Upload 14 files
Browse files- README.md +202 -0
- adapter_config.json +34 -0
- adapter_model.safetensors +3 -0
- added_tokens.json +5 -0
- merges.txt +0 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +20 -0
- tokenizer.json +0 -0
- tokenizer_config.json +44 -0
- trainer_state.json +2613 -0
- training_args.bin +3 -0
- vocab.json +0 -0
README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: unsloth/Qwen2-0.5B-Instruct-bnb-4bit
|
| 3 |
+
library_name: peft
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.12.0
|
adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "unsloth/Qwen2-0.5B-Instruct-bnb-4bit",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 16,
|
| 14 |
+
"lora_dropout": 0,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 16,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"up_proj",
|
| 24 |
+
"o_proj",
|
| 25 |
+
"k_proj",
|
| 26 |
+
"down_proj",
|
| 27 |
+
"gate_proj",
|
| 28 |
+
"q_proj",
|
| 29 |
+
"v_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c5854c7ecfafcd10ff420c69c0cb38bd41ceb9ed1f51d9e6751c18480259b2e0
|
| 3 |
+
size 35237104
|
added_tokens.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<|endoftext|>": 151643,
|
| 3 |
+
"<|im_end|>": 151645,
|
| 4 |
+
"<|im_start|>": 151644
|
| 5 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:07d8089dc4f4bcffdc79b3bb908d5ca793f7c9b1c52ca6054bcb395c00fb22bf
|
| 3 |
+
size 18570356
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:50e2371618277946e2da1e64547c013892c09eeb7f60b06b9ceca5a24b9bfef0
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:daadeae2bf702a072b1904c6a20b58d572123ebe414d340783d471449d5a1bbb
|
| 3 |
+
size 1064
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>"
|
| 5 |
+
],
|
| 6 |
+
"eos_token": {
|
| 7 |
+
"content": "<|im_end|>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false
|
| 12 |
+
},
|
| 13 |
+
"pad_token": {
|
| 14 |
+
"content": "<|endoftext|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false
|
| 19 |
+
}
|
| 20 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"151643": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"151644": {
|
| 13 |
+
"content": "<|im_start|>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"151645": {
|
| 21 |
+
"content": "<|im_end|>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
}
|
| 28 |
+
},
|
| 29 |
+
"additional_special_tokens": [
|
| 30 |
+
"<|im_start|>",
|
| 31 |
+
"<|im_end|>"
|
| 32 |
+
],
|
| 33 |
+
"bos_token": null,
|
| 34 |
+
"chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
| 35 |
+
"clean_up_tokenization_spaces": false,
|
| 36 |
+
"eos_token": "<|im_end|>",
|
| 37 |
+
"errors": "replace",
|
| 38 |
+
"model_max_length": 32768,
|
| 39 |
+
"pad_token": "<|endoftext|>",
|
| 40 |
+
"padding_side": "right",
|
| 41 |
+
"split_special_tokens": false,
|
| 42 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 43 |
+
"unk_token": null
|
| 44 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2613 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 15.762511493497964,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 30000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.052541704978326546,
|
| 13 |
+
"grad_norm": 0.744549572467804,
|
| 14 |
+
"learning_rate": 1.6666666666666667e-06,
|
| 15 |
+
"loss": 1.663,
|
| 16 |
+
"step": 100
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.10508340995665309,
|
| 20 |
+
"grad_norm": 0.6462538838386536,
|
| 21 |
+
"learning_rate": 3.3333333333333333e-06,
|
| 22 |
+
"loss": 1.616,
|
| 23 |
+
"step": 200
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.15762511493497963,
|
| 27 |
+
"grad_norm": 0.5421179533004761,
|
| 28 |
+
"learning_rate": 5e-06,
|
| 29 |
+
"loss": 1.4549,
|
| 30 |
+
"step": 300
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.21016681991330619,
|
| 34 |
+
"grad_norm": 0.8848033547401428,
|
| 35 |
+
"learning_rate": 6.666666666666667e-06,
|
| 36 |
+
"loss": 1.3941,
|
| 37 |
+
"step": 400
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.2627085248916327,
|
| 41 |
+
"grad_norm": 0.7000551819801331,
|
| 42 |
+
"learning_rate": 8.333333333333334e-06,
|
| 43 |
+
"loss": 1.2752,
|
| 44 |
+
"step": 500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.2627085248916327,
|
| 48 |
+
"eval_loss": 1.0633598566055298,
|
| 49 |
+
"eval_runtime": 1.3002,
|
| 50 |
+
"eval_samples_per_second": 7.691,
|
| 51 |
+
"eval_steps_per_second": 3.845,
|
| 52 |
+
"step": 500
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.31525022986995926,
|
| 56 |
+
"grad_norm": 0.8002354502677917,
|
| 57 |
+
"learning_rate": 1e-05,
|
| 58 |
+
"loss": 1.2205,
|
| 59 |
+
"step": 600
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.3677919348482858,
|
| 63 |
+
"grad_norm": 0.7082624435424805,
|
| 64 |
+
"learning_rate": 1.1666666666666668e-05,
|
| 65 |
+
"loss": 1.188,
|
| 66 |
+
"step": 700
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.42033363982661237,
|
| 70 |
+
"grad_norm": 0.626582682132721,
|
| 71 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 72 |
+
"loss": 1.1647,
|
| 73 |
+
"step": 800
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.4728753448049389,
|
| 77 |
+
"grad_norm": 1.0509939193725586,
|
| 78 |
+
"learning_rate": 1.5e-05,
|
| 79 |
+
"loss": 1.1427,
|
| 80 |
+
"step": 900
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.5254170497832654,
|
| 84 |
+
"grad_norm": 1.1202670335769653,
|
| 85 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 86 |
+
"loss": 1.144,
|
| 87 |
+
"step": 1000
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.5254170497832654,
|
| 91 |
+
"eval_loss": 0.9546993374824524,
|
| 92 |
+
"eval_runtime": 1.2391,
|
| 93 |
+
"eval_samples_per_second": 8.07,
|
| 94 |
+
"eval_steps_per_second": 4.035,
|
| 95 |
+
"step": 1000
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.577958754761592,
|
| 99 |
+
"grad_norm": 1.1231364011764526,
|
| 100 |
+
"learning_rate": 1.8333333333333333e-05,
|
| 101 |
+
"loss": 1.0935,
|
| 102 |
+
"step": 1100
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.6305004597399185,
|
| 106 |
+
"grad_norm": 1.0733870267868042,
|
| 107 |
+
"learning_rate": 2e-05,
|
| 108 |
+
"loss": 1.1038,
|
| 109 |
+
"step": 1200
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.6830421647182451,
|
| 113 |
+
"grad_norm": 1.0306121110916138,
|
| 114 |
+
"learning_rate": 2.1666666666666667e-05,
|
| 115 |
+
"loss": 1.1055,
|
| 116 |
+
"step": 1300
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.7355838696965716,
|
| 120 |
+
"grad_norm": 1.2776762247085571,
|
| 121 |
+
"learning_rate": 2.3333333333333336e-05,
|
| 122 |
+
"loss": 1.0724,
|
| 123 |
+
"step": 1400
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.7881255746748982,
|
| 127 |
+
"grad_norm": 1.0678656101226807,
|
| 128 |
+
"learning_rate": 2.5e-05,
|
| 129 |
+
"loss": 1.0564,
|
| 130 |
+
"step": 1500
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.7881255746748982,
|
| 134 |
+
"eval_loss": 0.912558913230896,
|
| 135 |
+
"eval_runtime": 1.2576,
|
| 136 |
+
"eval_samples_per_second": 7.952,
|
| 137 |
+
"eval_steps_per_second": 3.976,
|
| 138 |
+
"step": 1500
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.8406672796532247,
|
| 142 |
+
"grad_norm": 1.6063746213912964,
|
| 143 |
+
"learning_rate": 2.6666666666666667e-05,
|
| 144 |
+
"loss": 1.0391,
|
| 145 |
+
"step": 1600
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.8932089846315513,
|
| 149 |
+
"grad_norm": 1.367933750152588,
|
| 150 |
+
"learning_rate": 2.8333333333333335e-05,
|
| 151 |
+
"loss": 1.0435,
|
| 152 |
+
"step": 1700
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.9457506896098778,
|
| 156 |
+
"grad_norm": 1.0610206127166748,
|
| 157 |
+
"learning_rate": 3e-05,
|
| 158 |
+
"loss": 1.0436,
|
| 159 |
+
"step": 1800
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.9982923945882044,
|
| 163 |
+
"grad_norm": 0.8625739216804504,
|
| 164 |
+
"learning_rate": 3.1666666666666666e-05,
|
| 165 |
+
"loss": 1.0334,
|
| 166 |
+
"step": 1900
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 1.0508340995665308,
|
| 170 |
+
"grad_norm": 1.4904906749725342,
|
| 171 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 172 |
+
"loss": 1.0228,
|
| 173 |
+
"step": 2000
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 1.0508340995665308,
|
| 177 |
+
"eval_loss": 0.8912132978439331,
|
| 178 |
+
"eval_runtime": 1.2665,
|
| 179 |
+
"eval_samples_per_second": 7.896,
|
| 180 |
+
"eval_steps_per_second": 3.948,
|
| 181 |
+
"step": 2000
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 1.1033758045448574,
|
| 185 |
+
"grad_norm": 1.4299525022506714,
|
| 186 |
+
"learning_rate": 3.5e-05,
|
| 187 |
+
"loss": 1.0009,
|
| 188 |
+
"step": 2100
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 1.155917509523184,
|
| 192 |
+
"grad_norm": 1.2776519060134888,
|
| 193 |
+
"learning_rate": 3.6666666666666666e-05,
|
| 194 |
+
"loss": 0.9988,
|
| 195 |
+
"step": 2200
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 1.2084592145015105,
|
| 199 |
+
"grad_norm": 1.1559321880340576,
|
| 200 |
+
"learning_rate": 3.8333333333333334e-05,
|
| 201 |
+
"loss": 1.0003,
|
| 202 |
+
"step": 2300
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 1.261000919479837,
|
| 206 |
+
"grad_norm": 0.9451723098754883,
|
| 207 |
+
"learning_rate": 4e-05,
|
| 208 |
+
"loss": 0.9961,
|
| 209 |
+
"step": 2400
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 1.3135426244581636,
|
| 213 |
+
"grad_norm": 1.4040967226028442,
|
| 214 |
+
"learning_rate": 4.166666666666667e-05,
|
| 215 |
+
"loss": 0.9981,
|
| 216 |
+
"step": 2500
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 1.3135426244581636,
|
| 220 |
+
"eval_loss": 0.8769587278366089,
|
| 221 |
+
"eval_runtime": 1.2527,
|
| 222 |
+
"eval_samples_per_second": 7.983,
|
| 223 |
+
"eval_steps_per_second": 3.991,
|
| 224 |
+
"step": 2500
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 1.3660843294364902,
|
| 228 |
+
"grad_norm": 1.469843864440918,
|
| 229 |
+
"learning_rate": 4.3333333333333334e-05,
|
| 230 |
+
"loss": 0.9868,
|
| 231 |
+
"step": 2600
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 1.4186260344148167,
|
| 235 |
+
"grad_norm": 1.1479499340057373,
|
| 236 |
+
"learning_rate": 4.5e-05,
|
| 237 |
+
"loss": 0.9822,
|
| 238 |
+
"step": 2700
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 1.4711677393931433,
|
| 242 |
+
"grad_norm": 2.1333274841308594,
|
| 243 |
+
"learning_rate": 4.666666666666667e-05,
|
| 244 |
+
"loss": 0.9921,
|
| 245 |
+
"step": 2800
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 1.5237094443714698,
|
| 249 |
+
"grad_norm": 1.162014365196228,
|
| 250 |
+
"learning_rate": 4.8333333333333334e-05,
|
| 251 |
+
"loss": 0.9813,
|
| 252 |
+
"step": 2900
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 1.5762511493497964,
|
| 256 |
+
"grad_norm": 0.9883254170417786,
|
| 257 |
+
"learning_rate": 5e-05,
|
| 258 |
+
"loss": 0.9796,
|
| 259 |
+
"step": 3000
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 1.5762511493497964,
|
| 263 |
+
"eval_loss": 0.8728264570236206,
|
| 264 |
+
"eval_runtime": 1.262,
|
| 265 |
+
"eval_samples_per_second": 7.924,
|
| 266 |
+
"eval_steps_per_second": 3.962,
|
| 267 |
+
"step": 3000
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 1.628792854328123,
|
| 271 |
+
"grad_norm": 1.1366589069366455,
|
| 272 |
+
"learning_rate": 4.981481481481482e-05,
|
| 273 |
+
"loss": 0.985,
|
| 274 |
+
"step": 3100
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 1.6813345593064495,
|
| 278 |
+
"grad_norm": 1.0342519283294678,
|
| 279 |
+
"learning_rate": 4.962962962962963e-05,
|
| 280 |
+
"loss": 0.9872,
|
| 281 |
+
"step": 3200
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 1.733876264284776,
|
| 285 |
+
"grad_norm": 0.9889224767684937,
|
| 286 |
+
"learning_rate": 4.9444444444444446e-05,
|
| 287 |
+
"loss": 0.9892,
|
| 288 |
+
"step": 3300
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 1.7864179692631026,
|
| 292 |
+
"grad_norm": 0.9875237345695496,
|
| 293 |
+
"learning_rate": 4.925925925925926e-05,
|
| 294 |
+
"loss": 0.9606,
|
| 295 |
+
"step": 3400
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 1.8389596742414291,
|
| 299 |
+
"grad_norm": 0.9079448580741882,
|
| 300 |
+
"learning_rate": 4.9074074074074075e-05,
|
| 301 |
+
"loss": 0.9846,
|
| 302 |
+
"step": 3500
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 1.8389596742414291,
|
| 306 |
+
"eval_loss": 0.869242787361145,
|
| 307 |
+
"eval_runtime": 1.2422,
|
| 308 |
+
"eval_samples_per_second": 8.05,
|
| 309 |
+
"eval_steps_per_second": 4.025,
|
| 310 |
+
"step": 3500
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 1.8915013792197557,
|
| 314 |
+
"grad_norm": 1.0478876829147339,
|
| 315 |
+
"learning_rate": 4.888888888888889e-05,
|
| 316 |
+
"loss": 0.9616,
|
| 317 |
+
"step": 3600
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 1.9440430841980822,
|
| 321 |
+
"grad_norm": 1.0536926984786987,
|
| 322 |
+
"learning_rate": 4.8703703703703704e-05,
|
| 323 |
+
"loss": 0.9674,
|
| 324 |
+
"step": 3700
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 1.9965847891764088,
|
| 328 |
+
"grad_norm": 1.1787534952163696,
|
| 329 |
+
"learning_rate": 4.851851851851852e-05,
|
| 330 |
+
"loss": 0.9567,
|
| 331 |
+
"step": 3800
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 2.049126494154735,
|
| 335 |
+
"grad_norm": 1.0072757005691528,
|
| 336 |
+
"learning_rate": 4.8333333333333334e-05,
|
| 337 |
+
"loss": 0.9441,
|
| 338 |
+
"step": 3900
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 2.1016681991330617,
|
| 342 |
+
"grad_norm": 1.2437305450439453,
|
| 343 |
+
"learning_rate": 4.814814814814815e-05,
|
| 344 |
+
"loss": 0.9316,
|
| 345 |
+
"step": 4000
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 2.1016681991330617,
|
| 349 |
+
"eval_loss": 0.8525739908218384,
|
| 350 |
+
"eval_runtime": 1.2391,
|
| 351 |
+
"eval_samples_per_second": 8.07,
|
| 352 |
+
"eval_steps_per_second": 4.035,
|
| 353 |
+
"step": 4000
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 2.1542099041113882,
|
| 357 |
+
"grad_norm": 1.722901701927185,
|
| 358 |
+
"learning_rate": 4.796296296296296e-05,
|
| 359 |
+
"loss": 0.934,
|
| 360 |
+
"step": 4100
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 2.206751609089715,
|
| 364 |
+
"grad_norm": 1.032166600227356,
|
| 365 |
+
"learning_rate": 4.7777777777777784e-05,
|
| 366 |
+
"loss": 0.9324,
|
| 367 |
+
"step": 4200
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 2.2592933140680413,
|
| 371 |
+
"grad_norm": 1.0329689979553223,
|
| 372 |
+
"learning_rate": 4.759259259259259e-05,
|
| 373 |
+
"loss": 0.9327,
|
| 374 |
+
"step": 4300
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 2.311835019046368,
|
| 378 |
+
"grad_norm": 0.8714644908905029,
|
| 379 |
+
"learning_rate": 4.740740740740741e-05,
|
| 380 |
+
"loss": 0.9228,
|
| 381 |
+
"step": 4400
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 2.3643767240246945,
|
| 385 |
+
"grad_norm": 1.048893928527832,
|
| 386 |
+
"learning_rate": 4.722222222222222e-05,
|
| 387 |
+
"loss": 0.9356,
|
| 388 |
+
"step": 4500
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 2.3643767240246945,
|
| 392 |
+
"eval_loss": 0.8477146029472351,
|
| 393 |
+
"eval_runtime": 1.2917,
|
| 394 |
+
"eval_samples_per_second": 7.742,
|
| 395 |
+
"eval_steps_per_second": 3.871,
|
| 396 |
+
"step": 4500
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 2.416918429003021,
|
| 400 |
+
"grad_norm": 1.1038933992385864,
|
| 401 |
+
"learning_rate": 4.703703703703704e-05,
|
| 402 |
+
"loss": 0.9317,
|
| 403 |
+
"step": 4600
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 2.4694601339813476,
|
| 407 |
+
"grad_norm": 0.9085045456886292,
|
| 408 |
+
"learning_rate": 4.685185185185185e-05,
|
| 409 |
+
"loss": 0.9411,
|
| 410 |
+
"step": 4700
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 2.522001838959674,
|
| 414 |
+
"grad_norm": 1.1415351629257202,
|
| 415 |
+
"learning_rate": 4.666666666666667e-05,
|
| 416 |
+
"loss": 0.9227,
|
| 417 |
+
"step": 4800
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 2.5745435439380007,
|
| 421 |
+
"grad_norm": 0.9230244755744934,
|
| 422 |
+
"learning_rate": 4.648148148148148e-05,
|
| 423 |
+
"loss": 0.9362,
|
| 424 |
+
"step": 4900
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 2.627085248916327,
|
| 428 |
+
"grad_norm": 0.9721058011054993,
|
| 429 |
+
"learning_rate": 4.62962962962963e-05,
|
| 430 |
+
"loss": 0.9297,
|
| 431 |
+
"step": 5000
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 2.627085248916327,
|
| 435 |
+
"eval_loss": 0.8504465818405151,
|
| 436 |
+
"eval_runtime": 1.2834,
|
| 437 |
+
"eval_samples_per_second": 7.792,
|
| 438 |
+
"eval_steps_per_second": 3.896,
|
| 439 |
+
"step": 5000
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 2.6796269538946538,
|
| 443 |
+
"grad_norm": 0.933588981628418,
|
| 444 |
+
"learning_rate": 4.6111111111111115e-05,
|
| 445 |
+
"loss": 0.9339,
|
| 446 |
+
"step": 5100
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 2.7321686588729803,
|
| 450 |
+
"grad_norm": 0.915013313293457,
|
| 451 |
+
"learning_rate": 4.592592592592593e-05,
|
| 452 |
+
"loss": 0.9322,
|
| 453 |
+
"step": 5200
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 2.784710363851307,
|
| 457 |
+
"grad_norm": 1.2846601009368896,
|
| 458 |
+
"learning_rate": 4.5740740740740745e-05,
|
| 459 |
+
"loss": 0.913,
|
| 460 |
+
"step": 5300
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 2.8372520688296334,
|
| 464 |
+
"grad_norm": 1.1330525875091553,
|
| 465 |
+
"learning_rate": 4.555555555555556e-05,
|
| 466 |
+
"loss": 0.9241,
|
| 467 |
+
"step": 5400
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 2.88979377380796,
|
| 471 |
+
"grad_norm": 1.6967169046401978,
|
| 472 |
+
"learning_rate": 4.5370370370370374e-05,
|
| 473 |
+
"loss": 0.9127,
|
| 474 |
+
"step": 5500
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 2.88979377380796,
|
| 478 |
+
"eval_loss": 0.8335689306259155,
|
| 479 |
+
"eval_runtime": 1.2838,
|
| 480 |
+
"eval_samples_per_second": 7.789,
|
| 481 |
+
"eval_steps_per_second": 3.895,
|
| 482 |
+
"step": 5500
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 2.9423354787862865,
|
| 486 |
+
"grad_norm": 0.9576010704040527,
|
| 487 |
+
"learning_rate": 4.518518518518519e-05,
|
| 488 |
+
"loss": 0.9097,
|
| 489 |
+
"step": 5600
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 2.994877183764613,
|
| 493 |
+
"grad_norm": 1.229671835899353,
|
| 494 |
+
"learning_rate": 4.5e-05,
|
| 495 |
+
"loss": 0.9165,
|
| 496 |
+
"step": 5700
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 3.0474188887429396,
|
| 500 |
+
"grad_norm": 0.9229328632354736,
|
| 501 |
+
"learning_rate": 4.481481481481482e-05,
|
| 502 |
+
"loss": 0.9066,
|
| 503 |
+
"step": 5800
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 3.099960593721266,
|
| 507 |
+
"grad_norm": 1.1152088642120361,
|
| 508 |
+
"learning_rate": 4.462962962962963e-05,
|
| 509 |
+
"loss": 0.8888,
|
| 510 |
+
"step": 5900
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 3.1525022986995928,
|
| 514 |
+
"grad_norm": 1.0948377847671509,
|
| 515 |
+
"learning_rate": 4.4444444444444447e-05,
|
| 516 |
+
"loss": 0.9233,
|
| 517 |
+
"step": 6000
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"epoch": 3.1525022986995928,
|
| 521 |
+
"eval_loss": 0.8405929803848267,
|
| 522 |
+
"eval_runtime": 1.2669,
|
| 523 |
+
"eval_samples_per_second": 7.893,
|
| 524 |
+
"eval_steps_per_second": 3.947,
|
| 525 |
+
"step": 6000
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 3.2050440036779193,
|
| 529 |
+
"grad_norm": 1.320657730102539,
|
| 530 |
+
"learning_rate": 4.425925925925926e-05,
|
| 531 |
+
"loss": 0.9024,
|
| 532 |
+
"step": 6100
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 3.257585708656246,
|
| 536 |
+
"grad_norm": 1.3515260219573975,
|
| 537 |
+
"learning_rate": 4.4074074074074076e-05,
|
| 538 |
+
"loss": 0.8992,
|
| 539 |
+
"step": 6200
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 3.3101274136345724,
|
| 543 |
+
"grad_norm": 0.9061586260795593,
|
| 544 |
+
"learning_rate": 4.388888888888889e-05,
|
| 545 |
+
"loss": 0.8966,
|
| 546 |
+
"step": 6300
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 3.362669118612899,
|
| 550 |
+
"grad_norm": 0.7893356084823608,
|
| 551 |
+
"learning_rate": 4.3703703703703705e-05,
|
| 552 |
+
"loss": 0.8772,
|
| 553 |
+
"step": 6400
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 3.4152108235912255,
|
| 557 |
+
"grad_norm": 1.1485052108764648,
|
| 558 |
+
"learning_rate": 4.351851851851852e-05,
|
| 559 |
+
"loss": 0.8935,
|
| 560 |
+
"step": 6500
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 3.4152108235912255,
|
| 564 |
+
"eval_loss": 0.8316594362258911,
|
| 565 |
+
"eval_runtime": 1.2559,
|
| 566 |
+
"eval_samples_per_second": 7.962,
|
| 567 |
+
"eval_steps_per_second": 3.981,
|
| 568 |
+
"step": 6500
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 3.467752528569552,
|
| 572 |
+
"grad_norm": 1.2252397537231445,
|
| 573 |
+
"learning_rate": 4.3333333333333334e-05,
|
| 574 |
+
"loss": 0.8877,
|
| 575 |
+
"step": 6600
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 3.5202942335478786,
|
| 579 |
+
"grad_norm": 0.937276303768158,
|
| 580 |
+
"learning_rate": 4.314814814814815e-05,
|
| 581 |
+
"loss": 0.899,
|
| 582 |
+
"step": 6700
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 3.572835938526205,
|
| 586 |
+
"grad_norm": 1.1383343935012817,
|
| 587 |
+
"learning_rate": 4.296296296296296e-05,
|
| 588 |
+
"loss": 0.884,
|
| 589 |
+
"step": 6800
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 3.6253776435045317,
|
| 593 |
+
"grad_norm": 0.9624786376953125,
|
| 594 |
+
"learning_rate": 4.277777777777778e-05,
|
| 595 |
+
"loss": 0.8933,
|
| 596 |
+
"step": 6900
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 3.6779193484828583,
|
| 600 |
+
"grad_norm": 1.2297359704971313,
|
| 601 |
+
"learning_rate": 4.259259259259259e-05,
|
| 602 |
+
"loss": 0.8902,
|
| 603 |
+
"step": 7000
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 3.6779193484828583,
|
| 607 |
+
"eval_loss": 0.8357389569282532,
|
| 608 |
+
"eval_runtime": 1.2564,
|
| 609 |
+
"eval_samples_per_second": 7.959,
|
| 610 |
+
"eval_steps_per_second": 3.979,
|
| 611 |
+
"step": 7000
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 3.730461053461185,
|
| 615 |
+
"grad_norm": 1.3117122650146484,
|
| 616 |
+
"learning_rate": 4.240740740740741e-05,
|
| 617 |
+
"loss": 0.8833,
|
| 618 |
+
"step": 7100
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 3.7830027584395114,
|
| 622 |
+
"grad_norm": 1.0405583381652832,
|
| 623 |
+
"learning_rate": 4.222222222222222e-05,
|
| 624 |
+
"loss": 0.8974,
|
| 625 |
+
"step": 7200
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 3.835544463417838,
|
| 629 |
+
"grad_norm": 1.1837128400802612,
|
| 630 |
+
"learning_rate": 4.203703703703704e-05,
|
| 631 |
+
"loss": 0.9108,
|
| 632 |
+
"step": 7300
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 3.8880861683961645,
|
| 636 |
+
"grad_norm": 1.070272445678711,
|
| 637 |
+
"learning_rate": 4.185185185185185e-05,
|
| 638 |
+
"loss": 0.888,
|
| 639 |
+
"step": 7400
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 3.940627873374491,
|
| 643 |
+
"grad_norm": 1.2699558734893799,
|
| 644 |
+
"learning_rate": 4.166666666666667e-05,
|
| 645 |
+
"loss": 0.8996,
|
| 646 |
+
"step": 7500
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 3.940627873374491,
|
| 650 |
+
"eval_loss": 0.8259842991828918,
|
| 651 |
+
"eval_runtime": 1.2588,
|
| 652 |
+
"eval_samples_per_second": 7.944,
|
| 653 |
+
"eval_steps_per_second": 3.972,
|
| 654 |
+
"step": 7500
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 3.9931695783528176,
|
| 658 |
+
"grad_norm": 1.1410374641418457,
|
| 659 |
+
"learning_rate": 4.148148148148148e-05,
|
| 660 |
+
"loss": 0.8931,
|
| 661 |
+
"step": 7600
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 4.045711283331144,
|
| 665 |
+
"grad_norm": 0.8494368195533752,
|
| 666 |
+
"learning_rate": 4.12962962962963e-05,
|
| 667 |
+
"loss": 0.8735,
|
| 668 |
+
"step": 7700
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 4.09825298830947,
|
| 672 |
+
"grad_norm": 1.6662884950637817,
|
| 673 |
+
"learning_rate": 4.111111111111111e-05,
|
| 674 |
+
"loss": 0.8706,
|
| 675 |
+
"step": 7800
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 4.150794693287797,
|
| 679 |
+
"grad_norm": 1.103721022605896,
|
| 680 |
+
"learning_rate": 4.092592592592593e-05,
|
| 681 |
+
"loss": 0.8868,
|
| 682 |
+
"step": 7900
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 4.203336398266123,
|
| 686 |
+
"grad_norm": 1.0457319021224976,
|
| 687 |
+
"learning_rate": 4.074074074074074e-05,
|
| 688 |
+
"loss": 0.8616,
|
| 689 |
+
"step": 8000
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 4.203336398266123,
|
| 693 |
+
"eval_loss": 0.8296699523925781,
|
| 694 |
+
"eval_runtime": 1.2594,
|
| 695 |
+
"eval_samples_per_second": 7.941,
|
| 696 |
+
"eval_steps_per_second": 3.97,
|
| 697 |
+
"step": 8000
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 4.25587810324445,
|
| 701 |
+
"grad_norm": 1.038172721862793,
|
| 702 |
+
"learning_rate": 4.055555555555556e-05,
|
| 703 |
+
"loss": 0.8814,
|
| 704 |
+
"step": 8100
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 4.3084198082227765,
|
| 708 |
+
"grad_norm": 1.0770879983901978,
|
| 709 |
+
"learning_rate": 4.0370370370370374e-05,
|
| 710 |
+
"loss": 0.8781,
|
| 711 |
+
"step": 8200
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 4.3609615132011035,
|
| 715 |
+
"grad_norm": 0.9559742212295532,
|
| 716 |
+
"learning_rate": 4.018518518518519e-05,
|
| 717 |
+
"loss": 0.8631,
|
| 718 |
+
"step": 8300
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 4.41350321817943,
|
| 722 |
+
"grad_norm": 1.2352747917175293,
|
| 723 |
+
"learning_rate": 4e-05,
|
| 724 |
+
"loss": 0.8619,
|
| 725 |
+
"step": 8400
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 4.466044923157757,
|
| 729 |
+
"grad_norm": 1.0156300067901611,
|
| 730 |
+
"learning_rate": 3.981481481481482e-05,
|
| 731 |
+
"loss": 0.8589,
|
| 732 |
+
"step": 8500
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 4.466044923157757,
|
| 736 |
+
"eval_loss": 0.8272676467895508,
|
| 737 |
+
"eval_runtime": 1.239,
|
| 738 |
+
"eval_samples_per_second": 8.071,
|
| 739 |
+
"eval_steps_per_second": 4.035,
|
| 740 |
+
"step": 8500
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 4.518586628136083,
|
| 744 |
+
"grad_norm": 1.3172954320907593,
|
| 745 |
+
"learning_rate": 3.962962962962963e-05,
|
| 746 |
+
"loss": 0.8782,
|
| 747 |
+
"step": 8600
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 4.57112833311441,
|
| 751 |
+
"grad_norm": 1.0361146926879883,
|
| 752 |
+
"learning_rate": 3.944444444444445e-05,
|
| 753 |
+
"loss": 0.8929,
|
| 754 |
+
"step": 8700
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 4.623670038092736,
|
| 758 |
+
"grad_norm": 1.0141929388046265,
|
| 759 |
+
"learning_rate": 3.925925925925926e-05,
|
| 760 |
+
"loss": 0.8701,
|
| 761 |
+
"step": 8800
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 4.676211743071063,
|
| 765 |
+
"grad_norm": 1.4929876327514648,
|
| 766 |
+
"learning_rate": 3.9074074074074076e-05,
|
| 767 |
+
"loss": 0.8877,
|
| 768 |
+
"step": 8900
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 4.728753448049389,
|
| 772 |
+
"grad_norm": 1.6893892288208008,
|
| 773 |
+
"learning_rate": 3.888888888888889e-05,
|
| 774 |
+
"loss": 0.8751,
|
| 775 |
+
"step": 9000
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 4.728753448049389,
|
| 779 |
+
"eval_loss": 0.822452187538147,
|
| 780 |
+
"eval_runtime": 1.246,
|
| 781 |
+
"eval_samples_per_second": 8.026,
|
| 782 |
+
"eval_steps_per_second": 4.013,
|
| 783 |
+
"step": 9000
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 4.781295153027716,
|
| 787 |
+
"grad_norm": 0.993008017539978,
|
| 788 |
+
"learning_rate": 3.8703703703703705e-05,
|
| 789 |
+
"loss": 0.8689,
|
| 790 |
+
"step": 9100
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 4.833836858006042,
|
| 794 |
+
"grad_norm": 0.8024290800094604,
|
| 795 |
+
"learning_rate": 3.851851851851852e-05,
|
| 796 |
+
"loss": 0.8945,
|
| 797 |
+
"step": 9200
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 4.886378562984369,
|
| 801 |
+
"grad_norm": 0.8442456722259521,
|
| 802 |
+
"learning_rate": 3.8333333333333334e-05,
|
| 803 |
+
"loss": 0.8897,
|
| 804 |
+
"step": 9300
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 4.938920267962695,
|
| 808 |
+
"grad_norm": 1.6505470275878906,
|
| 809 |
+
"learning_rate": 3.814814814814815e-05,
|
| 810 |
+
"loss": 0.8481,
|
| 811 |
+
"step": 9400
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 4.991461972941022,
|
| 815 |
+
"grad_norm": 0.9656145572662354,
|
| 816 |
+
"learning_rate": 3.7962962962962964e-05,
|
| 817 |
+
"loss": 0.8699,
|
| 818 |
+
"step": 9500
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 4.991461972941022,
|
| 822 |
+
"eval_loss": 0.8228476643562317,
|
| 823 |
+
"eval_runtime": 1.2383,
|
| 824 |
+
"eval_samples_per_second": 8.075,
|
| 825 |
+
"eval_steps_per_second": 4.038,
|
| 826 |
+
"step": 9500
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 5.044003677919348,
|
| 830 |
+
"grad_norm": 1.1603432893753052,
|
| 831 |
+
"learning_rate": 3.777777777777778e-05,
|
| 832 |
+
"loss": 0.8731,
|
| 833 |
+
"step": 9600
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 5.096545382897675,
|
| 837 |
+
"grad_norm": 0.8760092854499817,
|
| 838 |
+
"learning_rate": 3.759259259259259e-05,
|
| 839 |
+
"loss": 0.8268,
|
| 840 |
+
"step": 9700
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 5.149087087876001,
|
| 844 |
+
"grad_norm": 1.50885009765625,
|
| 845 |
+
"learning_rate": 3.740740740740741e-05,
|
| 846 |
+
"loss": 0.8341,
|
| 847 |
+
"step": 9800
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 5.201628792854328,
|
| 851 |
+
"grad_norm": 1.164678692817688,
|
| 852 |
+
"learning_rate": 3.722222222222222e-05,
|
| 853 |
+
"loss": 0.8511,
|
| 854 |
+
"step": 9900
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 5.254170497832654,
|
| 858 |
+
"grad_norm": 1.2179008722305298,
|
| 859 |
+
"learning_rate": 3.7037037037037037e-05,
|
| 860 |
+
"loss": 0.863,
|
| 861 |
+
"step": 10000
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 5.254170497832654,
|
| 865 |
+
"eval_loss": 0.8227807283401489,
|
| 866 |
+
"eval_runtime": 1.2397,
|
| 867 |
+
"eval_samples_per_second": 8.067,
|
| 868 |
+
"eval_steps_per_second": 4.033,
|
| 869 |
+
"step": 10000
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 5.306712202810981,
|
| 873 |
+
"grad_norm": 1.1593024730682373,
|
| 874 |
+
"learning_rate": 3.685185185185185e-05,
|
| 875 |
+
"loss": 0.8481,
|
| 876 |
+
"step": 10100
|
| 877 |
+
},
|
| 878 |
+
{
|
| 879 |
+
"epoch": 5.3592539077893075,
|
| 880 |
+
"grad_norm": 1.1822712421417236,
|
| 881 |
+
"learning_rate": 3.6666666666666666e-05,
|
| 882 |
+
"loss": 0.8435,
|
| 883 |
+
"step": 10200
|
| 884 |
+
},
|
| 885 |
+
{
|
| 886 |
+
"epoch": 5.4117956127676345,
|
| 887 |
+
"grad_norm": 1.1157796382904053,
|
| 888 |
+
"learning_rate": 3.648148148148148e-05,
|
| 889 |
+
"loss": 0.8265,
|
| 890 |
+
"step": 10300
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 5.464337317745961,
|
| 894 |
+
"grad_norm": 1.2513401508331299,
|
| 895 |
+
"learning_rate": 3.62962962962963e-05,
|
| 896 |
+
"loss": 0.8916,
|
| 897 |
+
"step": 10400
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 5.516879022724288,
|
| 901 |
+
"grad_norm": 1.07020902633667,
|
| 902 |
+
"learning_rate": 3.611111111111111e-05,
|
| 903 |
+
"loss": 0.855,
|
| 904 |
+
"step": 10500
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"epoch": 5.516879022724288,
|
| 908 |
+
"eval_loss": 0.8260787725448608,
|
| 909 |
+
"eval_runtime": 1.2426,
|
| 910 |
+
"eval_samples_per_second": 8.048,
|
| 911 |
+
"eval_steps_per_second": 4.024,
|
| 912 |
+
"step": 10500
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 5.569420727702614,
|
| 916 |
+
"grad_norm": 1.281821370124817,
|
| 917 |
+
"learning_rate": 3.592592592592593e-05,
|
| 918 |
+
"loss": 0.8375,
|
| 919 |
+
"step": 10600
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 5.621962432680941,
|
| 923 |
+
"grad_norm": 1.279232144355774,
|
| 924 |
+
"learning_rate": 3.574074074074074e-05,
|
| 925 |
+
"loss": 0.8374,
|
| 926 |
+
"step": 10700
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 5.674504137659267,
|
| 930 |
+
"grad_norm": 1.6183032989501953,
|
| 931 |
+
"learning_rate": 3.555555555555556e-05,
|
| 932 |
+
"loss": 0.8396,
|
| 933 |
+
"step": 10800
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 5.727045842637594,
|
| 937 |
+
"grad_norm": 1.5569584369659424,
|
| 938 |
+
"learning_rate": 3.537037037037037e-05,
|
| 939 |
+
"loss": 0.8474,
|
| 940 |
+
"step": 10900
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 5.77958754761592,
|
| 944 |
+
"grad_norm": 0.9284697771072388,
|
| 945 |
+
"learning_rate": 3.518518518518519e-05,
|
| 946 |
+
"loss": 0.8447,
|
| 947 |
+
"step": 11000
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 5.77958754761592,
|
| 951 |
+
"eval_loss": 0.82489413022995,
|
| 952 |
+
"eval_runtime": 1.2928,
|
| 953 |
+
"eval_samples_per_second": 7.735,
|
| 954 |
+
"eval_steps_per_second": 3.868,
|
| 955 |
+
"step": 11000
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 5.832129252594247,
|
| 959 |
+
"grad_norm": 1.129302740097046,
|
| 960 |
+
"learning_rate": 3.5e-05,
|
| 961 |
+
"loss": 0.8425,
|
| 962 |
+
"step": 11100
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 5.884670957572573,
|
| 966 |
+
"grad_norm": 1.1644898653030396,
|
| 967 |
+
"learning_rate": 3.481481481481482e-05,
|
| 968 |
+
"loss": 0.8545,
|
| 969 |
+
"step": 11200
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 5.9372126625509,
|
| 973 |
+
"grad_norm": 1.5778745412826538,
|
| 974 |
+
"learning_rate": 3.4629629629629626e-05,
|
| 975 |
+
"loss": 0.8488,
|
| 976 |
+
"step": 11300
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 5.989754367529226,
|
| 980 |
+
"grad_norm": 1.0982458591461182,
|
| 981 |
+
"learning_rate": 3.444444444444445e-05,
|
| 982 |
+
"loss": 0.8368,
|
| 983 |
+
"step": 11400
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 6.042296072507553,
|
| 987 |
+
"grad_norm": 1.3936185836791992,
|
| 988 |
+
"learning_rate": 3.425925925925926e-05,
|
| 989 |
+
"loss": 0.8165,
|
| 990 |
+
"step": 11500
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 6.042296072507553,
|
| 994 |
+
"eval_loss": 0.8229165077209473,
|
| 995 |
+
"eval_runtime": 1.2812,
|
| 996 |
+
"eval_samples_per_second": 7.805,
|
| 997 |
+
"eval_steps_per_second": 3.903,
|
| 998 |
+
"step": 11500
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 6.094837777485879,
|
| 1002 |
+
"grad_norm": 0.8609622716903687,
|
| 1003 |
+
"learning_rate": 3.4074074074074077e-05,
|
| 1004 |
+
"loss": 0.813,
|
| 1005 |
+
"step": 11600
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 6.147379482464206,
|
| 1009 |
+
"grad_norm": 1.75618314743042,
|
| 1010 |
+
"learning_rate": 3.388888888888889e-05,
|
| 1011 |
+
"loss": 0.8285,
|
| 1012 |
+
"step": 11700
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"epoch": 6.199921187442532,
|
| 1016 |
+
"grad_norm": 1.5755348205566406,
|
| 1017 |
+
"learning_rate": 3.3703703703703706e-05,
|
| 1018 |
+
"loss": 0.8061,
|
| 1019 |
+
"step": 11800
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 6.252462892420859,
|
| 1023 |
+
"grad_norm": 1.1621313095092773,
|
| 1024 |
+
"learning_rate": 3.351851851851852e-05,
|
| 1025 |
+
"loss": 0.8349,
|
| 1026 |
+
"step": 11900
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 6.3050045973991855,
|
| 1030 |
+
"grad_norm": 1.3047136068344116,
|
| 1031 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 1032 |
+
"loss": 0.8247,
|
| 1033 |
+
"step": 12000
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 6.3050045973991855,
|
| 1037 |
+
"eval_loss": 0.8217476010322571,
|
| 1038 |
+
"eval_runtime": 1.249,
|
| 1039 |
+
"eval_samples_per_second": 8.007,
|
| 1040 |
+
"eval_steps_per_second": 4.003,
|
| 1041 |
+
"step": 12000
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 6.3575463023775125,
|
| 1045 |
+
"grad_norm": 1.161156415939331,
|
| 1046 |
+
"learning_rate": 3.314814814814815e-05,
|
| 1047 |
+
"loss": 0.8248,
|
| 1048 |
+
"step": 12100
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 6.410088007355839,
|
| 1052 |
+
"grad_norm": 1.095155954360962,
|
| 1053 |
+
"learning_rate": 3.2962962962962964e-05,
|
| 1054 |
+
"loss": 0.8275,
|
| 1055 |
+
"step": 12200
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 6.462629712334166,
|
| 1059 |
+
"grad_norm": 1.3355261087417603,
|
| 1060 |
+
"learning_rate": 3.277777777777778e-05,
|
| 1061 |
+
"loss": 0.833,
|
| 1062 |
+
"step": 12300
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 6.515171417312492,
|
| 1066 |
+
"grad_norm": 1.5305536985397339,
|
| 1067 |
+
"learning_rate": 3.25925925925926e-05,
|
| 1068 |
+
"loss": 0.8259,
|
| 1069 |
+
"step": 12400
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 6.567713122290819,
|
| 1073 |
+
"grad_norm": 2.5994789600372314,
|
| 1074 |
+
"learning_rate": 3.240740740740741e-05,
|
| 1075 |
+
"loss": 0.8459,
|
| 1076 |
+
"step": 12500
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 6.567713122290819,
|
| 1080 |
+
"eval_loss": 0.8286579251289368,
|
| 1081 |
+
"eval_runtime": 1.2728,
|
| 1082 |
+
"eval_samples_per_second": 7.856,
|
| 1083 |
+
"eval_steps_per_second": 3.928,
|
| 1084 |
+
"step": 12500
|
| 1085 |
+
},
|
| 1086 |
+
{
|
| 1087 |
+
"epoch": 6.620254827269145,
|
| 1088 |
+
"grad_norm": 1.442550539970398,
|
| 1089 |
+
"learning_rate": 3.222222222222223e-05,
|
| 1090 |
+
"loss": 0.8294,
|
| 1091 |
+
"step": 12600
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 6.672796532247471,
|
| 1095 |
+
"grad_norm": 1.1451183557510376,
|
| 1096 |
+
"learning_rate": 3.203703703703704e-05,
|
| 1097 |
+
"loss": 0.8284,
|
| 1098 |
+
"step": 12700
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 6.725338237225798,
|
| 1102 |
+
"grad_norm": 1.0634784698486328,
|
| 1103 |
+
"learning_rate": 3.185185185185185e-05,
|
| 1104 |
+
"loss": 0.823,
|
| 1105 |
+
"step": 12800
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 6.777879942204125,
|
| 1109 |
+
"grad_norm": 1.2910544872283936,
|
| 1110 |
+
"learning_rate": 3.1666666666666666e-05,
|
| 1111 |
+
"loss": 0.8248,
|
| 1112 |
+
"step": 12900
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 6.830421647182451,
|
| 1116 |
+
"grad_norm": 1.1855148077011108,
|
| 1117 |
+
"learning_rate": 3.148148148148148e-05,
|
| 1118 |
+
"loss": 0.854,
|
| 1119 |
+
"step": 13000
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 6.830421647182451,
|
| 1123 |
+
"eval_loss": 0.8177132606506348,
|
| 1124 |
+
"eval_runtime": 1.2889,
|
| 1125 |
+
"eval_samples_per_second": 7.759,
|
| 1126 |
+
"eval_steps_per_second": 3.879,
|
| 1127 |
+
"step": 13000
|
| 1128 |
+
},
|
| 1129 |
+
{
|
| 1130 |
+
"epoch": 6.882963352160777,
|
| 1131 |
+
"grad_norm": 1.2636213302612305,
|
| 1132 |
+
"learning_rate": 3.1296296296296295e-05,
|
| 1133 |
+
"loss": 0.8429,
|
| 1134 |
+
"step": 13100
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 6.935505057139104,
|
| 1138 |
+
"grad_norm": 1.2894644737243652,
|
| 1139 |
+
"learning_rate": 3.111111111111111e-05,
|
| 1140 |
+
"loss": 0.8279,
|
| 1141 |
+
"step": 13200
|
| 1142 |
+
},
|
| 1143 |
+
{
|
| 1144 |
+
"epoch": 6.988046762117431,
|
| 1145 |
+
"grad_norm": 1.64339280128479,
|
| 1146 |
+
"learning_rate": 3.0925925925925924e-05,
|
| 1147 |
+
"loss": 0.8217,
|
| 1148 |
+
"step": 13300
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 7.040588467095757,
|
| 1152 |
+
"grad_norm": 0.9605098962783813,
|
| 1153 |
+
"learning_rate": 3.074074074074074e-05,
|
| 1154 |
+
"loss": 0.8375,
|
| 1155 |
+
"step": 13400
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 7.093130172074083,
|
| 1159 |
+
"grad_norm": 1.4828298091888428,
|
| 1160 |
+
"learning_rate": 3.055555555555556e-05,
|
| 1161 |
+
"loss": 0.8079,
|
| 1162 |
+
"step": 13500
|
| 1163 |
+
},
|
| 1164 |
+
{
|
| 1165 |
+
"epoch": 7.093130172074083,
|
| 1166 |
+
"eval_loss": 0.8257712125778198,
|
| 1167 |
+
"eval_runtime": 1.2505,
|
| 1168 |
+
"eval_samples_per_second": 7.997,
|
| 1169 |
+
"eval_steps_per_second": 3.998,
|
| 1170 |
+
"step": 13500
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 7.14567187705241,
|
| 1174 |
+
"grad_norm": 1.3807919025421143,
|
| 1175 |
+
"learning_rate": 3.037037037037037e-05,
|
| 1176 |
+
"loss": 0.8096,
|
| 1177 |
+
"step": 13600
|
| 1178 |
+
},
|
| 1179 |
+
{
|
| 1180 |
+
"epoch": 7.1982135820307365,
|
| 1181 |
+
"grad_norm": 1.5678062438964844,
|
| 1182 |
+
"learning_rate": 3.018518518518519e-05,
|
| 1183 |
+
"loss": 0.7869,
|
| 1184 |
+
"step": 13700
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 7.2507552870090635,
|
| 1188 |
+
"grad_norm": 1.0710649490356445,
|
| 1189 |
+
"learning_rate": 3e-05,
|
| 1190 |
+
"loss": 0.813,
|
| 1191 |
+
"step": 13800
|
| 1192 |
+
},
|
| 1193 |
+
{
|
| 1194 |
+
"epoch": 7.30329699198739,
|
| 1195 |
+
"grad_norm": 1.150152564048767,
|
| 1196 |
+
"learning_rate": 2.981481481481482e-05,
|
| 1197 |
+
"loss": 0.7974,
|
| 1198 |
+
"step": 13900
|
| 1199 |
+
},
|
| 1200 |
+
{
|
| 1201 |
+
"epoch": 7.355838696965717,
|
| 1202 |
+
"grad_norm": 1.4336960315704346,
|
| 1203 |
+
"learning_rate": 2.962962962962963e-05,
|
| 1204 |
+
"loss": 0.8126,
|
| 1205 |
+
"step": 14000
|
| 1206 |
+
},
|
| 1207 |
+
{
|
| 1208 |
+
"epoch": 7.355838696965717,
|
| 1209 |
+
"eval_loss": 0.8250346183776855,
|
| 1210 |
+
"eval_runtime": 1.2966,
|
| 1211 |
+
"eval_samples_per_second": 7.712,
|
| 1212 |
+
"eval_steps_per_second": 3.856,
|
| 1213 |
+
"step": 14000
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 7.408380401944043,
|
| 1217 |
+
"grad_norm": 1.454750895500183,
|
| 1218 |
+
"learning_rate": 2.9444444444444448e-05,
|
| 1219 |
+
"loss": 0.8534,
|
| 1220 |
+
"step": 14100
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 7.46092210692237,
|
| 1224 |
+
"grad_norm": 1.3246815204620361,
|
| 1225 |
+
"learning_rate": 2.925925925925926e-05,
|
| 1226 |
+
"loss": 0.8313,
|
| 1227 |
+
"step": 14200
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 7.513463811900696,
|
| 1231 |
+
"grad_norm": 1.116432547569275,
|
| 1232 |
+
"learning_rate": 2.9074074074074077e-05,
|
| 1233 |
+
"loss": 0.8085,
|
| 1234 |
+
"step": 14300
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 7.566005516879023,
|
| 1238 |
+
"grad_norm": 1.0311377048492432,
|
| 1239 |
+
"learning_rate": 2.8888888888888888e-05,
|
| 1240 |
+
"loss": 0.7984,
|
| 1241 |
+
"step": 14400
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 7.618547221857349,
|
| 1245 |
+
"grad_norm": 1.5071169137954712,
|
| 1246 |
+
"learning_rate": 2.8703703703703706e-05,
|
| 1247 |
+
"loss": 0.817,
|
| 1248 |
+
"step": 14500
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 7.618547221857349,
|
| 1252 |
+
"eval_loss": 0.8244579434394836,
|
| 1253 |
+
"eval_runtime": 1.2449,
|
| 1254 |
+
"eval_samples_per_second": 8.032,
|
| 1255 |
+
"eval_steps_per_second": 4.016,
|
| 1256 |
+
"step": 14500
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 7.671088926835676,
|
| 1260 |
+
"grad_norm": 1.2359856367111206,
|
| 1261 |
+
"learning_rate": 2.851851851851852e-05,
|
| 1262 |
+
"loss": 0.807,
|
| 1263 |
+
"step": 14600
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 7.723630631814002,
|
| 1267 |
+
"grad_norm": 1.2495603561401367,
|
| 1268 |
+
"learning_rate": 2.8333333333333335e-05,
|
| 1269 |
+
"loss": 0.8035,
|
| 1270 |
+
"step": 14700
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 7.776172336792329,
|
| 1274 |
+
"grad_norm": 1.0622730255126953,
|
| 1275 |
+
"learning_rate": 2.814814814814815e-05,
|
| 1276 |
+
"loss": 0.8199,
|
| 1277 |
+
"step": 14800
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 7.828714041770655,
|
| 1281 |
+
"grad_norm": 1.097486138343811,
|
| 1282 |
+
"learning_rate": 2.7962962962962965e-05,
|
| 1283 |
+
"loss": 0.8107,
|
| 1284 |
+
"step": 14900
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 7.881255746748982,
|
| 1288 |
+
"grad_norm": 1.1956055164337158,
|
| 1289 |
+
"learning_rate": 2.777777777777778e-05,
|
| 1290 |
+
"loss": 0.7962,
|
| 1291 |
+
"step": 15000
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 7.881255746748982,
|
| 1295 |
+
"eval_loss": 0.8224829435348511,
|
| 1296 |
+
"eval_runtime": 1.2586,
|
| 1297 |
+
"eval_samples_per_second": 7.946,
|
| 1298 |
+
"eval_steps_per_second": 3.973,
|
| 1299 |
+
"step": 15000
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 7.933797451727308,
|
| 1303 |
+
"grad_norm": 1.154567837715149,
|
| 1304 |
+
"learning_rate": 2.7592592592592594e-05,
|
| 1305 |
+
"loss": 0.8278,
|
| 1306 |
+
"step": 15100
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 7.986339156705635,
|
| 1310 |
+
"grad_norm": 1.4666606187820435,
|
| 1311 |
+
"learning_rate": 2.7407407407407408e-05,
|
| 1312 |
+
"loss": 0.8157,
|
| 1313 |
+
"step": 15200
|
| 1314 |
+
},
|
| 1315 |
+
{
|
| 1316 |
+
"epoch": 8.038880861683962,
|
| 1317 |
+
"grad_norm": 1.115820050239563,
|
| 1318 |
+
"learning_rate": 2.7222222222222223e-05,
|
| 1319 |
+
"loss": 0.7899,
|
| 1320 |
+
"step": 15300
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"epoch": 8.091422566662288,
|
| 1324 |
+
"grad_norm": 1.4497051239013672,
|
| 1325 |
+
"learning_rate": 2.7037037037037037e-05,
|
| 1326 |
+
"loss": 0.7809,
|
| 1327 |
+
"step": 15400
|
| 1328 |
+
},
|
| 1329 |
+
{
|
| 1330 |
+
"epoch": 8.143964271640614,
|
| 1331 |
+
"grad_norm": 1.9520905017852783,
|
| 1332 |
+
"learning_rate": 2.6851851851851855e-05,
|
| 1333 |
+
"loss": 0.7972,
|
| 1334 |
+
"step": 15500
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 8.143964271640614,
|
| 1338 |
+
"eval_loss": 0.8295345306396484,
|
| 1339 |
+
"eval_runtime": 1.2468,
|
| 1340 |
+
"eval_samples_per_second": 8.02,
|
| 1341 |
+
"eval_steps_per_second": 4.01,
|
| 1342 |
+
"step": 15500
|
| 1343 |
+
},
|
| 1344 |
+
{
|
| 1345 |
+
"epoch": 8.19650597661894,
|
| 1346 |
+
"grad_norm": 1.1650198698043823,
|
| 1347 |
+
"learning_rate": 2.6666666666666667e-05,
|
| 1348 |
+
"loss": 0.7869,
|
| 1349 |
+
"step": 15600
|
| 1350 |
+
},
|
| 1351 |
+
{
|
| 1352 |
+
"epoch": 8.249047681597268,
|
| 1353 |
+
"grad_norm": 0.9997352957725525,
|
| 1354 |
+
"learning_rate": 2.6481481481481485e-05,
|
| 1355 |
+
"loss": 0.7786,
|
| 1356 |
+
"step": 15700
|
| 1357 |
+
},
|
| 1358 |
+
{
|
| 1359 |
+
"epoch": 8.301589386575595,
|
| 1360 |
+
"grad_norm": 1.173376202583313,
|
| 1361 |
+
"learning_rate": 2.6296296296296296e-05,
|
| 1362 |
+
"loss": 0.7903,
|
| 1363 |
+
"step": 15800
|
| 1364 |
+
},
|
| 1365 |
+
{
|
| 1366 |
+
"epoch": 8.35413109155392,
|
| 1367 |
+
"grad_norm": 1.3240666389465332,
|
| 1368 |
+
"learning_rate": 2.6111111111111114e-05,
|
| 1369 |
+
"loss": 0.7874,
|
| 1370 |
+
"step": 15900
|
| 1371 |
+
},
|
| 1372 |
+
{
|
| 1373 |
+
"epoch": 8.406672796532247,
|
| 1374 |
+
"grad_norm": 1.077017903327942,
|
| 1375 |
+
"learning_rate": 2.5925925925925925e-05,
|
| 1376 |
+
"loss": 0.7835,
|
| 1377 |
+
"step": 16000
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 8.406672796532247,
|
| 1381 |
+
"eval_loss": 0.8272402882575989,
|
| 1382 |
+
"eval_runtime": 1.2976,
|
| 1383 |
+
"eval_samples_per_second": 7.706,
|
| 1384 |
+
"eval_steps_per_second": 3.853,
|
| 1385 |
+
"step": 16000
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 8.459214501510575,
|
| 1389 |
+
"grad_norm": 1.0706350803375244,
|
| 1390 |
+
"learning_rate": 2.5740740740740743e-05,
|
| 1391 |
+
"loss": 0.8083,
|
| 1392 |
+
"step": 16100
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 8.5117562064889,
|
| 1396 |
+
"grad_norm": 1.0505809783935547,
|
| 1397 |
+
"learning_rate": 2.5555555555555554e-05,
|
| 1398 |
+
"loss": 0.8085,
|
| 1399 |
+
"step": 16200
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 8.564297911467227,
|
| 1403 |
+
"grad_norm": 1.0813027620315552,
|
| 1404 |
+
"learning_rate": 2.5370370370370372e-05,
|
| 1405 |
+
"loss": 0.7943,
|
| 1406 |
+
"step": 16300
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 8.616839616445553,
|
| 1410 |
+
"grad_norm": 1.4488904476165771,
|
| 1411 |
+
"learning_rate": 2.5185185185185183e-05,
|
| 1412 |
+
"loss": 0.7885,
|
| 1413 |
+
"step": 16400
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 8.66938132142388,
|
| 1417 |
+
"grad_norm": 1.1785513162612915,
|
| 1418 |
+
"learning_rate": 2.5e-05,
|
| 1419 |
+
"loss": 0.7867,
|
| 1420 |
+
"step": 16500
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 8.66938132142388,
|
| 1424 |
+
"eval_loss": 0.8290830850601196,
|
| 1425 |
+
"eval_runtime": 1.2989,
|
| 1426 |
+
"eval_samples_per_second": 7.699,
|
| 1427 |
+
"eval_steps_per_second": 3.849,
|
| 1428 |
+
"step": 16500
|
| 1429 |
+
},
|
| 1430 |
+
{
|
| 1431 |
+
"epoch": 8.721923026402207,
|
| 1432 |
+
"grad_norm": 1.331755518913269,
|
| 1433 |
+
"learning_rate": 2.4814814814814816e-05,
|
| 1434 |
+
"loss": 0.7887,
|
| 1435 |
+
"step": 16600
|
| 1436 |
+
},
|
| 1437 |
+
{
|
| 1438 |
+
"epoch": 8.774464731380533,
|
| 1439 |
+
"grad_norm": 1.0079772472381592,
|
| 1440 |
+
"learning_rate": 2.462962962962963e-05,
|
| 1441 |
+
"loss": 0.7831,
|
| 1442 |
+
"step": 16700
|
| 1443 |
+
},
|
| 1444 |
+
{
|
| 1445 |
+
"epoch": 8.82700643635886,
|
| 1446 |
+
"grad_norm": 1.6257929801940918,
|
| 1447 |
+
"learning_rate": 2.4444444444444445e-05,
|
| 1448 |
+
"loss": 0.788,
|
| 1449 |
+
"step": 16800
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 8.879548141337187,
|
| 1453 |
+
"grad_norm": 1.5751090049743652,
|
| 1454 |
+
"learning_rate": 2.425925925925926e-05,
|
| 1455 |
+
"loss": 0.7864,
|
| 1456 |
+
"step": 16900
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"epoch": 8.932089846315513,
|
| 1460 |
+
"grad_norm": 1.0488544702529907,
|
| 1461 |
+
"learning_rate": 2.4074074074074074e-05,
|
| 1462 |
+
"loss": 0.8083,
|
| 1463 |
+
"step": 17000
|
| 1464 |
+
},
|
| 1465 |
+
{
|
| 1466 |
+
"epoch": 8.932089846315513,
|
| 1467 |
+
"eval_loss": 0.8188499212265015,
|
| 1468 |
+
"eval_runtime": 1.2935,
|
| 1469 |
+
"eval_samples_per_second": 7.731,
|
| 1470 |
+
"eval_steps_per_second": 3.865,
|
| 1471 |
+
"step": 17000
|
| 1472 |
+
},
|
| 1473 |
+
{
|
| 1474 |
+
"epoch": 8.98463155129384,
|
| 1475 |
+
"grad_norm": 1.8487260341644287,
|
| 1476 |
+
"learning_rate": 2.3888888888888892e-05,
|
| 1477 |
+
"loss": 0.7956,
|
| 1478 |
+
"step": 17100
|
| 1479 |
+
},
|
| 1480 |
+
{
|
| 1481 |
+
"epoch": 9.037173256272165,
|
| 1482 |
+
"grad_norm": 1.395914912223816,
|
| 1483 |
+
"learning_rate": 2.3703703703703707e-05,
|
| 1484 |
+
"loss": 0.7921,
|
| 1485 |
+
"step": 17200
|
| 1486 |
+
},
|
| 1487 |
+
{
|
| 1488 |
+
"epoch": 9.089714961250493,
|
| 1489 |
+
"grad_norm": 1.341793417930603,
|
| 1490 |
+
"learning_rate": 2.351851851851852e-05,
|
| 1491 |
+
"loss": 0.7975,
|
| 1492 |
+
"step": 17300
|
| 1493 |
+
},
|
| 1494 |
+
{
|
| 1495 |
+
"epoch": 9.14225666622882,
|
| 1496 |
+
"grad_norm": 1.0076344013214111,
|
| 1497 |
+
"learning_rate": 2.3333333333333336e-05,
|
| 1498 |
+
"loss": 0.773,
|
| 1499 |
+
"step": 17400
|
| 1500 |
+
},
|
| 1501 |
+
{
|
| 1502 |
+
"epoch": 9.194798371207145,
|
| 1503 |
+
"grad_norm": 1.081777811050415,
|
| 1504 |
+
"learning_rate": 2.314814814814815e-05,
|
| 1505 |
+
"loss": 0.7654,
|
| 1506 |
+
"step": 17500
|
| 1507 |
+
},
|
| 1508 |
+
{
|
| 1509 |
+
"epoch": 9.194798371207145,
|
| 1510 |
+
"eval_loss": 0.8274938464164734,
|
| 1511 |
+
"eval_runtime": 1.2836,
|
| 1512 |
+
"eval_samples_per_second": 7.79,
|
| 1513 |
+
"eval_steps_per_second": 3.895,
|
| 1514 |
+
"step": 17500
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 9.247340076185472,
|
| 1518 |
+
"grad_norm": 1.1430171728134155,
|
| 1519 |
+
"learning_rate": 2.2962962962962965e-05,
|
| 1520 |
+
"loss": 0.7956,
|
| 1521 |
+
"step": 17600
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 9.2998817811638,
|
| 1525 |
+
"grad_norm": 1.0450961589813232,
|
| 1526 |
+
"learning_rate": 2.277777777777778e-05,
|
| 1527 |
+
"loss": 0.7774,
|
| 1528 |
+
"step": 17700
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 9.352423486142126,
|
| 1532 |
+
"grad_norm": 1.0086592435836792,
|
| 1533 |
+
"learning_rate": 2.2592592592592594e-05,
|
| 1534 |
+
"loss": 0.7739,
|
| 1535 |
+
"step": 17800
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 9.404965191120452,
|
| 1539 |
+
"grad_norm": 1.7970887422561646,
|
| 1540 |
+
"learning_rate": 2.240740740740741e-05,
|
| 1541 |
+
"loss": 0.7793,
|
| 1542 |
+
"step": 17900
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 9.457506896098778,
|
| 1546 |
+
"grad_norm": 1.5623388290405273,
|
| 1547 |
+
"learning_rate": 2.2222222222222223e-05,
|
| 1548 |
+
"loss": 0.7793,
|
| 1549 |
+
"step": 18000
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 9.457506896098778,
|
| 1553 |
+
"eval_loss": 0.8288339376449585,
|
| 1554 |
+
"eval_runtime": 1.2843,
|
| 1555 |
+
"eval_samples_per_second": 7.786,
|
| 1556 |
+
"eval_steps_per_second": 3.893,
|
| 1557 |
+
"step": 18000
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 9.510048601077106,
|
| 1561 |
+
"grad_norm": 1.1271198987960815,
|
| 1562 |
+
"learning_rate": 2.2037037037037038e-05,
|
| 1563 |
+
"loss": 0.7693,
|
| 1564 |
+
"step": 18100
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 9.562590306055432,
|
| 1568 |
+
"grad_norm": 1.0703665018081665,
|
| 1569 |
+
"learning_rate": 2.1851851851851852e-05,
|
| 1570 |
+
"loss": 0.7734,
|
| 1571 |
+
"step": 18200
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 9.615132011033758,
|
| 1575 |
+
"grad_norm": 1.5558685064315796,
|
| 1576 |
+
"learning_rate": 2.1666666666666667e-05,
|
| 1577 |
+
"loss": 0.7778,
|
| 1578 |
+
"step": 18300
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 9.667673716012084,
|
| 1582 |
+
"grad_norm": 1.932632565498352,
|
| 1583 |
+
"learning_rate": 2.148148148148148e-05,
|
| 1584 |
+
"loss": 0.7842,
|
| 1585 |
+
"step": 18400
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 9.720215420990412,
|
| 1589 |
+
"grad_norm": 2.2928659915924072,
|
| 1590 |
+
"learning_rate": 2.1296296296296296e-05,
|
| 1591 |
+
"loss": 0.7761,
|
| 1592 |
+
"step": 18500
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 9.720215420990412,
|
| 1596 |
+
"eval_loss": 0.8304858207702637,
|
| 1597 |
+
"eval_runtime": 1.2431,
|
| 1598 |
+
"eval_samples_per_second": 8.045,
|
| 1599 |
+
"eval_steps_per_second": 4.022,
|
| 1600 |
+
"step": 18500
|
| 1601 |
+
},
|
| 1602 |
+
{
|
| 1603 |
+
"epoch": 9.772757125968738,
|
| 1604 |
+
"grad_norm": 1.588517189025879,
|
| 1605 |
+
"learning_rate": 2.111111111111111e-05,
|
| 1606 |
+
"loss": 0.7738,
|
| 1607 |
+
"step": 18600
|
| 1608 |
+
},
|
| 1609 |
+
{
|
| 1610 |
+
"epoch": 9.825298830947064,
|
| 1611 |
+
"grad_norm": 1.4118093252182007,
|
| 1612 |
+
"learning_rate": 2.0925925925925925e-05,
|
| 1613 |
+
"loss": 0.7852,
|
| 1614 |
+
"step": 18700
|
| 1615 |
+
},
|
| 1616 |
+
{
|
| 1617 |
+
"epoch": 9.87784053592539,
|
| 1618 |
+
"grad_norm": 1.7786134481430054,
|
| 1619 |
+
"learning_rate": 2.074074074074074e-05,
|
| 1620 |
+
"loss": 0.789,
|
| 1621 |
+
"step": 18800
|
| 1622 |
+
},
|
| 1623 |
+
{
|
| 1624 |
+
"epoch": 9.930382240903718,
|
| 1625 |
+
"grad_norm": 1.4427546262741089,
|
| 1626 |
+
"learning_rate": 2.0555555555555555e-05,
|
| 1627 |
+
"loss": 0.8028,
|
| 1628 |
+
"step": 18900
|
| 1629 |
+
},
|
| 1630 |
+
{
|
| 1631 |
+
"epoch": 9.982923945882044,
|
| 1632 |
+
"grad_norm": 1.2574381828308105,
|
| 1633 |
+
"learning_rate": 2.037037037037037e-05,
|
| 1634 |
+
"loss": 0.7694,
|
| 1635 |
+
"step": 19000
|
| 1636 |
+
},
|
| 1637 |
+
{
|
| 1638 |
+
"epoch": 9.982923945882044,
|
| 1639 |
+
"eval_loss": 0.8281936645507812,
|
| 1640 |
+
"eval_runtime": 1.2455,
|
| 1641 |
+
"eval_samples_per_second": 8.029,
|
| 1642 |
+
"eval_steps_per_second": 4.015,
|
| 1643 |
+
"step": 19000
|
| 1644 |
+
},
|
| 1645 |
+
{
|
| 1646 |
+
"epoch": 10.03546565086037,
|
| 1647 |
+
"grad_norm": 1.5743870735168457,
|
| 1648 |
+
"learning_rate": 2.0185185185185187e-05,
|
| 1649 |
+
"loss": 0.7619,
|
| 1650 |
+
"step": 19100
|
| 1651 |
+
},
|
| 1652 |
+
{
|
| 1653 |
+
"epoch": 10.088007355838696,
|
| 1654 |
+
"grad_norm": 1.350224494934082,
|
| 1655 |
+
"learning_rate": 2e-05,
|
| 1656 |
+
"loss": 0.7596,
|
| 1657 |
+
"step": 19200
|
| 1658 |
+
},
|
| 1659 |
+
{
|
| 1660 |
+
"epoch": 10.140549060817024,
|
| 1661 |
+
"grad_norm": 1.1520729064941406,
|
| 1662 |
+
"learning_rate": 1.9814814814814816e-05,
|
| 1663 |
+
"loss": 0.7561,
|
| 1664 |
+
"step": 19300
|
| 1665 |
+
},
|
| 1666 |
+
{
|
| 1667 |
+
"epoch": 10.19309076579535,
|
| 1668 |
+
"grad_norm": 1.2705488204956055,
|
| 1669 |
+
"learning_rate": 1.962962962962963e-05,
|
| 1670 |
+
"loss": 0.7659,
|
| 1671 |
+
"step": 19400
|
| 1672 |
+
},
|
| 1673 |
+
{
|
| 1674 |
+
"epoch": 10.245632470773677,
|
| 1675 |
+
"grad_norm": 1.1752071380615234,
|
| 1676 |
+
"learning_rate": 1.9444444444444445e-05,
|
| 1677 |
+
"loss": 0.7597,
|
| 1678 |
+
"step": 19500
|
| 1679 |
+
},
|
| 1680 |
+
{
|
| 1681 |
+
"epoch": 10.245632470773677,
|
| 1682 |
+
"eval_loss": 0.8358650207519531,
|
| 1683 |
+
"eval_runtime": 1.2389,
|
| 1684 |
+
"eval_samples_per_second": 8.072,
|
| 1685 |
+
"eval_steps_per_second": 4.036,
|
| 1686 |
+
"step": 19500
|
| 1687 |
+
},
|
| 1688 |
+
{
|
| 1689 |
+
"epoch": 10.298174175752003,
|
| 1690 |
+
"grad_norm": 1.3173915147781372,
|
| 1691 |
+
"learning_rate": 1.925925925925926e-05,
|
| 1692 |
+
"loss": 0.7787,
|
| 1693 |
+
"step": 19600
|
| 1694 |
+
},
|
| 1695 |
+
{
|
| 1696 |
+
"epoch": 10.35071588073033,
|
| 1697 |
+
"grad_norm": 1.3181281089782715,
|
| 1698 |
+
"learning_rate": 1.9074074074074075e-05,
|
| 1699 |
+
"loss": 0.7559,
|
| 1700 |
+
"step": 19700
|
| 1701 |
+
},
|
| 1702 |
+
{
|
| 1703 |
+
"epoch": 10.403257585708657,
|
| 1704 |
+
"grad_norm": 1.1058646440505981,
|
| 1705 |
+
"learning_rate": 1.888888888888889e-05,
|
| 1706 |
+
"loss": 0.7659,
|
| 1707 |
+
"step": 19800
|
| 1708 |
+
},
|
| 1709 |
+
{
|
| 1710 |
+
"epoch": 10.455799290686983,
|
| 1711 |
+
"grad_norm": 1.2898966073989868,
|
| 1712 |
+
"learning_rate": 1.8703703703703704e-05,
|
| 1713 |
+
"loss": 0.7642,
|
| 1714 |
+
"step": 19900
|
| 1715 |
+
},
|
| 1716 |
+
{
|
| 1717 |
+
"epoch": 10.508340995665309,
|
| 1718 |
+
"grad_norm": 1.7255585193634033,
|
| 1719 |
+
"learning_rate": 1.8518518518518518e-05,
|
| 1720 |
+
"loss": 0.7659,
|
| 1721 |
+
"step": 20000
|
| 1722 |
+
},
|
| 1723 |
+
{
|
| 1724 |
+
"epoch": 10.508340995665309,
|
| 1725 |
+
"eval_loss": 0.8337475061416626,
|
| 1726 |
+
"eval_runtime": 1.2724,
|
| 1727 |
+
"eval_samples_per_second": 7.859,
|
| 1728 |
+
"eval_steps_per_second": 3.93,
|
| 1729 |
+
"step": 20000
|
| 1730 |
+
},
|
| 1731 |
+
{
|
| 1732 |
+
"epoch": 10.560882700643635,
|
| 1733 |
+
"grad_norm": 1.101854681968689,
|
| 1734 |
+
"learning_rate": 1.8333333333333333e-05,
|
| 1735 |
+
"loss": 0.7754,
|
| 1736 |
+
"step": 20100
|
| 1737 |
+
},
|
| 1738 |
+
{
|
| 1739 |
+
"epoch": 10.613424405621963,
|
| 1740 |
+
"grad_norm": 1.6675972938537598,
|
| 1741 |
+
"learning_rate": 1.814814814814815e-05,
|
| 1742 |
+
"loss": 0.7597,
|
| 1743 |
+
"step": 20200
|
| 1744 |
+
},
|
| 1745 |
+
{
|
| 1746 |
+
"epoch": 10.665966110600289,
|
| 1747 |
+
"grad_norm": 1.428888201713562,
|
| 1748 |
+
"learning_rate": 1.7962962962962965e-05,
|
| 1749 |
+
"loss": 0.7714,
|
| 1750 |
+
"step": 20300
|
| 1751 |
+
},
|
| 1752 |
+
{
|
| 1753 |
+
"epoch": 10.718507815578615,
|
| 1754 |
+
"grad_norm": 1.2556451559066772,
|
| 1755 |
+
"learning_rate": 1.777777777777778e-05,
|
| 1756 |
+
"loss": 0.7628,
|
| 1757 |
+
"step": 20400
|
| 1758 |
+
},
|
| 1759 |
+
{
|
| 1760 |
+
"epoch": 10.771049520556943,
|
| 1761 |
+
"grad_norm": 1.817168951034546,
|
| 1762 |
+
"learning_rate": 1.7592592592592595e-05,
|
| 1763 |
+
"loss": 0.7652,
|
| 1764 |
+
"step": 20500
|
| 1765 |
+
},
|
| 1766 |
+
{
|
| 1767 |
+
"epoch": 10.771049520556943,
|
| 1768 |
+
"eval_loss": 0.8289246559143066,
|
| 1769 |
+
"eval_runtime": 1.2657,
|
| 1770 |
+
"eval_samples_per_second": 7.901,
|
| 1771 |
+
"eval_steps_per_second": 3.95,
|
| 1772 |
+
"step": 20500
|
| 1773 |
+
},
|
| 1774 |
+
{
|
| 1775 |
+
"epoch": 10.823591225535269,
|
| 1776 |
+
"grad_norm": 0.9452287554740906,
|
| 1777 |
+
"learning_rate": 1.740740740740741e-05,
|
| 1778 |
+
"loss": 0.7661,
|
| 1779 |
+
"step": 20600
|
| 1780 |
+
},
|
| 1781 |
+
{
|
| 1782 |
+
"epoch": 10.876132930513595,
|
| 1783 |
+
"grad_norm": 1.0433977842330933,
|
| 1784 |
+
"learning_rate": 1.7222222222222224e-05,
|
| 1785 |
+
"loss": 0.7662,
|
| 1786 |
+
"step": 20700
|
| 1787 |
+
},
|
| 1788 |
+
{
|
| 1789 |
+
"epoch": 10.928674635491921,
|
| 1790 |
+
"grad_norm": 1.7316306829452515,
|
| 1791 |
+
"learning_rate": 1.7037037037037038e-05,
|
| 1792 |
+
"loss": 0.7694,
|
| 1793 |
+
"step": 20800
|
| 1794 |
+
},
|
| 1795 |
+
{
|
| 1796 |
+
"epoch": 10.981216340470247,
|
| 1797 |
+
"grad_norm": 1.1855412721633911,
|
| 1798 |
+
"learning_rate": 1.6851851851851853e-05,
|
| 1799 |
+
"loss": 0.7608,
|
| 1800 |
+
"step": 20900
|
| 1801 |
+
},
|
| 1802 |
+
{
|
| 1803 |
+
"epoch": 11.033758045448575,
|
| 1804 |
+
"grad_norm": 1.2221699953079224,
|
| 1805 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 1806 |
+
"loss": 0.7538,
|
| 1807 |
+
"step": 21000
|
| 1808 |
+
},
|
| 1809 |
+
{
|
| 1810 |
+
"epoch": 11.033758045448575,
|
| 1811 |
+
"eval_loss": 0.8385075330734253,
|
| 1812 |
+
"eval_runtime": 1.2472,
|
| 1813 |
+
"eval_samples_per_second": 8.018,
|
| 1814 |
+
"eval_steps_per_second": 4.009,
|
| 1815 |
+
"step": 21000
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 11.086299750426901,
|
| 1819 |
+
"grad_norm": 1.1642967462539673,
|
| 1820 |
+
"learning_rate": 1.6481481481481482e-05,
|
| 1821 |
+
"loss": 0.7348,
|
| 1822 |
+
"step": 21100
|
| 1823 |
+
},
|
| 1824 |
+
{
|
| 1825 |
+
"epoch": 11.138841455405228,
|
| 1826 |
+
"grad_norm": 1.7363336086273193,
|
| 1827 |
+
"learning_rate": 1.62962962962963e-05,
|
| 1828 |
+
"loss": 0.756,
|
| 1829 |
+
"step": 21200
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 11.191383160383554,
|
| 1833 |
+
"grad_norm": 1.3126277923583984,
|
| 1834 |
+
"learning_rate": 1.6111111111111115e-05,
|
| 1835 |
+
"loss": 0.7515,
|
| 1836 |
+
"step": 21300
|
| 1837 |
+
},
|
| 1838 |
+
{
|
| 1839 |
+
"epoch": 11.243924865361882,
|
| 1840 |
+
"grad_norm": 2.1372787952423096,
|
| 1841 |
+
"learning_rate": 1.5925925925925926e-05,
|
| 1842 |
+
"loss": 0.7487,
|
| 1843 |
+
"step": 21400
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 11.296466570340208,
|
| 1847 |
+
"grad_norm": 1.5635650157928467,
|
| 1848 |
+
"learning_rate": 1.574074074074074e-05,
|
| 1849 |
+
"loss": 0.7554,
|
| 1850 |
+
"step": 21500
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 11.296466570340208,
|
| 1854 |
+
"eval_loss": 0.8373192548751831,
|
| 1855 |
+
"eval_runtime": 1.2681,
|
| 1856 |
+
"eval_samples_per_second": 7.886,
|
| 1857 |
+
"eval_steps_per_second": 3.943,
|
| 1858 |
+
"step": 21500
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 11.349008275318534,
|
| 1862 |
+
"grad_norm": 1.708914875984192,
|
| 1863 |
+
"learning_rate": 1.5555555555555555e-05,
|
| 1864 |
+
"loss": 0.7648,
|
| 1865 |
+
"step": 21600
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 11.40154998029686,
|
| 1869 |
+
"grad_norm": 1.1601842641830444,
|
| 1870 |
+
"learning_rate": 1.537037037037037e-05,
|
| 1871 |
+
"loss": 0.7614,
|
| 1872 |
+
"step": 21700
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 11.454091685275188,
|
| 1876 |
+
"grad_norm": 1.1674526929855347,
|
| 1877 |
+
"learning_rate": 1.5185185185185186e-05,
|
| 1878 |
+
"loss": 0.7653,
|
| 1879 |
+
"step": 21800
|
| 1880 |
+
},
|
| 1881 |
+
{
|
| 1882 |
+
"epoch": 11.506633390253514,
|
| 1883 |
+
"grad_norm": 1.2474111318588257,
|
| 1884 |
+
"learning_rate": 1.5e-05,
|
| 1885 |
+
"loss": 0.7596,
|
| 1886 |
+
"step": 21900
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 11.55917509523184,
|
| 1890 |
+
"grad_norm": 1.2556248903274536,
|
| 1891 |
+
"learning_rate": 1.4814814814814815e-05,
|
| 1892 |
+
"loss": 0.7445,
|
| 1893 |
+
"step": 22000
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 11.55917509523184,
|
| 1897 |
+
"eval_loss": 0.8322497606277466,
|
| 1898 |
+
"eval_runtime": 1.2428,
|
| 1899 |
+
"eval_samples_per_second": 8.046,
|
| 1900 |
+
"eval_steps_per_second": 4.023,
|
| 1901 |
+
"step": 22000
|
| 1902 |
+
},
|
| 1903 |
+
{
|
| 1904 |
+
"epoch": 11.611716800210166,
|
| 1905 |
+
"grad_norm": 1.5506947040557861,
|
| 1906 |
+
"learning_rate": 1.462962962962963e-05,
|
| 1907 |
+
"loss": 0.7449,
|
| 1908 |
+
"step": 22100
|
| 1909 |
+
},
|
| 1910 |
+
{
|
| 1911 |
+
"epoch": 11.664258505188494,
|
| 1912 |
+
"grad_norm": 1.124089241027832,
|
| 1913 |
+
"learning_rate": 1.4444444444444444e-05,
|
| 1914 |
+
"loss": 0.7613,
|
| 1915 |
+
"step": 22200
|
| 1916 |
+
},
|
| 1917 |
+
{
|
| 1918 |
+
"epoch": 11.71680021016682,
|
| 1919 |
+
"grad_norm": 1.5663940906524658,
|
| 1920 |
+
"learning_rate": 1.425925925925926e-05,
|
| 1921 |
+
"loss": 0.7447,
|
| 1922 |
+
"step": 22300
|
| 1923 |
+
},
|
| 1924 |
+
{
|
| 1925 |
+
"epoch": 11.769341915145146,
|
| 1926 |
+
"grad_norm": 1.4085638523101807,
|
| 1927 |
+
"learning_rate": 1.4074074074074075e-05,
|
| 1928 |
+
"loss": 0.745,
|
| 1929 |
+
"step": 22400
|
| 1930 |
+
},
|
| 1931 |
+
{
|
| 1932 |
+
"epoch": 11.821883620123472,
|
| 1933 |
+
"grad_norm": 1.8693653345108032,
|
| 1934 |
+
"learning_rate": 1.388888888888889e-05,
|
| 1935 |
+
"loss": 0.7615,
|
| 1936 |
+
"step": 22500
|
| 1937 |
+
},
|
| 1938 |
+
{
|
| 1939 |
+
"epoch": 11.821883620123472,
|
| 1940 |
+
"eval_loss": 0.8351184129714966,
|
| 1941 |
+
"eval_runtime": 1.2433,
|
| 1942 |
+
"eval_samples_per_second": 8.043,
|
| 1943 |
+
"eval_steps_per_second": 4.022,
|
| 1944 |
+
"step": 22500
|
| 1945 |
+
},
|
| 1946 |
+
{
|
| 1947 |
+
"epoch": 11.8744253251018,
|
| 1948 |
+
"grad_norm": 1.807320237159729,
|
| 1949 |
+
"learning_rate": 1.3703703703703704e-05,
|
| 1950 |
+
"loss": 0.7605,
|
| 1951 |
+
"step": 22600
|
| 1952 |
+
},
|
| 1953 |
+
{
|
| 1954 |
+
"epoch": 11.926967030080126,
|
| 1955 |
+
"grad_norm": 1.1300692558288574,
|
| 1956 |
+
"learning_rate": 1.3518518518518519e-05,
|
| 1957 |
+
"loss": 0.7604,
|
| 1958 |
+
"step": 22700
|
| 1959 |
+
},
|
| 1960 |
+
{
|
| 1961 |
+
"epoch": 11.979508735058452,
|
| 1962 |
+
"grad_norm": 1.5714143514633179,
|
| 1963 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 1964 |
+
"loss": 0.7462,
|
| 1965 |
+
"step": 22800
|
| 1966 |
+
},
|
| 1967 |
+
{
|
| 1968 |
+
"epoch": 12.032050440036778,
|
| 1969 |
+
"grad_norm": 1.1730937957763672,
|
| 1970 |
+
"learning_rate": 1.3148148148148148e-05,
|
| 1971 |
+
"loss": 0.7655,
|
| 1972 |
+
"step": 22900
|
| 1973 |
+
},
|
| 1974 |
+
{
|
| 1975 |
+
"epoch": 12.084592145015106,
|
| 1976 |
+
"grad_norm": 1.1946797370910645,
|
| 1977 |
+
"learning_rate": 1.2962962962962962e-05,
|
| 1978 |
+
"loss": 0.7326,
|
| 1979 |
+
"step": 23000
|
| 1980 |
+
},
|
| 1981 |
+
{
|
| 1982 |
+
"epoch": 12.084592145015106,
|
| 1983 |
+
"eval_loss": 0.8375317454338074,
|
| 1984 |
+
"eval_runtime": 1.2867,
|
| 1985 |
+
"eval_samples_per_second": 7.772,
|
| 1986 |
+
"eval_steps_per_second": 3.886,
|
| 1987 |
+
"step": 23000
|
| 1988 |
+
},
|
| 1989 |
+
{
|
| 1990 |
+
"epoch": 12.137133849993432,
|
| 1991 |
+
"grad_norm": 1.1328163146972656,
|
| 1992 |
+
"learning_rate": 1.2777777777777777e-05,
|
| 1993 |
+
"loss": 0.7439,
|
| 1994 |
+
"step": 23100
|
| 1995 |
+
},
|
| 1996 |
+
{
|
| 1997 |
+
"epoch": 12.189675554971759,
|
| 1998 |
+
"grad_norm": 1.026856780052185,
|
| 1999 |
+
"learning_rate": 1.2592592592592592e-05,
|
| 2000 |
+
"loss": 0.7589,
|
| 2001 |
+
"step": 23200
|
| 2002 |
+
},
|
| 2003 |
+
{
|
| 2004 |
+
"epoch": 12.242217259950085,
|
| 2005 |
+
"grad_norm": 1.920116662979126,
|
| 2006 |
+
"learning_rate": 1.2407407407407408e-05,
|
| 2007 |
+
"loss": 0.7458,
|
| 2008 |
+
"step": 23300
|
| 2009 |
+
},
|
| 2010 |
+
{
|
| 2011 |
+
"epoch": 12.294758964928413,
|
| 2012 |
+
"grad_norm": 1.3238016366958618,
|
| 2013 |
+
"learning_rate": 1.2222222222222222e-05,
|
| 2014 |
+
"loss": 0.74,
|
| 2015 |
+
"step": 23400
|
| 2016 |
+
},
|
| 2017 |
+
{
|
| 2018 |
+
"epoch": 12.347300669906739,
|
| 2019 |
+
"grad_norm": 1.192124843597412,
|
| 2020 |
+
"learning_rate": 1.2037037037037037e-05,
|
| 2021 |
+
"loss": 0.7369,
|
| 2022 |
+
"step": 23500
|
| 2023 |
+
},
|
| 2024 |
+
{
|
| 2025 |
+
"epoch": 12.347300669906739,
|
| 2026 |
+
"eval_loss": 0.8405577540397644,
|
| 2027 |
+
"eval_runtime": 1.2401,
|
| 2028 |
+
"eval_samples_per_second": 8.064,
|
| 2029 |
+
"eval_steps_per_second": 4.032,
|
| 2030 |
+
"step": 23500
|
| 2031 |
+
},
|
| 2032 |
+
{
|
| 2033 |
+
"epoch": 12.399842374885065,
|
| 2034 |
+
"grad_norm": 1.3931485414505005,
|
| 2035 |
+
"learning_rate": 1.1851851851851853e-05,
|
| 2036 |
+
"loss": 0.7619,
|
| 2037 |
+
"step": 23600
|
| 2038 |
+
},
|
| 2039 |
+
{
|
| 2040 |
+
"epoch": 12.452384079863391,
|
| 2041 |
+
"grad_norm": 1.071673035621643,
|
| 2042 |
+
"learning_rate": 1.1666666666666668e-05,
|
| 2043 |
+
"loss": 0.753,
|
| 2044 |
+
"step": 23700
|
| 2045 |
+
},
|
| 2046 |
+
{
|
| 2047 |
+
"epoch": 12.504925784841719,
|
| 2048 |
+
"grad_norm": 1.2407554388046265,
|
| 2049 |
+
"learning_rate": 1.1481481481481482e-05,
|
| 2050 |
+
"loss": 0.7382,
|
| 2051 |
+
"step": 23800
|
| 2052 |
+
},
|
| 2053 |
+
{
|
| 2054 |
+
"epoch": 12.557467489820045,
|
| 2055 |
+
"grad_norm": 1.2360953092575073,
|
| 2056 |
+
"learning_rate": 1.1296296296296297e-05,
|
| 2057 |
+
"loss": 0.7348,
|
| 2058 |
+
"step": 23900
|
| 2059 |
+
},
|
| 2060 |
+
{
|
| 2061 |
+
"epoch": 12.610009194798371,
|
| 2062 |
+
"grad_norm": 1.2687872648239136,
|
| 2063 |
+
"learning_rate": 1.1111111111111112e-05,
|
| 2064 |
+
"loss": 0.75,
|
| 2065 |
+
"step": 24000
|
| 2066 |
+
},
|
| 2067 |
+
{
|
| 2068 |
+
"epoch": 12.610009194798371,
|
| 2069 |
+
"eval_loss": 0.8404332399368286,
|
| 2070 |
+
"eval_runtime": 1.2513,
|
| 2071 |
+
"eval_samples_per_second": 7.992,
|
| 2072 |
+
"eval_steps_per_second": 3.996,
|
| 2073 |
+
"step": 24000
|
| 2074 |
+
},
|
| 2075 |
+
{
|
| 2076 |
+
"epoch": 12.662550899776697,
|
| 2077 |
+
"grad_norm": 1.1866815090179443,
|
| 2078 |
+
"learning_rate": 1.0925925925925926e-05,
|
| 2079 |
+
"loss": 0.7419,
|
| 2080 |
+
"step": 24100
|
| 2081 |
+
},
|
| 2082 |
+
{
|
| 2083 |
+
"epoch": 12.715092604755025,
|
| 2084 |
+
"grad_norm": 1.715956687927246,
|
| 2085 |
+
"learning_rate": 1.074074074074074e-05,
|
| 2086 |
+
"loss": 0.7406,
|
| 2087 |
+
"step": 24200
|
| 2088 |
+
},
|
| 2089 |
+
{
|
| 2090 |
+
"epoch": 12.767634309733351,
|
| 2091 |
+
"grad_norm": 1.1529712677001953,
|
| 2092 |
+
"learning_rate": 1.0555555555555555e-05,
|
| 2093 |
+
"loss": 0.7516,
|
| 2094 |
+
"step": 24300
|
| 2095 |
+
},
|
| 2096 |
+
{
|
| 2097 |
+
"epoch": 12.820176014711677,
|
| 2098 |
+
"grad_norm": 1.2465269565582275,
|
| 2099 |
+
"learning_rate": 1.037037037037037e-05,
|
| 2100 |
+
"loss": 0.7407,
|
| 2101 |
+
"step": 24400
|
| 2102 |
+
},
|
| 2103 |
+
{
|
| 2104 |
+
"epoch": 12.872717719690003,
|
| 2105 |
+
"grad_norm": 1.1018378734588623,
|
| 2106 |
+
"learning_rate": 1.0185185185185185e-05,
|
| 2107 |
+
"loss": 0.7514,
|
| 2108 |
+
"step": 24500
|
| 2109 |
+
},
|
| 2110 |
+
{
|
| 2111 |
+
"epoch": 12.872717719690003,
|
| 2112 |
+
"eval_loss": 0.8341609835624695,
|
| 2113 |
+
"eval_runtime": 1.2427,
|
| 2114 |
+
"eval_samples_per_second": 8.047,
|
| 2115 |
+
"eval_steps_per_second": 4.024,
|
| 2116 |
+
"step": 24500
|
| 2117 |
+
},
|
| 2118 |
+
{
|
| 2119 |
+
"epoch": 12.925259424668331,
|
| 2120 |
+
"grad_norm": 1.2097246646881104,
|
| 2121 |
+
"learning_rate": 1e-05,
|
| 2122 |
+
"loss": 0.7298,
|
| 2123 |
+
"step": 24600
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 12.977801129646657,
|
| 2127 |
+
"grad_norm": 1.5760364532470703,
|
| 2128 |
+
"learning_rate": 9.814814814814815e-06,
|
| 2129 |
+
"loss": 0.7538,
|
| 2130 |
+
"step": 24700
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 13.030342834624983,
|
| 2134 |
+
"grad_norm": 1.2670038938522339,
|
| 2135 |
+
"learning_rate": 9.62962962962963e-06,
|
| 2136 |
+
"loss": 0.7437,
|
| 2137 |
+
"step": 24800
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 13.08288453960331,
|
| 2141 |
+
"grad_norm": 1.178148627281189,
|
| 2142 |
+
"learning_rate": 9.444444444444445e-06,
|
| 2143 |
+
"loss": 0.7392,
|
| 2144 |
+
"step": 24900
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 13.135426244581637,
|
| 2148 |
+
"grad_norm": 1.2803364992141724,
|
| 2149 |
+
"learning_rate": 9.259259259259259e-06,
|
| 2150 |
+
"loss": 0.7178,
|
| 2151 |
+
"step": 25000
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 13.135426244581637,
|
| 2155 |
+
"eval_loss": 0.8406384587287903,
|
| 2156 |
+
"eval_runtime": 1.2436,
|
| 2157 |
+
"eval_samples_per_second": 8.041,
|
| 2158 |
+
"eval_steps_per_second": 4.02,
|
| 2159 |
+
"step": 25000
|
| 2160 |
+
},
|
| 2161 |
+
{
|
| 2162 |
+
"epoch": 13.187967949559964,
|
| 2163 |
+
"grad_norm": 1.3507287502288818,
|
| 2164 |
+
"learning_rate": 9.074074074074075e-06,
|
| 2165 |
+
"loss": 0.7473,
|
| 2166 |
+
"step": 25100
|
| 2167 |
+
},
|
| 2168 |
+
{
|
| 2169 |
+
"epoch": 13.24050965453829,
|
| 2170 |
+
"grad_norm": 1.1901633739471436,
|
| 2171 |
+
"learning_rate": 8.88888888888889e-06,
|
| 2172 |
+
"loss": 0.7386,
|
| 2173 |
+
"step": 25200
|
| 2174 |
+
},
|
| 2175 |
+
{
|
| 2176 |
+
"epoch": 13.293051359516616,
|
| 2177 |
+
"grad_norm": 1.25368332862854,
|
| 2178 |
+
"learning_rate": 8.703703703703705e-06,
|
| 2179 |
+
"loss": 0.7426,
|
| 2180 |
+
"step": 25300
|
| 2181 |
+
},
|
| 2182 |
+
{
|
| 2183 |
+
"epoch": 13.345593064494944,
|
| 2184 |
+
"grad_norm": 1.4581819772720337,
|
| 2185 |
+
"learning_rate": 8.518518518518519e-06,
|
| 2186 |
+
"loss": 0.7479,
|
| 2187 |
+
"step": 25400
|
| 2188 |
+
},
|
| 2189 |
+
{
|
| 2190 |
+
"epoch": 13.39813476947327,
|
| 2191 |
+
"grad_norm": 1.201744556427002,
|
| 2192 |
+
"learning_rate": 8.333333333333334e-06,
|
| 2193 |
+
"loss": 0.7266,
|
| 2194 |
+
"step": 25500
|
| 2195 |
+
},
|
| 2196 |
+
{
|
| 2197 |
+
"epoch": 13.39813476947327,
|
| 2198 |
+
"eval_loss": 0.8411173820495605,
|
| 2199 |
+
"eval_runtime": 1.2635,
|
| 2200 |
+
"eval_samples_per_second": 7.915,
|
| 2201 |
+
"eval_steps_per_second": 3.957,
|
| 2202 |
+
"step": 25500
|
| 2203 |
+
},
|
| 2204 |
+
{
|
| 2205 |
+
"epoch": 13.450676474451596,
|
| 2206 |
+
"grad_norm": 1.3724862337112427,
|
| 2207 |
+
"learning_rate": 8.14814814814815e-06,
|
| 2208 |
+
"loss": 0.7392,
|
| 2209 |
+
"step": 25600
|
| 2210 |
+
},
|
| 2211 |
+
{
|
| 2212 |
+
"epoch": 13.503218179429922,
|
| 2213 |
+
"grad_norm": 1.2667688131332397,
|
| 2214 |
+
"learning_rate": 7.962962962962963e-06,
|
| 2215 |
+
"loss": 0.731,
|
| 2216 |
+
"step": 25700
|
| 2217 |
+
},
|
| 2218 |
+
{
|
| 2219 |
+
"epoch": 13.55575988440825,
|
| 2220 |
+
"grad_norm": 1.3549320697784424,
|
| 2221 |
+
"learning_rate": 7.777777777777777e-06,
|
| 2222 |
+
"loss": 0.7307,
|
| 2223 |
+
"step": 25800
|
| 2224 |
+
},
|
| 2225 |
+
{
|
| 2226 |
+
"epoch": 13.608301589386576,
|
| 2227 |
+
"grad_norm": 1.3319281339645386,
|
| 2228 |
+
"learning_rate": 7.592592592592593e-06,
|
| 2229 |
+
"loss": 0.7315,
|
| 2230 |
+
"step": 25900
|
| 2231 |
+
},
|
| 2232 |
+
{
|
| 2233 |
+
"epoch": 13.660843294364902,
|
| 2234 |
+
"grad_norm": 1.3759852647781372,
|
| 2235 |
+
"learning_rate": 7.4074074074074075e-06,
|
| 2236 |
+
"loss": 0.7338,
|
| 2237 |
+
"step": 26000
|
| 2238 |
+
},
|
| 2239 |
+
{
|
| 2240 |
+
"epoch": 13.660843294364902,
|
| 2241 |
+
"eval_loss": 0.8397306203842163,
|
| 2242 |
+
"eval_runtime": 1.2452,
|
| 2243 |
+
"eval_samples_per_second": 8.031,
|
| 2244 |
+
"eval_steps_per_second": 4.015,
|
| 2245 |
+
"step": 26000
|
| 2246 |
+
},
|
| 2247 |
+
{
|
| 2248 |
+
"epoch": 13.713384999343228,
|
| 2249 |
+
"grad_norm": 1.452658772468567,
|
| 2250 |
+
"learning_rate": 7.222222222222222e-06,
|
| 2251 |
+
"loss": 0.7339,
|
| 2252 |
+
"step": 26100
|
| 2253 |
+
},
|
| 2254 |
+
{
|
| 2255 |
+
"epoch": 13.765926704321554,
|
| 2256 |
+
"grad_norm": 1.1617493629455566,
|
| 2257 |
+
"learning_rate": 7.0370370370370375e-06,
|
| 2258 |
+
"loss": 0.737,
|
| 2259 |
+
"step": 26200
|
| 2260 |
+
},
|
| 2261 |
+
{
|
| 2262 |
+
"epoch": 13.818468409299882,
|
| 2263 |
+
"grad_norm": 1.628431797027588,
|
| 2264 |
+
"learning_rate": 6.851851851851852e-06,
|
| 2265 |
+
"loss": 0.7437,
|
| 2266 |
+
"step": 26300
|
| 2267 |
+
},
|
| 2268 |
+
{
|
| 2269 |
+
"epoch": 13.871010114278208,
|
| 2270 |
+
"grad_norm": 1.4544808864593506,
|
| 2271 |
+
"learning_rate": 6.666666666666667e-06,
|
| 2272 |
+
"loss": 0.7411,
|
| 2273 |
+
"step": 26400
|
| 2274 |
+
},
|
| 2275 |
+
{
|
| 2276 |
+
"epoch": 13.923551819256534,
|
| 2277 |
+
"grad_norm": 1.7027857303619385,
|
| 2278 |
+
"learning_rate": 6.481481481481481e-06,
|
| 2279 |
+
"loss": 0.7432,
|
| 2280 |
+
"step": 26500
|
| 2281 |
+
},
|
| 2282 |
+
{
|
| 2283 |
+
"epoch": 13.923551819256534,
|
| 2284 |
+
"eval_loss": 0.8381926417350769,
|
| 2285 |
+
"eval_runtime": 1.2458,
|
| 2286 |
+
"eval_samples_per_second": 8.027,
|
| 2287 |
+
"eval_steps_per_second": 4.013,
|
| 2288 |
+
"step": 26500
|
| 2289 |
+
},
|
| 2290 |
+
{
|
| 2291 |
+
"epoch": 13.976093524234862,
|
| 2292 |
+
"grad_norm": 1.320162296295166,
|
| 2293 |
+
"learning_rate": 6.296296296296296e-06,
|
| 2294 |
+
"loss": 0.7463,
|
| 2295 |
+
"step": 26600
|
| 2296 |
+
},
|
| 2297 |
+
{
|
| 2298 |
+
"epoch": 14.028635229213188,
|
| 2299 |
+
"grad_norm": 1.2044928073883057,
|
| 2300 |
+
"learning_rate": 6.111111111111111e-06,
|
| 2301 |
+
"loss": 0.7358,
|
| 2302 |
+
"step": 26700
|
| 2303 |
+
},
|
| 2304 |
+
{
|
| 2305 |
+
"epoch": 14.081176934191515,
|
| 2306 |
+
"grad_norm": 1.0798685550689697,
|
| 2307 |
+
"learning_rate": 5.925925925925927e-06,
|
| 2308 |
+
"loss": 0.7416,
|
| 2309 |
+
"step": 26800
|
| 2310 |
+
},
|
| 2311 |
+
{
|
| 2312 |
+
"epoch": 14.13371863916984,
|
| 2313 |
+
"grad_norm": 1.4219785928726196,
|
| 2314 |
+
"learning_rate": 5.740740740740741e-06,
|
| 2315 |
+
"loss": 0.7256,
|
| 2316 |
+
"step": 26900
|
| 2317 |
+
},
|
| 2318 |
+
{
|
| 2319 |
+
"epoch": 14.186260344148167,
|
| 2320 |
+
"grad_norm": 1.1347541809082031,
|
| 2321 |
+
"learning_rate": 5.555555555555556e-06,
|
| 2322 |
+
"loss": 0.7322,
|
| 2323 |
+
"step": 27000
|
| 2324 |
+
},
|
| 2325 |
+
{
|
| 2326 |
+
"epoch": 14.186260344148167,
|
| 2327 |
+
"eval_loss": 0.8432482481002808,
|
| 2328 |
+
"eval_runtime": 1.2881,
|
| 2329 |
+
"eval_samples_per_second": 7.763,
|
| 2330 |
+
"eval_steps_per_second": 3.882,
|
| 2331 |
+
"step": 27000
|
| 2332 |
+
},
|
| 2333 |
+
{
|
| 2334 |
+
"epoch": 14.238802049126495,
|
| 2335 |
+
"grad_norm": 1.5265473127365112,
|
| 2336 |
+
"learning_rate": 5.37037037037037e-06,
|
| 2337 |
+
"loss": 0.7281,
|
| 2338 |
+
"step": 27100
|
| 2339 |
+
},
|
| 2340 |
+
{
|
| 2341 |
+
"epoch": 14.29134375410482,
|
| 2342 |
+
"grad_norm": 1.0720326900482178,
|
| 2343 |
+
"learning_rate": 5.185185185185185e-06,
|
| 2344 |
+
"loss": 0.731,
|
| 2345 |
+
"step": 27200
|
| 2346 |
+
},
|
| 2347 |
+
{
|
| 2348 |
+
"epoch": 14.343885459083147,
|
| 2349 |
+
"grad_norm": 1.5150460004806519,
|
| 2350 |
+
"learning_rate": 5e-06,
|
| 2351 |
+
"loss": 0.719,
|
| 2352 |
+
"step": 27300
|
| 2353 |
+
},
|
| 2354 |
+
{
|
| 2355 |
+
"epoch": 14.396427164061473,
|
| 2356 |
+
"grad_norm": 1.2847768068313599,
|
| 2357 |
+
"learning_rate": 4.814814814814815e-06,
|
| 2358 |
+
"loss": 0.7307,
|
| 2359 |
+
"step": 27400
|
| 2360 |
+
},
|
| 2361 |
+
{
|
| 2362 |
+
"epoch": 14.4489688690398,
|
| 2363 |
+
"grad_norm": 1.4064009189605713,
|
| 2364 |
+
"learning_rate": 4.6296296296296296e-06,
|
| 2365 |
+
"loss": 0.7293,
|
| 2366 |
+
"step": 27500
|
| 2367 |
+
},
|
| 2368 |
+
{
|
| 2369 |
+
"epoch": 14.4489688690398,
|
| 2370 |
+
"eval_loss": 0.8425260782241821,
|
| 2371 |
+
"eval_runtime": 1.247,
|
| 2372 |
+
"eval_samples_per_second": 8.019,
|
| 2373 |
+
"eval_steps_per_second": 4.01,
|
| 2374 |
+
"step": 27500
|
| 2375 |
+
},
|
| 2376 |
+
{
|
| 2377 |
+
"epoch": 14.501510574018127,
|
| 2378 |
+
"grad_norm": 1.1766741275787354,
|
| 2379 |
+
"learning_rate": 4.444444444444445e-06,
|
| 2380 |
+
"loss": 0.7406,
|
| 2381 |
+
"step": 27600
|
| 2382 |
+
},
|
| 2383 |
+
{
|
| 2384 |
+
"epoch": 14.554052278996453,
|
| 2385 |
+
"grad_norm": 1.3252798318862915,
|
| 2386 |
+
"learning_rate": 4.2592592592592596e-06,
|
| 2387 |
+
"loss": 0.7377,
|
| 2388 |
+
"step": 27700
|
| 2389 |
+
},
|
| 2390 |
+
{
|
| 2391 |
+
"epoch": 14.60659398397478,
|
| 2392 |
+
"grad_norm": 1.2687978744506836,
|
| 2393 |
+
"learning_rate": 4.074074074074075e-06,
|
| 2394 |
+
"loss": 0.7303,
|
| 2395 |
+
"step": 27800
|
| 2396 |
+
},
|
| 2397 |
+
{
|
| 2398 |
+
"epoch": 14.659135688953107,
|
| 2399 |
+
"grad_norm": 1.29690420627594,
|
| 2400 |
+
"learning_rate": 3.888888888888889e-06,
|
| 2401 |
+
"loss": 0.7349,
|
| 2402 |
+
"step": 27900
|
| 2403 |
+
},
|
| 2404 |
+
{
|
| 2405 |
+
"epoch": 14.711677393931433,
|
| 2406 |
+
"grad_norm": 1.4593523740768433,
|
| 2407 |
+
"learning_rate": 3.7037037037037037e-06,
|
| 2408 |
+
"loss": 0.7327,
|
| 2409 |
+
"step": 28000
|
| 2410 |
+
},
|
| 2411 |
+
{
|
| 2412 |
+
"epoch": 14.711677393931433,
|
| 2413 |
+
"eval_loss": 0.842442512512207,
|
| 2414 |
+
"eval_runtime": 1.2608,
|
| 2415 |
+
"eval_samples_per_second": 7.931,
|
| 2416 |
+
"eval_steps_per_second": 3.966,
|
| 2417 |
+
"step": 28000
|
| 2418 |
+
},
|
| 2419 |
+
{
|
| 2420 |
+
"epoch": 14.76421909890976,
|
| 2421 |
+
"grad_norm": 1.1667600870132446,
|
| 2422 |
+
"learning_rate": 3.5185185185185187e-06,
|
| 2423 |
+
"loss": 0.7276,
|
| 2424 |
+
"step": 28100
|
| 2425 |
+
},
|
| 2426 |
+
{
|
| 2427 |
+
"epoch": 14.816760803888085,
|
| 2428 |
+
"grad_norm": 1.0612125396728516,
|
| 2429 |
+
"learning_rate": 3.3333333333333333e-06,
|
| 2430 |
+
"loss": 0.7468,
|
| 2431 |
+
"step": 28200
|
| 2432 |
+
},
|
| 2433 |
+
{
|
| 2434 |
+
"epoch": 14.869302508866413,
|
| 2435 |
+
"grad_norm": 1.117440938949585,
|
| 2436 |
+
"learning_rate": 3.148148148148148e-06,
|
| 2437 |
+
"loss": 0.7189,
|
| 2438 |
+
"step": 28300
|
| 2439 |
+
},
|
| 2440 |
+
{
|
| 2441 |
+
"epoch": 14.92184421384474,
|
| 2442 |
+
"grad_norm": 1.1088405847549438,
|
| 2443 |
+
"learning_rate": 2.9629629629629633e-06,
|
| 2444 |
+
"loss": 0.732,
|
| 2445 |
+
"step": 28400
|
| 2446 |
+
},
|
| 2447 |
+
{
|
| 2448 |
+
"epoch": 14.974385918823065,
|
| 2449 |
+
"grad_norm": 1.381748914718628,
|
| 2450 |
+
"learning_rate": 2.777777777777778e-06,
|
| 2451 |
+
"loss": 0.7368,
|
| 2452 |
+
"step": 28500
|
| 2453 |
+
},
|
| 2454 |
+
{
|
| 2455 |
+
"epoch": 14.974385918823065,
|
| 2456 |
+
"eval_loss": 0.844028651714325,
|
| 2457 |
+
"eval_runtime": 1.2451,
|
| 2458 |
+
"eval_samples_per_second": 8.031,
|
| 2459 |
+
"eval_steps_per_second": 4.016,
|
| 2460 |
+
"step": 28500
|
| 2461 |
+
},
|
| 2462 |
+
{
|
| 2463 |
+
"epoch": 15.026927623801392,
|
| 2464 |
+
"grad_norm": 1.2738327980041504,
|
| 2465 |
+
"learning_rate": 2.5925925925925925e-06,
|
| 2466 |
+
"loss": 0.7411,
|
| 2467 |
+
"step": 28600
|
| 2468 |
+
},
|
| 2469 |
+
{
|
| 2470 |
+
"epoch": 15.07946932877972,
|
| 2471 |
+
"grad_norm": 1.450596809387207,
|
| 2472 |
+
"learning_rate": 2.4074074074074075e-06,
|
| 2473 |
+
"loss": 0.721,
|
| 2474 |
+
"step": 28700
|
| 2475 |
+
},
|
| 2476 |
+
{
|
| 2477 |
+
"epoch": 15.132011033758046,
|
| 2478 |
+
"grad_norm": 1.2589495182037354,
|
| 2479 |
+
"learning_rate": 2.2222222222222225e-06,
|
| 2480 |
+
"loss": 0.7134,
|
| 2481 |
+
"step": 28800
|
| 2482 |
+
},
|
| 2483 |
+
{
|
| 2484 |
+
"epoch": 15.184552738736372,
|
| 2485 |
+
"grad_norm": 1.1227418184280396,
|
| 2486 |
+
"learning_rate": 2.0370370370370375e-06,
|
| 2487 |
+
"loss": 0.7361,
|
| 2488 |
+
"step": 28900
|
| 2489 |
+
},
|
| 2490 |
+
{
|
| 2491 |
+
"epoch": 15.237094443714698,
|
| 2492 |
+
"grad_norm": 1.1688610315322876,
|
| 2493 |
+
"learning_rate": 1.8518518518518519e-06,
|
| 2494 |
+
"loss": 0.722,
|
| 2495 |
+
"step": 29000
|
| 2496 |
+
},
|
| 2497 |
+
{
|
| 2498 |
+
"epoch": 15.237094443714698,
|
| 2499 |
+
"eval_loss": 0.8448740243911743,
|
| 2500 |
+
"eval_runtime": 1.2712,
|
| 2501 |
+
"eval_samples_per_second": 7.867,
|
| 2502 |
+
"eval_steps_per_second": 3.933,
|
| 2503 |
+
"step": 29000
|
| 2504 |
+
},
|
| 2505 |
+
{
|
| 2506 |
+
"epoch": 15.289636148693026,
|
| 2507 |
+
"grad_norm": 1.4582873582839966,
|
| 2508 |
+
"learning_rate": 1.6666666666666667e-06,
|
| 2509 |
+
"loss": 0.7236,
|
| 2510 |
+
"step": 29100
|
| 2511 |
+
},
|
| 2512 |
+
{
|
| 2513 |
+
"epoch": 15.342177853671352,
|
| 2514 |
+
"grad_norm": 1.5905903577804565,
|
| 2515 |
+
"learning_rate": 1.4814814814814817e-06,
|
| 2516 |
+
"loss": 0.7332,
|
| 2517 |
+
"step": 29200
|
| 2518 |
+
},
|
| 2519 |
+
{
|
| 2520 |
+
"epoch": 15.394719558649678,
|
| 2521 |
+
"grad_norm": 2.0454487800598145,
|
| 2522 |
+
"learning_rate": 1.2962962962962962e-06,
|
| 2523 |
+
"loss": 0.7222,
|
| 2524 |
+
"step": 29300
|
| 2525 |
+
},
|
| 2526 |
+
{
|
| 2527 |
+
"epoch": 15.447261263628004,
|
| 2528 |
+
"grad_norm": 1.3177134990692139,
|
| 2529 |
+
"learning_rate": 1.1111111111111112e-06,
|
| 2530 |
+
"loss": 0.7362,
|
| 2531 |
+
"step": 29400
|
| 2532 |
+
},
|
| 2533 |
+
{
|
| 2534 |
+
"epoch": 15.499802968606332,
|
| 2535 |
+
"grad_norm": 1.0010744333267212,
|
| 2536 |
+
"learning_rate": 9.259259259259259e-07,
|
| 2537 |
+
"loss": 0.7304,
|
| 2538 |
+
"step": 29500
|
| 2539 |
+
},
|
| 2540 |
+
{
|
| 2541 |
+
"epoch": 15.499802968606332,
|
| 2542 |
+
"eval_loss": 0.84196537733078,
|
| 2543 |
+
"eval_runtime": 1.2445,
|
| 2544 |
+
"eval_samples_per_second": 8.035,
|
| 2545 |
+
"eval_steps_per_second": 4.018,
|
| 2546 |
+
"step": 29500
|
| 2547 |
+
},
|
| 2548 |
+
{
|
| 2549 |
+
"epoch": 15.552344673584658,
|
| 2550 |
+
"grad_norm": 1.296751618385315,
|
| 2551 |
+
"learning_rate": 7.407407407407408e-07,
|
| 2552 |
+
"loss": 0.719,
|
| 2553 |
+
"step": 29600
|
| 2554 |
+
},
|
| 2555 |
+
{
|
| 2556 |
+
"epoch": 15.604886378562984,
|
| 2557 |
+
"grad_norm": 1.198317050933838,
|
| 2558 |
+
"learning_rate": 5.555555555555556e-07,
|
| 2559 |
+
"loss": 0.7359,
|
| 2560 |
+
"step": 29700
|
| 2561 |
+
},
|
| 2562 |
+
{
|
| 2563 |
+
"epoch": 15.65742808354131,
|
| 2564 |
+
"grad_norm": 1.3005775213241577,
|
| 2565 |
+
"learning_rate": 3.703703703703704e-07,
|
| 2566 |
+
"loss": 0.7268,
|
| 2567 |
+
"step": 29800
|
| 2568 |
+
},
|
| 2569 |
+
{
|
| 2570 |
+
"epoch": 15.709969788519638,
|
| 2571 |
+
"grad_norm": 1.1755659580230713,
|
| 2572 |
+
"learning_rate": 1.851851851851852e-07,
|
| 2573 |
+
"loss": 0.7266,
|
| 2574 |
+
"step": 29900
|
| 2575 |
+
},
|
| 2576 |
+
{
|
| 2577 |
+
"epoch": 15.762511493497964,
|
| 2578 |
+
"grad_norm": 1.1558780670166016,
|
| 2579 |
+
"learning_rate": 0.0,
|
| 2580 |
+
"loss": 0.7389,
|
| 2581 |
+
"step": 30000
|
| 2582 |
+
},
|
| 2583 |
+
{
|
| 2584 |
+
"epoch": 15.762511493497964,
|
| 2585 |
+
"eval_loss": 0.8437487483024597,
|
| 2586 |
+
"eval_runtime": 1.263,
|
| 2587 |
+
"eval_samples_per_second": 7.918,
|
| 2588 |
+
"eval_steps_per_second": 3.959,
|
| 2589 |
+
"step": 30000
|
| 2590 |
+
}
|
| 2591 |
+
],
|
| 2592 |
+
"logging_steps": 100,
|
| 2593 |
+
"max_steps": 30000,
|
| 2594 |
+
"num_input_tokens_seen": 0,
|
| 2595 |
+
"num_train_epochs": 16,
|
| 2596 |
+
"save_steps": 500,
|
| 2597 |
+
"stateful_callbacks": {
|
| 2598 |
+
"TrainerControl": {
|
| 2599 |
+
"args": {
|
| 2600 |
+
"should_epoch_stop": false,
|
| 2601 |
+
"should_evaluate": false,
|
| 2602 |
+
"should_log": false,
|
| 2603 |
+
"should_save": true,
|
| 2604 |
+
"should_training_stop": true
|
| 2605 |
+
},
|
| 2606 |
+
"attributes": {}
|
| 2607 |
+
}
|
| 2608 |
+
},
|
| 2609 |
+
"total_flos": 5.658737511387988e+18,
|
| 2610 |
+
"train_batch_size": 2,
|
| 2611 |
+
"trial_name": null,
|
| 2612 |
+
"trial_params": null
|
| 2613 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1fed3b6ffc0e1aa2e3544015af517ce809f0eaebfa074858f7c9a516e07a079a
|
| 3 |
+
size 5304
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|