |
+
"grad_norm": 0.14973363280296326,
|
| 1186 |
+
"learning_rate": 0.0001,
|
| 1187 |
+
"loss": 0.7868502140045166,
|
| 1188 |
+
"mean_token_accuracy": 0.7696151733398438,
|
| 1189 |
+
"num_tokens": 8312997.0,
|
| 1190 |
+
"step": 118
|
| 1191 |
+
},
|
| 1192 |
+
{
|
| 1193 |
+
"entropy": 0.790012925863266,
|
| 1194 |
+
"epoch": 2.38,
|
| 1195 |
+
"grad_norm": 0.15735657513141632,
|
| 1196 |
+
"learning_rate": 0.0001,
|
| 1197 |
+
"loss": 0.7770582437515259,
|
| 1198 |
+
"mean_token_accuracy": 0.7715879082679749,
|
| 1199 |
+
"num_tokens": 8380963.0,
|
| 1200 |
+
"step": 119
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"entropy": 0.7878563702106476,
|
| 1204 |
+
"epoch": 2.4,
|
| 1205 |
+
"grad_norm": 0.15908536314964294,
|
| 1206 |
+
"learning_rate": 0.0001,
|
| 1207 |
+
"loss": 0.7946950197219849,
|
| 1208 |
+
"mean_token_accuracy": 0.7720945775508881,
|
| 1209 |
+
"num_tokens": 8453009.0,
|
| 1210 |
+
"step": 120
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"entropy": 0.8163405060768127,
|
| 1214 |
+
"epoch": 2.42,
|
| 1215 |
+
"grad_norm": 0.15914228558540344,
|
| 1216 |
+
"learning_rate": 0.0001,
|
| 1217 |
+
"loss": 0.8022626042366028,
|
| 1218 |
+
"mean_token_accuracy": 0.765992671251297,
|
| 1219 |
+
"num_tokens": 8522525.0,
|
| 1220 |
+
"step": 121
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"entropy": 0.8679061532020569,
|
| 1224 |
+
"epoch": 2.44,
|
| 1225 |
+
"grad_norm": 0.1549653708934784,
|
| 1226 |
+
"learning_rate": 0.0001,
|
| 1227 |
+
"loss": 0.8452656269073486,
|
| 1228 |
+
"mean_token_accuracy": 0.7564500868320465,
|
| 1229 |
+
"num_tokens": 8591511.0,
|
| 1230 |
+
"step": 122
|
| 1231 |
+
},
|
| 1232 |
+
{
|
| 1233 |
+
"entropy": 0.8327716588973999,
|
| 1234 |
+
"epoch": 2.46,
|
| 1235 |
+
"grad_norm": 0.16247446835041046,
|
| 1236 |
+
"learning_rate": 0.0001,
|
| 1237 |
+
"loss": 0.8243684768676758,
|
| 1238 |
+
"mean_token_accuracy": 0.7590730786323547,
|
| 1239 |
+
"num_tokens": 8665286.0,
|
| 1240 |
+
"step": 123
|
| 1241 |
+
},
|
| 1242 |
+
{
|
| 1243 |
+
"entropy": 0.7765352427959442,
|
| 1244 |
+
"epoch": 2.48,
|
| 1245 |
+
"grad_norm": 0.15758228302001953,
|
| 1246 |
+
"learning_rate": 0.0001,
|
| 1247 |
+
"loss": 0.7422535419464111,
|
| 1248 |
+
"mean_token_accuracy": 0.783282607793808,
|
| 1249 |
+
"num_tokens": 8730146.0,
|
| 1250 |
+
"step": 124
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"entropy": 0.8039740025997162,
|
| 1254 |
+
"epoch": 2.5,
|
| 1255 |
+
"grad_norm": 0.1573210507631302,
|
| 1256 |
+
"learning_rate": 0.0001,
|
| 1257 |
+
"loss": 0.7967308759689331,
|
| 1258 |
+
"mean_token_accuracy": 0.7692459225654602,
|
| 1259 |
+
"num_tokens": 8801629.0,
|
| 1260 |
+
"step": 125
|
| 1261 |
+
},
|
| 1262 |
+
{
|
| 1263 |
+
"entropy": 0.8415170609951019,
|
| 1264 |
+
"epoch": 2.52,
|
| 1265 |
+
"grad_norm": 0.16268476843833923,
|
| 1266 |
+
"learning_rate": 0.0001,
|
| 1267 |
+
"loss": 0.8165377378463745,
|
| 1268 |
+
"mean_token_accuracy": 0.7615750133991241,
|
| 1269 |
+
"num_tokens": 8877985.0,
|
| 1270 |
+
"step": 126
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"entropy": 0.8203210234642029,
|
| 1274 |
+
"epoch": 2.54,
|
| 1275 |
+
"grad_norm": 0.16346436738967896,
|
| 1276 |
+
"learning_rate": 0.0001,
|
| 1277 |
+
"loss": 0.8121747970581055,
|
| 1278 |
+
"mean_token_accuracy": 0.761315256357193,
|
| 1279 |
+
"num_tokens": 8951559.0,
|
| 1280 |
+
"step": 127
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"entropy": 0.8293347358703613,
|
| 1284 |
+
"epoch": 2.56,
|
| 1285 |
+
"grad_norm": 0.17023281753063202,
|
| 1286 |
+
"learning_rate": 0.0001,
|
| 1287 |
+
"loss": 0.8173530101776123,
|
| 1288 |
+
"mean_token_accuracy": 0.759048581123352,
|
| 1289 |
+
"num_tokens": 9021509.0,
|
| 1290 |
+
"step": 128
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"entropy": 0.7746993601322174,
|
| 1294 |
+
"epoch": 2.58,
|
| 1295 |
+
"grad_norm": 0.1615564227104187,
|
| 1296 |
+
"learning_rate": 0.0001,
|
| 1297 |
+
"loss": 0.7658690214157104,
|
| 1298 |
+
"mean_token_accuracy": 0.7726005017757416,
|
| 1299 |
+
"num_tokens": 9090508.0,
|
| 1300 |
+
"step": 129
|
| 1301 |
+
},
|
| 1302 |
+
{
|
| 1303 |
+
"entropy": 0.8143576085567474,
|
| 1304 |
+
"epoch": 2.6,
|
| 1305 |
+
"grad_norm": 0.1704084575176239,
|
| 1306 |
+
"learning_rate": 0.0001,
|
| 1307 |
+
"loss": 0.8276199102401733,
|
| 1308 |
+
"mean_token_accuracy": 0.7586769461631775,
|
| 1309 |
+
"num_tokens": 9156045.0,
|
| 1310 |
+
"step": 130
|
| 1311 |
+
},
|
| 1312 |
+
{
|
| 1313 |
+
"entropy": 0.7868927419185638,
|
| 1314 |
+
"epoch": 2.62,
|
| 1315 |
+
"grad_norm": 0.16065886616706848,
|
| 1316 |
+
"learning_rate": 0.0001,
|
| 1317 |
+
"loss": 0.7649659514427185,
|
| 1318 |
+
"mean_token_accuracy": 0.7774228751659393,
|
| 1319 |
+
"num_tokens": 9221515.0,
|
| 1320 |
+
"step": 131
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"entropy": 0.8241930305957794,
|
| 1324 |
+
"epoch": 2.64,
|
| 1325 |
+
"grad_norm": 0.1710738241672516,
|
| 1326 |
+
"learning_rate": 0.0001,
|
| 1327 |
+
"loss": 0.8104192018508911,
|
| 1328 |
+
"mean_token_accuracy": 0.7651428282260895,
|
| 1329 |
+
"num_tokens": 9290829.0,
|
| 1330 |
+
"step": 132
|
| 1331 |
+
},
|
| 1332 |
+
{
|
| 1333 |
+
"entropy": 0.7782109975814819,
|
| 1334 |
+
"epoch": 2.66,
|
| 1335 |
+
"grad_norm": 0.3252999484539032,
|
| 1336 |
+
"learning_rate": 0.0001,
|
| 1337 |
+
"loss": 0.7537873983383179,
|
| 1338 |
+
"mean_token_accuracy": 0.7770578563213348,
|
| 1339 |
+
"num_tokens": 9358923.0,
|
| 1340 |
+
"step": 133
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"entropy": 0.7932650744915009,
|
| 1344 |
+
"epoch": 2.68,
|
| 1345 |
+
"grad_norm": 0.16687457263469696,
|
| 1346 |
+
"learning_rate": 0.0001,
|
| 1347 |
+
"loss": 0.771995484828949,
|
| 1348 |
+
"mean_token_accuracy": 0.7717720866203308,
|
| 1349 |
+
"num_tokens": 9431495.0,
|
| 1350 |
+
"step": 134
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"entropy": 0.8635589182376862,
|
| 1354 |
+
"epoch": 2.7,
|
| 1355 |
+
"grad_norm": 0.17788194119930267,
|
| 1356 |
+
"learning_rate": 0.0001,
|
| 1357 |
+
"loss": 0.839271605014801,
|
| 1358 |
+
"mean_token_accuracy": 0.7549299001693726,
|
| 1359 |
+
"num_tokens": 9502949.0,
|
| 1360 |
+
"step": 135
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"entropy": 0.8827160894870758,
|
| 1364 |
+
"epoch": 2.7199999999999998,
|
| 1365 |
+
"grad_norm": 0.17214906215667725,
|
| 1366 |
+
"learning_rate": 0.0001,
|
| 1367 |
+
"loss": 0.8584389686584473,
|
| 1368 |
+
"mean_token_accuracy": 0.7523661851882935,
|
| 1369 |
+
"num_tokens": 9572738.0,
|
| 1370 |
+
"step": 136
|
| 1371 |
+
},
|
| 1372 |
+
{
|
| 1373 |
+
"entropy": 0.7438818514347076,
|
| 1374 |
+
"epoch": 2.74,
|
| 1375 |
+
"grad_norm": 0.15866513550281525,
|
| 1376 |
+
"learning_rate": 0.0001,
|
| 1377 |
+
"loss": 0.7251607179641724,
|
| 1378 |
+
"mean_token_accuracy": 0.7865616679191589,
|
| 1379 |
+
"num_tokens": 9643339.0,
|
| 1380 |
+
"step": 137
|
| 1381 |
+
},
|
| 1382 |
+
{
|
| 1383 |
+
"entropy": 0.8008526265621185,
|
| 1384 |
+
"epoch": 2.76,
|
| 1385 |
+
"grad_norm": 0.17728553712368011,
|
| 1386 |
+
"learning_rate": 0.0001,
|
| 1387 |
+
"loss": 0.7907190322875977,
|
| 1388 |
+
"mean_token_accuracy": 0.7696272730827332,
|
| 1389 |
+
"num_tokens": 9712087.0,
|
| 1390 |
+
"step": 138
|
| 1391 |
+
},
|
| 1392 |
+
{
|
| 1393 |
+
"entropy": 0.7775652408599854,
|
| 1394 |
+
"epoch": 2.7800000000000002,
|
| 1395 |
+
"grad_norm": 0.16898134350776672,
|
| 1396 |
+
"learning_rate": 0.0001,
|
| 1397 |
+
"loss": 0.7762832641601562,
|
| 1398 |
+
"mean_token_accuracy": 0.7671337127685547,
|
| 1399 |
+
"num_tokens": 9787274.0,
|
| 1400 |
+
"step": 139
|
| 1401 |
+
},
|
| 1402 |
+
{
|
| 1403 |
+
"entropy": 0.7524736523628235,
|
| 1404 |
+
"epoch": 2.8,
|
| 1405 |
+
"grad_norm": 0.1687132865190506,
|
| 1406 |
+
"learning_rate": 0.0001,
|
| 1407 |
+
"loss": 0.7515966892242432,
|
| 1408 |
+
"mean_token_accuracy": 0.7743718028068542,
|
| 1409 |
+
"num_tokens": 9850649.0,
|
| 1410 |
+
"step": 140
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"entropy": 0.784816324710846,
|
| 1414 |
+
"epoch": 2.82,
|
| 1415 |
+
"grad_norm": 0.16266104578971863,
|
| 1416 |
+
"learning_rate": 0.0001,
|
| 1417 |
+
"loss": 0.7850303649902344,
|
| 1418 |
+
"mean_token_accuracy": 0.7671224176883698,
|
| 1419 |
+
"num_tokens": 9919647.0,
|
| 1420 |
+
"step": 141
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"entropy": 0.845661848783493,
|
| 1424 |
+
"epoch": 2.84,
|
| 1425 |
+
"grad_norm": 0.177549347281456,
|
| 1426 |
+
"learning_rate": 0.0001,
|
| 1427 |
+
"loss": 0.8321537375450134,
|
| 1428 |
+
"mean_token_accuracy": 0.7545971870422363,
|
| 1429 |
+
"num_tokens": 9988951.0,
|
| 1430 |
+
"step": 142
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"entropy": 0.7890813946723938,
|
| 1434 |
+
"epoch": 2.86,
|
| 1435 |
+
"grad_norm": 0.16998162865638733,
|
| 1436 |
+
"learning_rate": 0.0001,
|
| 1437 |
+
"loss": 0.7851375937461853,
|
| 1438 |
+
"mean_token_accuracy": 0.77273029088974,
|
| 1439 |
+
"num_tokens": 10059418.0,
|
| 1440 |
+
"step": 143
|
| 1441 |
+
},
|
| 1442 |
+
{
|
| 1443 |
+
"entropy": 0.8383583724498749,
|
| 1444 |
+
"epoch": 2.88,
|
| 1445 |
+
"grad_norm": 0.16811728477478027,
|
| 1446 |
+
"learning_rate": 0.0001,
|
| 1447 |
+
"loss": 0.8264563083648682,
|
| 1448 |
+
"mean_token_accuracy": 0.7561212778091431,
|
| 1449 |
+
"num_tokens": 10130582.0,
|
| 1450 |
+
"step": 144
|
| 1451 |
+
},
|
| 1452 |
+
{
|
| 1453 |
+
"entropy": 0.7998828291893005,
|
| 1454 |
+
"epoch": 2.9,
|
| 1455 |
+
"grad_norm": 0.162356436252594,
|
| 1456 |
+
"learning_rate": 0.0001,
|
| 1457 |
+
"loss": 0.7867046594619751,
|
| 1458 |
+
"mean_token_accuracy": 0.7678299248218536,
|
| 1459 |
+
"num_tokens": 10205184.0,
|
| 1460 |
+
"step": 145
|
| 1461 |
+
},
|
| 1462 |
+
{
|
| 1463 |
+
"entropy": 0.8201400637626648,
|
| 1464 |
+
"epoch": 2.92,
|
| 1465 |
+
"grad_norm": 0.1775413304567337,
|
| 1466 |
+
"learning_rate": 0.0001,
|
| 1467 |
+
"loss": 0.8155138492584229,
|
| 1468 |
+
"mean_token_accuracy": 0.7631427645683289,
|
| 1469 |
+
"num_tokens": 10272128.0,
|
| 1470 |
+
"step": 146
|
| 1471 |
+
},
|
| 1472 |
+
{
|
| 1473 |
+
"entropy": 0.8001563251018524,
|
| 1474 |
+
"epoch": 2.94,
|
| 1475 |
+
"grad_norm": 0.1714172512292862,
|
| 1476 |
+
"learning_rate": 0.0001,
|
| 1477 |
+
"loss": 0.7718967795372009,
|
| 1478 |
+
"mean_token_accuracy": 0.7731671333312988,
|
| 1479 |
+
"num_tokens": 10339140.0,
|
| 1480 |
+
"step": 147
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"entropy": 0.8686825633049011,
|
| 1484 |
+
"epoch": 2.96,
|
| 1485 |
+
"grad_norm": 0.1718156337738037,
|
| 1486 |
+
"learning_rate": 0.0001,
|
| 1487 |
+
"loss": 0.841813862323761,
|
| 1488 |
+
"mean_token_accuracy": 0.7538741528987885,
|
| 1489 |
+
"num_tokens": 10405402.0,
|
| 1490 |
+
"step": 148
|
| 1491 |
+
},
|
| 1492 |
+
{
|
| 1493 |
+
"entropy": 0.8255911767482758,
|
| 1494 |
+
"epoch": 2.98,
|
| 1495 |
+
"grad_norm": 0.17787101864814758,
|
| 1496 |
+
"learning_rate": 0.0001,
|
| 1497 |
+
"loss": 0.7991260290145874,
|
| 1498 |
+
"mean_token_accuracy": 0.7636489570140839,
|
| 1499 |
+
"num_tokens": 10473811.0,
|
| 1500 |
+
"step": 149
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"entropy": 0.8001417219638824,
|
| 1504 |
+
"epoch": 3.0,
|
| 1505 |
+
"grad_norm": 0.17027507722377777,
|
| 1506 |
+
"learning_rate": 0.0001,
|
| 1507 |
+
"loss": 0.7719438076019287,
|
| 1508 |
+
"mean_token_accuracy": 0.7698873281478882,
|
| 1509 |
+
"num_tokens": 10546089.0,
|
| 1510 |
+
"step": 150
|
| 1511 |
+
},
|
| 1512 |
+
{
|
| 1513 |
+
"entropy": 0.8200977146625519,
|
| 1514 |
+
"epoch": 3.02,
|
| 1515 |
+
"grad_norm": 0.16800017654895782,
|
| 1516 |
+
"learning_rate": 0.0001,
|
| 1517 |
+
"loss": 0.7360785007476807,
|
| 1518 |
+
"mean_token_accuracy": 0.7826903462409973,
|
| 1519 |
+
"num_tokens": 10618015.0,
|
| 1520 |
+
"step": 151
|
| 1521 |
+
},
|
| 1522 |
+
{
|
| 1523 |
+
"entropy": 0.8175333142280579,
|
| 1524 |
+
"epoch": 3.04,
|
| 1525 |
+
"grad_norm": 0.18896523118019104,
|
| 1526 |
+
"learning_rate": 0.0001,
|
| 1527 |
+
"loss": 0.7504415512084961,
|
| 1528 |
+
"mean_token_accuracy": 0.7746379971504211,
|
| 1529 |
+
"num_tokens": 10688911.0,
|
| 1530 |
+
"step": 152
|
| 1531 |
+
},
|
| 1532 |
+
{
|
| 1533 |
+
"entropy": 0.7592836618423462,
|
| 1534 |
+
"epoch": 3.06,
|
| 1535 |
+
"grad_norm": 0.18069066107273102,
|
| 1536 |
+
"learning_rate": 0.0001,
|
| 1537 |
+
"loss": 0.7176339626312256,
|
| 1538 |
+
"mean_token_accuracy": 0.7862937152385712,
|
| 1539 |
+
"num_tokens": 10755190.0,
|
| 1540 |
+
"step": 153
|
| 1541 |
+
},
|
| 1542 |
+
{
|
| 1543 |
+
"entropy": 0.7064773738384247,
|
| 1544 |
+
"epoch": 3.08,
|
| 1545 |
+
"grad_norm": 0.17506442964076996,
|
| 1546 |
+
"learning_rate": 0.0001,
|
| 1547 |
+
"loss": 0.6661837697029114,
|
| 1548 |
+
"mean_token_accuracy": 0.7990798652172089,
|
| 1549 |
+
"num_tokens": 10824572.0,
|
| 1550 |
+
"step": 154
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"entropy": 0.7049046158790588,
|
| 1554 |
+
"epoch": 3.1,
|
| 1555 |
+
"grad_norm": 0.18128055334091187,
|
| 1556 |
+
"learning_rate": 0.0001,
|
| 1557 |
+
"loss": 0.6970986127853394,
|
| 1558 |
+
"mean_token_accuracy": 0.7910968661308289,
|
| 1559 |
+
"num_tokens": 10897921.0,
|
| 1560 |
+
"step": 155
|
| 1561 |
+
},
|
| 1562 |
+
{
|
| 1563 |
+
"entropy": 0.7131330072879791,
|
| 1564 |
+
"epoch": 3.12,
|
| 1565 |
+
"grad_norm": 0.1793287843465805,
|
| 1566 |
+
"learning_rate": 0.0001,
|
| 1567 |
+
"loss": 0.6969539523124695,
|
| 1568 |
+
"mean_token_accuracy": 0.7904528379440308,
|
| 1569 |
+
"num_tokens": 10967473.0,
|
| 1570 |
+
"step": 156
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"entropy": 0.7718028426170349,
|
| 1574 |
+
"epoch": 3.14,
|
| 1575 |
+
"grad_norm": 0.18882189691066742,
|
| 1576 |
+
"learning_rate": 0.0001,
|
| 1577 |
+
"loss": 0.7447178959846497,
|
| 1578 |
+
"mean_token_accuracy": 0.7770456969738007,
|
| 1579 |
+
"num_tokens": 11040256.0,
|
| 1580 |
+
"step": 157
|
| 1581 |
+
},
|
| 1582 |
+
{
|
| 1583 |
+
"entropy": 0.753845751285553,
|
| 1584 |
+
"epoch": 3.16,
|
| 1585 |
+
"grad_norm": 0.20335878431797028,
|
| 1586 |
+
"learning_rate": 0.0001,
|
| 1587 |
+
"loss": 0.7178476452827454,
|
| 1588 |
+
"mean_token_accuracy": 0.7853229939937592,
|
| 1589 |
+
"num_tokens": 11106853.0,
|
| 1590 |
+
"step": 158
|
| 1591 |
+
},
|
| 1592 |
+
{
|
| 1593 |
+
"entropy": 0.6985587477684021,
|
| 1594 |
+
"epoch": 3.18,
|
| 1595 |
+
"grad_norm": 0.18876291811466217,
|
| 1596 |
+
"learning_rate": 0.0001,
|
| 1597 |
+
"loss": 0.6741787195205688,
|
| 1598 |
+
"mean_token_accuracy": 0.7952553629875183,
|
| 1599 |
+
"num_tokens": 11178868.0,
|
| 1600 |
+
"step": 159
|
| 1601 |
+
},
|
| 1602 |
+
{
|
| 1603 |
+
"entropy": 0.7184737622737885,
|
| 1604 |
+
"epoch": 3.2,
|
| 1605 |
+
"grad_norm": 0.19795499742031097,
|
| 1606 |
+
"learning_rate": 0.0001,
|
| 1607 |
+
"loss": 0.6854847073554993,
|
| 1608 |
+
"mean_token_accuracy": 0.7917522490024567,
|
| 1609 |
+
"num_tokens": 11246484.0,
|
| 1610 |
+
"step": 160
|
| 1611 |
+
},
|
| 1612 |
+
{
|
| 1613 |
+
"entropy": 0.7506313323974609,
|
| 1614 |
+
"epoch": 3.22,
|
| 1615 |
+
"grad_norm": 0.2013498693704605,
|
| 1616 |
+
"learning_rate": 0.0001,
|
| 1617 |
+
"loss": 0.7236944437026978,
|
| 1618 |
+
"mean_token_accuracy": 0.7839900851249695,
|
| 1619 |
+
"num_tokens": 11319820.0,
|
| 1620 |
+
"step": 161
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"entropy": 0.7317833006381989,
|
| 1624 |
+
"epoch": 3.24,
|
| 1625 |
+
"grad_norm": 0.19697904586791992,
|
| 1626 |
+
"learning_rate": 0.0001,
|
| 1627 |
+
"loss": 0.7071319222450256,
|
| 1628 |
+
"mean_token_accuracy": 0.7910904288291931,
|
| 1629 |
+
"num_tokens": 11389201.0,
|
| 1630 |
+
"step": 162
|
| 1631 |
+
},
|
| 1632 |
+
{
|
| 1633 |
+
"entropy": 0.7270588874816895,
|
| 1634 |
+
"epoch": 3.26,
|
| 1635 |
+
"grad_norm": 0.19727207720279694,
|
| 1636 |
+
"learning_rate": 0.0001,
|
| 1637 |
+
"loss": 0.7034903168678284,
|
| 1638 |
+
"mean_token_accuracy": 0.7924522161483765,
|
| 1639 |
+
"num_tokens": 11458094.0,
|
| 1640 |
+
"step": 163
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"entropy": 0.6620264649391174,
|
| 1644 |
+
"epoch": 3.2800000000000002,
|
| 1645 |
+
"grad_norm": 0.1949145644903183,
|
| 1646 |
+
"learning_rate": 0.0001,
|
| 1647 |
+
"loss": 0.6431432366371155,
|
| 1648 |
+
"mean_token_accuracy": 0.8045243918895721,
|
| 1649 |
+
"num_tokens": 11526439.0,
|
| 1650 |
+
"step": 164
|
| 1651 |
+
},
|
| 1652 |
+
{
|
| 1653 |
+
"entropy": 0.7114729583263397,
|
| 1654 |
+
"epoch": 3.3,
|
| 1655 |
+
"grad_norm": 0.2044411301612854,
|
| 1656 |
+
"learning_rate": 0.0001,
|
| 1657 |
+
"loss": 0.6916588544845581,
|
| 1658 |
+
"mean_token_accuracy": 0.7911301851272583,
|
| 1659 |
+
"num_tokens": 11593907.0,
|
| 1660 |
+
"step": 165
|
| 1661 |
+
},
|
| 1662 |
+
{
|
| 1663 |
+
"entropy": 0.7394631803035736,
|
| 1664 |
+
"epoch": 3.32,
|
| 1665 |
+
"grad_norm": 0.20598116517066956,
|
| 1666 |
+
"learning_rate": 0.0001,
|
| 1667 |
+
"loss": 0.7143540978431702,
|
| 1668 |
+
"mean_token_accuracy": 0.7861869037151337,
|
| 1669 |
+
"num_tokens": 11659313.0,
|
| 1670 |
+
"step": 166
|
| 1671 |
+
},
|
| 1672 |
+
{
|
| 1673 |
+
"entropy": 0.7148211598396301,
|
| 1674 |
+
"epoch": 3.34,
|
| 1675 |
+
"grad_norm": 0.19798815250396729,
|
| 1676 |
+
"learning_rate": 0.0001,
|
| 1677 |
+
"loss": 0.6806311011314392,
|
| 1678 |
+
"mean_token_accuracy": 0.7966620624065399,
|
| 1679 |
+
"num_tokens": 11729203.0,
|
| 1680 |
+
"step": 167
|
| 1681 |
+
},
|
| 1682 |
+
{
|
| 1683 |
+
"entropy": 0.7278057634830475,
|
| 1684 |
+
"epoch": 3.36,
|
| 1685 |
+
"grad_norm": 0.2106526643037796,
|
| 1686 |
+
"learning_rate": 0.0001,
|
| 1687 |
+
"loss": 0.6907294392585754,
|
| 1688 |
+
"mean_token_accuracy": 0.7917556762695312,
|
| 1689 |
+
"num_tokens": 11798662.0,
|
| 1690 |
+
"step": 168
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"entropy": 0.7575972974300385,
|
| 1694 |
+
"epoch": 3.38,
|
| 1695 |
+
"grad_norm": 0.19657012820243835,
|
| 1696 |
+
"learning_rate": 0.0001,
|
| 1697 |
+
"loss": 0.7215894460678101,
|
| 1698 |
+
"mean_token_accuracy": 0.7850257754325867,
|
| 1699 |
+
"num_tokens": 11874700.0,
|
| 1700 |
+
"step": 169
|
| 1701 |
+
},
|
| 1702 |
+
{
|
| 1703 |
+
"entropy": 0.7198713719844818,
|
| 1704 |
+
"epoch": 3.4,
|
| 1705 |
+
"grad_norm": 0.19392815232276917,
|
| 1706 |
+
"learning_rate": 0.0001,
|
| 1707 |
+
"loss": 0.6976982355117798,
|
| 1708 |
+
"mean_token_accuracy": 0.7894782423973083,
|
| 1709 |
+
"num_tokens": 11946770.0,
|
| 1710 |
+
"step": 170
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"entropy": 0.6691116690635681,
|
| 1714 |
+
"epoch": 3.42,
|
| 1715 |
+
"grad_norm": 0.1919872909784317,
|
| 1716 |
+
"learning_rate": 0.0001,
|
| 1717 |
+
"loss": 0.6429901123046875,
|
| 1718 |
+
"mean_token_accuracy": 0.8067097663879395,
|
| 1719 |
+
"num_tokens": 12016943.0,
|
| 1720 |
+
"step": 171
|
| 1721 |
+
},
|
| 1722 |
+
{
|
| 1723 |
+
"entropy": 0.7087913751602173,
|
| 1724 |
+
"epoch": 3.44,
|
| 1725 |
+
"grad_norm": 0.19245345890522003,
|
| 1726 |
+
"learning_rate": 0.0001,
|
| 1727 |
+
"loss": 0.6743010878562927,
|
| 1728 |
+
"mean_token_accuracy": 0.8007382750511169,
|
| 1729 |
+
"num_tokens": 12088223.0,
|
| 1730 |
+
"step": 172
|
| 1731 |
+
},
|
| 1732 |
+
{
|
| 1733 |
+
"entropy": 0.7334369122982025,
|
| 1734 |
+
"epoch": 3.46,
|
| 1735 |
+
"grad_norm": 0.1944996863603592,
|
| 1736 |
+
"learning_rate": 0.0001,
|
| 1737 |
+
"loss": 0.7241754531860352,
|
| 1738 |
+
"mean_token_accuracy": 0.781945675611496,
|
| 1739 |
+
"num_tokens": 12164031.0,
|
| 1740 |
+
"step": 173
|
| 1741 |
+
},
|
| 1742 |
+
{
|
| 1743 |
+
"entropy": 0.7216465771198273,
|
| 1744 |
+
"epoch": 3.48,
|
| 1745 |
+
"grad_norm": 0.195100337266922,
|
| 1746 |
+
"learning_rate": 0.0001,
|
| 1747 |
+
"loss": 0.6905370950698853,
|
| 1748 |
+
"mean_token_accuracy": 0.7926844656467438,
|
| 1749 |
+
"num_tokens": 12235488.0,
|
| 1750 |
+
"step": 174
|
| 1751 |
+
},
|
| 1752 |
+
{
|
| 1753 |
+
"entropy": 0.7634322941303253,
|
| 1754 |
+
"epoch": 3.5,
|
| 1755 |
+
"grad_norm": 0.20126116275787354,
|
| 1756 |
+
"learning_rate": 0.0001,
|
| 1757 |
+
"loss": 0.7199342250823975,
|
| 1758 |
+
"mean_token_accuracy": 0.784062385559082,
|
| 1759 |
+
"num_tokens": 12304402.0,
|
| 1760 |
+
"step": 175
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"entropy": 0.7162297964096069,
|
| 1764 |
+
"epoch": 3.52,
|
| 1765 |
+
"grad_norm": 0.19708800315856934,
|
| 1766 |
+
"learning_rate": 0.0001,
|
| 1767 |
+
"loss": 0.6828768253326416,
|
| 1768 |
+
"mean_token_accuracy": 0.7963770925998688,
|
| 1769 |
+
"num_tokens": 12376874.0,
|
| 1770 |
+
"step": 176
|
| 1771 |
+
},
|
| 1772 |
+
{
|
| 1773 |
+
"entropy": 0.7292175590991974,
|
| 1774 |
+
"epoch": 3.54,
|
| 1775 |
+
"grad_norm": 0.19853827357292175,
|
| 1776 |
+
"learning_rate": 0.0001,
|
| 1777 |
+
"loss": 0.6944613456726074,
|
| 1778 |
+
"mean_token_accuracy": 0.7901931405067444,
|
| 1779 |
+
"num_tokens": 12443682.0,
|
| 1780 |
+
"step": 177
|
| 1781 |
+
},
|
| 1782 |
+
{
|
| 1783 |
+
"entropy": 0.7690876424312592,
|
| 1784 |
+
"epoch": 3.56,
|
| 1785 |
+
"grad_norm": 0.2102740854024887,
|
| 1786 |
+
"learning_rate": 0.0001,
|
| 1787 |
+
"loss": 0.7348027229309082,
|
| 1788 |
+
"mean_token_accuracy": 0.7807092070579529,
|
| 1789 |
+
"num_tokens": 12511430.0,
|
| 1790 |
+
"step": 178
|
| 1791 |
+
},
|
| 1792 |
+
{
|
| 1793 |
+
"entropy": 0.7362220287322998,
|
| 1794 |
+
"epoch": 3.58,
|
| 1795 |
+
"grad_norm": 0.20193730294704437,
|
| 1796 |
+
"learning_rate": 0.0001,
|
| 1797 |
+
"loss": 0.7197112441062927,
|
| 1798 |
+
"mean_token_accuracy": 0.7791264057159424,
|
| 1799 |
+
"num_tokens": 12582173.0,
|
| 1800 |
+
"step": 179
|
| 1801 |
+
},
|
| 1802 |
+
{
|
| 1803 |
+
"entropy": 0.716655433177948,
|
| 1804 |
+
"epoch": 3.6,
|
| 1805 |
+
"grad_norm": 0.19548293948173523,
|
| 1806 |
+
"learning_rate": 0.0001,
|
| 1807 |
+
"loss": 0.7020804286003113,
|
| 1808 |
+
"mean_token_accuracy": 0.789775550365448,
|
| 1809 |
+
"num_tokens": 12655124.0,
|
| 1810 |
+
"step": 180
|
| 1811 |
+
},
|
| 1812 |
+
{
|
| 1813 |
+
"entropy": 0.7400652468204498,
|
| 1814 |
+
"epoch": 3.62,
|
| 1815 |
+
"grad_norm": 0.20551350712776184,
|
| 1816 |
+
"learning_rate": 0.0001,
|
| 1817 |
+
"loss": 0.7202802300453186,
|
| 1818 |
+
"mean_token_accuracy": 0.7863712012767792,
|
| 1819 |
+
"num_tokens": 12728612.0,
|
| 1820 |
+
"step": 181
|
| 1821 |
+
},
|
| 1822 |
+
{
|
| 1823 |
+
"entropy": 0.7541409730911255,
|
| 1824 |
+
"epoch": 3.64,
|
| 1825 |
+
"grad_norm": 0.200267493724823,
|
| 1826 |
+
"learning_rate": 0.0001,
|
| 1827 |
+
"loss": 0.713320255279541,
|
| 1828 |
+
"mean_token_accuracy": 0.7859389185905457,
|
| 1829 |
+
"num_tokens": 12800056.0,
|
| 1830 |
+
"step": 182
|
| 1831 |
+
},
|
| 1832 |
+
{
|
| 1833 |
+
"entropy": 0.6940381526947021,
|
| 1834 |
+
"epoch": 3.66,
|
| 1835 |
+
"grad_norm": 0.19558116793632507,
|
| 1836 |
+
"learning_rate": 0.0001,
|
| 1837 |
+
"loss": 0.6574203968048096,
|
| 1838 |
+
"mean_token_accuracy": 0.8014397621154785,
|
| 1839 |
+
"num_tokens": 12868372.0,
|
| 1840 |
+
"step": 183
|
| 1841 |
+
},
|
| 1842 |
+
{
|
| 1843 |
+
"entropy": 0.7630845606327057,
|
| 1844 |
+
"epoch": 3.68,
|
| 1845 |
+
"grad_norm": 0.20073311030864716,
|
| 1846 |
+
"learning_rate": 0.0001,
|
| 1847 |
+
"loss": 0.7155758738517761,
|
| 1848 |
+
"mean_token_accuracy": 0.7896965146064758,
|
| 1849 |
+
"num_tokens": 12937518.0,
|
| 1850 |
+
"step": 184
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"entropy": 0.7708411812782288,
|
| 1854 |
+
"epoch": 3.7,
|
| 1855 |
+
"grad_norm": 0.22150248289108276,
|
| 1856 |
+
"learning_rate": 0.0001,
|
| 1857 |
+
"loss": 0.7369881868362427,
|
| 1858 |
+
"mean_token_accuracy": 0.7802594602108002,
|
| 1859 |
+
"num_tokens": 13003915.0,
|
| 1860 |
+
"step": 185
|
| 1861 |
+
},
|
| 1862 |
+
{
|
| 1863 |
+
"entropy": 0.7173754870891571,
|
| 1864 |
+
"epoch": 3.7199999999999998,
|
| 1865 |
+
"grad_norm": 0.19912731647491455,
|
| 1866 |
+
"learning_rate": 0.0001,
|
| 1867 |
+
"loss": 0.6876958608627319,
|
| 1868 |
+
"mean_token_accuracy": 0.7933018803596497,
|
| 1869 |
+
"num_tokens": 13075561.0,
|
| 1870 |
+
"step": 186
|
| 1871 |
+
},
|
| 1872 |
+
{
|
| 1873 |
+
"entropy": 0.7382989227771759,
|
| 1874 |
+
"epoch": 3.74,
|
| 1875 |
+
"grad_norm": 0.20131585001945496,
|
| 1876 |
+
"learning_rate": 0.0001,
|
| 1877 |
+
"loss": 0.7099729180335999,
|
| 1878 |
+
"mean_token_accuracy": 0.7907689809799194,
|
| 1879 |
+
"num_tokens": 13147726.0,
|
| 1880 |
+
"step": 187
|
| 1881 |
+
},
|
| 1882 |
+
{
|
| 1883 |
+
"entropy": 0.7296792566776276,
|
| 1884 |
+
"epoch": 3.76,
|
| 1885 |
+
"grad_norm": 0.19849984347820282,
|
| 1886 |
+
"learning_rate": 0.0001,
|
| 1887 |
+
"loss": 0.7037006616592407,
|
| 1888 |
+
"mean_token_accuracy": 0.7868267595767975,
|
| 1889 |
+
"num_tokens": 13219764.0,
|
| 1890 |
+
"step": 188
|
| 1891 |
+
},
|
| 1892 |
+
{
|
| 1893 |
+
"entropy": 0.7335399687290192,
|
| 1894 |
+
"epoch": 3.7800000000000002,
|
| 1895 |
+
"grad_norm": 0.20115980505943298,
|
| 1896 |
+
"learning_rate": 0.0001,
|
| 1897 |
+
"loss": 0.7100788354873657,
|
| 1898 |
+
"mean_token_accuracy": 0.786194235086441,
|
| 1899 |
+
"num_tokens": 13291698.0,
|
| 1900 |
+
"step": 189
|
| 1901 |
+
},
|
| 1902 |
+
{
|
| 1903 |
+
"entropy": 0.7148082256317139,
|
| 1904 |
+
"epoch": 3.8,
|
| 1905 |
+
"grad_norm": 0.19843769073486328,
|
| 1906 |
+
"learning_rate": 0.0001,
|
| 1907 |
+
"loss": 0.6846855878829956,
|
| 1908 |
+
"mean_token_accuracy": 0.7930681705474854,
|
| 1909 |
+
"num_tokens": 13364738.0,
|
| 1910 |
+
"step": 190
|
| 1911 |
+
},
|
| 1912 |
+
{
|
| 1913 |
+
"entropy": 0.71998131275177,
|
| 1914 |
+
"epoch": 3.82,
|
| 1915 |
+
"grad_norm": 0.20854182541370392,
|
| 1916 |
+
"learning_rate": 0.0001,
|
| 1917 |
+
"loss": 0.6897561550140381,
|
| 1918 |
+
"mean_token_accuracy": 0.7933003902435303,
|
| 1919 |
+
"num_tokens": 13436984.0,
|
| 1920 |
+
"step": 191
|
| 1921 |
+
},
|
| 1922 |
+
{
|
| 1923 |
+
"entropy": 0.7520318031311035,
|
| 1924 |
+
"epoch": 3.84,
|
| 1925 |
+
"grad_norm": 0.21299579739570618,
|
| 1926 |
+
"learning_rate": 0.0001,
|
| 1927 |
+
"loss": 0.7223616242408752,
|
| 1928 |
+
"mean_token_accuracy": 0.7838756442070007,
|
| 1929 |
+
"num_tokens": 13504383.0,
|
| 1930 |
+
"step": 192
|
| 1931 |
+
},
|
| 1932 |
+
{
|
| 1933 |
+
"entropy": 0.7173813283443451,
|
| 1934 |
+
"epoch": 3.86,
|
| 1935 |
+
"grad_norm": 0.20238681137561798,
|
| 1936 |
+
"learning_rate": 0.0001,
|
| 1937 |
+
"loss": 0.6963660717010498,
|
| 1938 |
+
"mean_token_accuracy": 0.7877775430679321,
|
| 1939 |
+
"num_tokens": 13578910.0,
|
| 1940 |
+
"step": 193
|
| 1941 |
+
},
|
| 1942 |
+
{
|
| 1943 |
+
"entropy": 0.7405160069465637,
|
| 1944 |
+
"epoch": 3.88,
|
| 1945 |
+
"grad_norm": 0.21617071330547333,
|
| 1946 |
+
"learning_rate": 0.0001,
|
| 1947 |
+
"loss": 0.7227989435195923,
|
| 1948 |
+
"mean_token_accuracy": 0.782155841588974,
|
| 1949 |
+
"num_tokens": 13646579.0,
|
| 1950 |
+
"step": 194
|
| 1951 |
+
},
|
| 1952 |
+
{
|
| 1953 |
+
"entropy": 0.6996143460273743,
|
| 1954 |
+
"epoch": 3.9,
|
| 1955 |
+
"grad_norm": 0.20972195267677307,
|
| 1956 |
+
"learning_rate": 0.0001,
|
| 1957 |
+
"loss": 0.6725365519523621,
|
| 1958 |
+
"mean_token_accuracy": 0.7987044751644135,
|
| 1959 |
+
"num_tokens": 13712265.0,
|
| 1960 |
+
"step": 195
|
| 1961 |
+
},
|
| 1962 |
+
{
|
| 1963 |
+
"entropy": 0.6924785077571869,
|
| 1964 |
+
"epoch": 3.92,
|
| 1965 |
+
"grad_norm": 0.20143532752990723,
|
| 1966 |
+
"learning_rate": 0.0001,
|
| 1967 |
+
"loss": 0.6744241118431091,
|
| 1968 |
+
"mean_token_accuracy": 0.7988313138484955,
|
| 1969 |
+
"num_tokens": 13778938.0,
|
| 1970 |
+
"step": 196
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"entropy": 0.7586347460746765,
|
| 1974 |
+
"epoch": 3.94,
|
| 1975 |
+
"grad_norm": 0.21675406396389008,
|
| 1976 |
+
"learning_rate": 0.0001,
|
| 1977 |
+
"loss": 0.720883846282959,
|
| 1978 |
+
"mean_token_accuracy": 0.7846451103687286,
|
| 1979 |
+
"num_tokens": 13850680.0,
|
| 1980 |
+
"step": 197
|
| 1981 |
+
},
|
| 1982 |
+
{
|
| 1983 |
+
"entropy": 0.7003247439861298,
|
| 1984 |
+
"epoch": 3.96,
|
| 1985 |
+
"grad_norm": 0.20092730224132538,
|
| 1986 |
+
"learning_rate": 0.0001,
|
| 1987 |
+
"loss": 0.6743336915969849,
|
| 1988 |
+
"mean_token_accuracy": 0.797335296869278,
|
| 1989 |
+
"num_tokens": 13922486.0,
|
| 1990 |
+
"step": 198
|
| 1991 |
+
},
|
| 1992 |
+
{
|
| 1993 |
+
"entropy": 0.7424158155918121,
|
| 1994 |
+
"epoch": 3.98,
|
| 1995 |
+
"grad_norm": 0.2068347930908203,
|
| 1996 |
+
"learning_rate": 0.0001,
|
| 1997 |
+
"loss": 0.7222142815589905,
|
| 1998 |
+
"mean_token_accuracy": 0.7855294048786163,
|
| 1999 |
+
"num_tokens": 13994794.0,
|
| 2000 |
+
"step": 199
|
| 2001 |
+
},
|
| 2002 |
+
{
|
| 2003 |
+
"entropy": 0.7328775823116302,
|
| 2004 |
+
"epoch": 4.0,
|
| 2005 |
+
"grad_norm": 0.21473339200019836,
|
| 2006 |
+
"learning_rate": 0.0001,
|
| 2007 |
+
"loss": 0.6824338436126709,
|
| 2008 |
+
"mean_token_accuracy": 0.7947524189949036,
|
| 2009 |
+
"num_tokens": 14060764.0,
|
| 2010 |
+
"step": 200
|
| 2011 |
+
}
|
| 2012 |
+
],
|
| 2013 |
+
"logging_steps": 1,
|
| 2014 |
+
"max_steps": 200,
|
| 2015 |
+
"num_input_tokens_seen": 0,
|
| 2016 |
+
"num_train_epochs": 4,
|
| 2017 |
+
"save_steps": 50,
|
| 2018 |
+
"stateful_callbacks": {
|
| 2019 |
+
"TrainerControl": {
|
| 2020 |
+
"args": {
|
| 2021 |
+
"should_epoch_stop": false,
|
| 2022 |
+
"should_evaluate": false,
|
| 2023 |
+
"should_log": false,
|
| 2024 |
+
"should_save": true,
|
| 2025 |
+
"should_training_stop": true
|
| 2026 |
+
},
|
| 2027 |
+
"attributes": {}
|
| 2028 |
+
}
|
| 2029 |
+
},
|
| 2030 |
+
"total_flos": 8.561776579712123e+17,
|
| 2031 |
+
"train_batch_size": 8,
|
| 2032 |
+
"trial_name": null,
|
| 2033 |
+
"trial_params": null
|
| 2034 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c2107d1061cc27913e7ba4b7172d06394cd18a40af75a298feec3836ec0e7d9f
|
| 3 |
+
size 5905
|