Training in progress, step 2500, checkpoint
Browse files- checkpoint-2500/README.md +202 -0
- checkpoint-2500/adapter_config.json +37 -0
- checkpoint-2500/adapter_model.safetensors +3 -0
- checkpoint-2500/added_tokens.json +5 -0
- checkpoint-2500/merges.txt +0 -0
- checkpoint-2500/optimizer.pt +3 -0
- checkpoint-2500/rng_state.pth +3 -0
- checkpoint-2500/scheduler.pt +3 -0
- checkpoint-2500/special_tokens_map.json +14 -0
- checkpoint-2500/tokenizer.json +3 -0
- checkpoint-2500/tokenizer_config.json +44 -0
- checkpoint-2500/trainer_state.json +2183 -0
- checkpoint-2500/training_args.bin +3 -0
- checkpoint-2500/vocab.json +0 -0
checkpoint-2500/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: Qwen/Qwen2-7B-Instruct
|
| 3 |
+
library_name: peft
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.14.0
|
checkpoint-2500/adapter_config.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "Qwen/Qwen2-7B-Instruct",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"eva_config": null,
|
| 7 |
+
"exclude_modules": null,
|
| 8 |
+
"fan_in_fan_out": false,
|
| 9 |
+
"inference_mode": true,
|
| 10 |
+
"init_lora_weights": true,
|
| 11 |
+
"layer_replication": null,
|
| 12 |
+
"layers_pattern": null,
|
| 13 |
+
"layers_to_transform": null,
|
| 14 |
+
"loftq_config": {},
|
| 15 |
+
"lora_alpha": 32,
|
| 16 |
+
"lora_bias": false,
|
| 17 |
+
"lora_dropout": 0.05,
|
| 18 |
+
"megatron_config": null,
|
| 19 |
+
"megatron_core": "megatron.core",
|
| 20 |
+
"modules_to_save": null,
|
| 21 |
+
"peft_type": "LORA",
|
| 22 |
+
"r": 16,
|
| 23 |
+
"rank_pattern": {},
|
| 24 |
+
"revision": null,
|
| 25 |
+
"target_modules": [
|
| 26 |
+
"up_proj",
|
| 27 |
+
"gate_proj",
|
| 28 |
+
"v_proj",
|
| 29 |
+
"down_proj",
|
| 30 |
+
"o_proj",
|
| 31 |
+
"q_proj",
|
| 32 |
+
"k_proj"
|
| 33 |
+
],
|
| 34 |
+
"task_type": "CAUSAL_LM",
|
| 35 |
+
"use_dora": false,
|
| 36 |
+
"use_rslora": false
|
| 37 |
+
}
|
checkpoint-2500/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d6bee7dba4bf9059d5a5b2079f0c75b3df7c0efc89715e14e294896a5b2c0348
|
| 3 |
+
size 161533192
|
checkpoint-2500/added_tokens.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<|endoftext|>": 151643,
|
| 3 |
+
"<|im_end|>": 151645,
|
| 4 |
+
"<|im_start|>": 151644
|
| 5 |
+
}
|
checkpoint-2500/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-2500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cad332a5a304062c0ca2481307682a4f468ac53c63aed0537b1dec42f15a600b
|
| 3 |
+
size 323290986
|
checkpoint-2500/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:88e6e9c0a0ea7115196a581deaa2b648dde6e45af0eabd9d9c1fba35762f90df
|
| 3 |
+
size 14244
|
checkpoint-2500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5f53712620b0753482220e3a4366330dbb729a9bd0885bfc4cbba925e9c14c00
|
| 3 |
+
size 1064
|
checkpoint-2500/special_tokens_map.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "<|im_end|>"
|
| 14 |
+
}
|
checkpoint-2500/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:79faeb53ce66e372f424aa1072c822bd68c71927fb82a2c639b8120026616df5
|
| 3 |
+
size 11418364
|
checkpoint-2500/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 |
+
"extra_special_tokens": {},
|
| 39 |
+
"model_max_length": 131072,
|
| 40 |
+
"pad_token": "<|im_end|>",
|
| 41 |
+
"split_special_tokens": false,
|
| 42 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 43 |
+
"unk_token": null
|
| 44 |
+
}
|
checkpoint-2500/trainer_state.json
ADDED
|
@@ -0,0 +1,2183 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.6511134676564154,
|
| 5 |
+
"eval_steps": 50,
|
| 6 |
+
"global_step": 2500,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.010604453870625663,
|
| 13 |
+
"grad_norm": 2.0663416385650635,
|
| 14 |
+
"learning_rate": 4.982325910215624e-05,
|
| 15 |
+
"loss": 1.91,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.021208907741251327,
|
| 20 |
+
"grad_norm": 0.7459995746612549,
|
| 21 |
+
"learning_rate": 4.964651820431248e-05,
|
| 22 |
+
"loss": 1.0094,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.031813361611876985,
|
| 27 |
+
"grad_norm": 0.656954824924469,
|
| 28 |
+
"learning_rate": 4.946977730646872e-05,
|
| 29 |
+
"loss": 0.8052,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.042417815482502653,
|
| 34 |
+
"grad_norm": 0.7273707389831543,
|
| 35 |
+
"learning_rate": 4.929303640862496e-05,
|
| 36 |
+
"loss": 0.7145,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.053022269353128315,
|
| 41 |
+
"grad_norm": 0.6689164042472839,
|
| 42 |
+
"learning_rate": 4.91162955107812e-05,
|
| 43 |
+
"loss": 0.6797,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.053022269353128315,
|
| 48 |
+
"eval_loss": 0.8142186403274536,
|
| 49 |
+
"eval_runtime": 11.794,
|
| 50 |
+
"eval_samples_per_second": 40.699,
|
| 51 |
+
"eval_steps_per_second": 2.544,
|
| 52 |
+
"step": 50
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.06362672322375397,
|
| 56 |
+
"grad_norm": 0.6781293749809265,
|
| 57 |
+
"learning_rate": 4.893955461293744e-05,
|
| 58 |
+
"loss": 0.6249,
|
| 59 |
+
"step": 60
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.07423117709437964,
|
| 63 |
+
"grad_norm": 0.6776543259620667,
|
| 64 |
+
"learning_rate": 4.876281371509368e-05,
|
| 65 |
+
"loss": 0.612,
|
| 66 |
+
"step": 70
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.08483563096500531,
|
| 70 |
+
"grad_norm": 0.7603946924209595,
|
| 71 |
+
"learning_rate": 4.858607281724991e-05,
|
| 72 |
+
"loss": 0.5998,
|
| 73 |
+
"step": 80
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.09544008483563096,
|
| 77 |
+
"grad_norm": 0.7581377029418945,
|
| 78 |
+
"learning_rate": 4.8409331919406155e-05,
|
| 79 |
+
"loss": 0.6032,
|
| 80 |
+
"step": 90
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.10604453870625663,
|
| 84 |
+
"grad_norm": 0.7402133345603943,
|
| 85 |
+
"learning_rate": 4.823259102156239e-05,
|
| 86 |
+
"loss": 0.5912,
|
| 87 |
+
"step": 100
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.10604453870625663,
|
| 91 |
+
"eval_loss": 0.7294260859489441,
|
| 92 |
+
"eval_runtime": 11.8272,
|
| 93 |
+
"eval_samples_per_second": 40.585,
|
| 94 |
+
"eval_steps_per_second": 2.537,
|
| 95 |
+
"step": 100
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.11664899257688228,
|
| 99 |
+
"grad_norm": 0.8224169015884399,
|
| 100 |
+
"learning_rate": 4.8055850123718633e-05,
|
| 101 |
+
"loss": 0.578,
|
| 102 |
+
"step": 110
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.12725344644750794,
|
| 106 |
+
"grad_norm": 0.7843881249427795,
|
| 107 |
+
"learning_rate": 4.7879109225874866e-05,
|
| 108 |
+
"loss": 0.5751,
|
| 109 |
+
"step": 120
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.1378579003181336,
|
| 113 |
+
"grad_norm": 0.772152304649353,
|
| 114 |
+
"learning_rate": 4.770236832803111e-05,
|
| 115 |
+
"loss": 0.5471,
|
| 116 |
+
"step": 130
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.14846235418875928,
|
| 120 |
+
"grad_norm": 0.6972452998161316,
|
| 121 |
+
"learning_rate": 4.7525627430187344e-05,
|
| 122 |
+
"loss": 0.5516,
|
| 123 |
+
"step": 140
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.15906680805938495,
|
| 127 |
+
"grad_norm": 0.7806265354156494,
|
| 128 |
+
"learning_rate": 4.734888653234359e-05,
|
| 129 |
+
"loss": 0.5263,
|
| 130 |
+
"step": 150
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.15906680805938495,
|
| 134 |
+
"eval_loss": 0.6928939819335938,
|
| 135 |
+
"eval_runtime": 11.8093,
|
| 136 |
+
"eval_samples_per_second": 40.646,
|
| 137 |
+
"eval_steps_per_second": 2.54,
|
| 138 |
+
"step": 150
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.16967126193001061,
|
| 142 |
+
"grad_norm": 0.7372023463249207,
|
| 143 |
+
"learning_rate": 4.717214563449982e-05,
|
| 144 |
+
"loss": 0.5715,
|
| 145 |
+
"step": 160
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.18027571580063625,
|
| 149 |
+
"grad_norm": 0.8236038684844971,
|
| 150 |
+
"learning_rate": 4.699540473665606e-05,
|
| 151 |
+
"loss": 0.4987,
|
| 152 |
+
"step": 170
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.19088016967126192,
|
| 156 |
+
"grad_norm": 0.8057310581207275,
|
| 157 |
+
"learning_rate": 4.681866383881231e-05,
|
| 158 |
+
"loss": 0.5097,
|
| 159 |
+
"step": 180
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.2014846235418876,
|
| 163 |
+
"grad_norm": 0.7124797105789185,
|
| 164 |
+
"learning_rate": 4.664192294096854e-05,
|
| 165 |
+
"loss": 0.4952,
|
| 166 |
+
"step": 190
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 0.21208907741251326,
|
| 170 |
+
"grad_norm": 0.7755710482597351,
|
| 171 |
+
"learning_rate": 4.6465182043124786e-05,
|
| 172 |
+
"loss": 0.497,
|
| 173 |
+
"step": 200
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 0.21208907741251326,
|
| 177 |
+
"eval_loss": 0.6748186349868774,
|
| 178 |
+
"eval_runtime": 11.8077,
|
| 179 |
+
"eval_samples_per_second": 40.651,
|
| 180 |
+
"eval_steps_per_second": 2.541,
|
| 181 |
+
"step": 200
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.22269353128313893,
|
| 185 |
+
"grad_norm": 0.912337064743042,
|
| 186 |
+
"learning_rate": 4.628844114528102e-05,
|
| 187 |
+
"loss": 0.4997,
|
| 188 |
+
"step": 210
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.23329798515376457,
|
| 192 |
+
"grad_norm": 0.771654486656189,
|
| 193 |
+
"learning_rate": 4.6111700247437265e-05,
|
| 194 |
+
"loss": 0.5027,
|
| 195 |
+
"step": 220
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.24390243902439024,
|
| 199 |
+
"grad_norm": 0.8241815567016602,
|
| 200 |
+
"learning_rate": 4.59349593495935e-05,
|
| 201 |
+
"loss": 0.5196,
|
| 202 |
+
"step": 230
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.2545068928950159,
|
| 206 |
+
"grad_norm": 0.7876004576683044,
|
| 207 |
+
"learning_rate": 4.5758218451749736e-05,
|
| 208 |
+
"loss": 0.4791,
|
| 209 |
+
"step": 240
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.2651113467656416,
|
| 213 |
+
"grad_norm": 0.7941911816596985,
|
| 214 |
+
"learning_rate": 4.5581477553905975e-05,
|
| 215 |
+
"loss": 0.5078,
|
| 216 |
+
"step": 250
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 0.2651113467656416,
|
| 220 |
+
"eval_loss": 0.653518795967102,
|
| 221 |
+
"eval_runtime": 11.7906,
|
| 222 |
+
"eval_samples_per_second": 40.71,
|
| 223 |
+
"eval_steps_per_second": 2.544,
|
| 224 |
+
"step": 250
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.2757158006362672,
|
| 228 |
+
"grad_norm": 0.8866105079650879,
|
| 229 |
+
"learning_rate": 4.5404736656062215e-05,
|
| 230 |
+
"loss": 0.477,
|
| 231 |
+
"step": 260
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.2863202545068929,
|
| 235 |
+
"grad_norm": 0.8498968482017517,
|
| 236 |
+
"learning_rate": 4.5227995758218454e-05,
|
| 237 |
+
"loss": 0.4926,
|
| 238 |
+
"step": 270
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 0.29692470837751855,
|
| 242 |
+
"grad_norm": 0.8863232135772705,
|
| 243 |
+
"learning_rate": 4.505125486037469e-05,
|
| 244 |
+
"loss": 0.463,
|
| 245 |
+
"step": 280
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 0.3075291622481442,
|
| 249 |
+
"grad_norm": 0.9501034021377563,
|
| 250 |
+
"learning_rate": 4.487451396253093e-05,
|
| 251 |
+
"loss": 0.4809,
|
| 252 |
+
"step": 290
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 0.3181336161187699,
|
| 256 |
+
"grad_norm": 0.7933001518249512,
|
| 257 |
+
"learning_rate": 4.469777306468717e-05,
|
| 258 |
+
"loss": 0.4941,
|
| 259 |
+
"step": 300
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 0.3181336161187699,
|
| 263 |
+
"eval_loss": 0.6434358954429626,
|
| 264 |
+
"eval_runtime": 11.7969,
|
| 265 |
+
"eval_samples_per_second": 40.689,
|
| 266 |
+
"eval_steps_per_second": 2.543,
|
| 267 |
+
"step": 300
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.32873806998939553,
|
| 271 |
+
"grad_norm": 0.9145284295082092,
|
| 272 |
+
"learning_rate": 4.452103216684341e-05,
|
| 273 |
+
"loss": 0.5235,
|
| 274 |
+
"step": 310
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.33934252386002123,
|
| 278 |
+
"grad_norm": 0.8557764887809753,
|
| 279 |
+
"learning_rate": 4.434429126899965e-05,
|
| 280 |
+
"loss": 0.4809,
|
| 281 |
+
"step": 320
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 0.34994697773064687,
|
| 285 |
+
"grad_norm": 0.8337067365646362,
|
| 286 |
+
"learning_rate": 4.416755037115589e-05,
|
| 287 |
+
"loss": 0.4764,
|
| 288 |
+
"step": 330
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 0.3605514316012725,
|
| 292 |
+
"grad_norm": 0.8928807377815247,
|
| 293 |
+
"learning_rate": 4.399080947331213e-05,
|
| 294 |
+
"loss": 0.4634,
|
| 295 |
+
"step": 340
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 0.3711558854718982,
|
| 299 |
+
"grad_norm": 0.7639658451080322,
|
| 300 |
+
"learning_rate": 4.381406857546837e-05,
|
| 301 |
+
"loss": 0.4829,
|
| 302 |
+
"step": 350
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.3711558854718982,
|
| 306 |
+
"eval_loss": 0.6269502639770508,
|
| 307 |
+
"eval_runtime": 11.7838,
|
| 308 |
+
"eval_samples_per_second": 40.734,
|
| 309 |
+
"eval_steps_per_second": 2.546,
|
| 310 |
+
"step": 350
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.38176033934252385,
|
| 314 |
+
"grad_norm": 0.8374601006507874,
|
| 315 |
+
"learning_rate": 4.3637327677624606e-05,
|
| 316 |
+
"loss": 0.471,
|
| 317 |
+
"step": 360
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.39236479321314954,
|
| 321 |
+
"grad_norm": 0.9471817016601562,
|
| 322 |
+
"learning_rate": 4.3460586779780846e-05,
|
| 323 |
+
"loss": 0.4528,
|
| 324 |
+
"step": 370
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.4029692470837752,
|
| 328 |
+
"grad_norm": 0.8860051035881042,
|
| 329 |
+
"learning_rate": 4.328384588193708e-05,
|
| 330 |
+
"loss": 0.4684,
|
| 331 |
+
"step": 380
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.4135737009544008,
|
| 335 |
+
"grad_norm": 0.9099433422088623,
|
| 336 |
+
"learning_rate": 4.3107104984093324e-05,
|
| 337 |
+
"loss": 0.4294,
|
| 338 |
+
"step": 390
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.4241781548250265,
|
| 342 |
+
"grad_norm": 0.792826771736145,
|
| 343 |
+
"learning_rate": 4.2930364086249556e-05,
|
| 344 |
+
"loss": 0.4597,
|
| 345 |
+
"step": 400
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.4241781548250265,
|
| 349 |
+
"eval_loss": 0.6197967529296875,
|
| 350 |
+
"eval_runtime": 11.8062,
|
| 351 |
+
"eval_samples_per_second": 40.657,
|
| 352 |
+
"eval_steps_per_second": 2.541,
|
| 353 |
+
"step": 400
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.43478260869565216,
|
| 357 |
+
"grad_norm": 0.8295171856880188,
|
| 358 |
+
"learning_rate": 4.27536231884058e-05,
|
| 359 |
+
"loss": 0.4842,
|
| 360 |
+
"step": 410
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.44538706256627786,
|
| 364 |
+
"grad_norm": 0.9126204252243042,
|
| 365 |
+
"learning_rate": 4.2576882290562035e-05,
|
| 366 |
+
"loss": 0.4688,
|
| 367 |
+
"step": 420
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.4559915164369035,
|
| 371 |
+
"grad_norm": 0.9485805630683899,
|
| 372 |
+
"learning_rate": 4.240014139271828e-05,
|
| 373 |
+
"loss": 0.4803,
|
| 374 |
+
"step": 430
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.46659597030752914,
|
| 378 |
+
"grad_norm": 0.8756628036499023,
|
| 379 |
+
"learning_rate": 4.222340049487451e-05,
|
| 380 |
+
"loss": 0.4572,
|
| 381 |
+
"step": 440
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.47720042417815484,
|
| 385 |
+
"grad_norm": 0.907244086265564,
|
| 386 |
+
"learning_rate": 4.204665959703076e-05,
|
| 387 |
+
"loss": 0.4394,
|
| 388 |
+
"step": 450
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.47720042417815484,
|
| 392 |
+
"eval_loss": 0.6146622896194458,
|
| 393 |
+
"eval_runtime": 11.8005,
|
| 394 |
+
"eval_samples_per_second": 40.676,
|
| 395 |
+
"eval_steps_per_second": 2.542,
|
| 396 |
+
"step": 450
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.4878048780487805,
|
| 400 |
+
"grad_norm": 0.9201627969741821,
|
| 401 |
+
"learning_rate": 4.186991869918699e-05,
|
| 402 |
+
"loss": 0.4294,
|
| 403 |
+
"step": 460
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 0.4984093319194062,
|
| 407 |
+
"grad_norm": 0.9242031574249268,
|
| 408 |
+
"learning_rate": 4.169317780134323e-05,
|
| 409 |
+
"loss": 0.4335,
|
| 410 |
+
"step": 470
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.5090137857900318,
|
| 414 |
+
"grad_norm": 0.840977132320404,
|
| 415 |
+
"learning_rate": 4.151643690349947e-05,
|
| 416 |
+
"loss": 0.4639,
|
| 417 |
+
"step": 480
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.5196182396606575,
|
| 421 |
+
"grad_norm": 0.9487953782081604,
|
| 422 |
+
"learning_rate": 4.133969600565571e-05,
|
| 423 |
+
"loss": 0.4173,
|
| 424 |
+
"step": 490
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 0.5302226935312832,
|
| 428 |
+
"grad_norm": 0.8343156576156616,
|
| 429 |
+
"learning_rate": 4.116295510781195e-05,
|
| 430 |
+
"loss": 0.4647,
|
| 431 |
+
"step": 500
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 0.5302226935312832,
|
| 435 |
+
"eval_loss": 0.6104319095611572,
|
| 436 |
+
"eval_runtime": 11.8139,
|
| 437 |
+
"eval_samples_per_second": 40.63,
|
| 438 |
+
"eval_steps_per_second": 2.539,
|
| 439 |
+
"step": 500
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 0.5408271474019088,
|
| 443 |
+
"grad_norm": 0.9216362237930298,
|
| 444 |
+
"learning_rate": 4.098621420996819e-05,
|
| 445 |
+
"loss": 0.4499,
|
| 446 |
+
"step": 510
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 0.5514316012725344,
|
| 450 |
+
"grad_norm": 0.957593560218811,
|
| 451 |
+
"learning_rate": 4.080947331212443e-05,
|
| 452 |
+
"loss": 0.4202,
|
| 453 |
+
"step": 520
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.5620360551431601,
|
| 457 |
+
"grad_norm": 1.0103106498718262,
|
| 458 |
+
"learning_rate": 4.0632732414280666e-05,
|
| 459 |
+
"loss": 0.4315,
|
| 460 |
+
"step": 530
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 0.5726405090137858,
|
| 464 |
+
"grad_norm": 1.0909500122070312,
|
| 465 |
+
"learning_rate": 4.0455991516436905e-05,
|
| 466 |
+
"loss": 0.4476,
|
| 467 |
+
"step": 540
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 0.5832449628844114,
|
| 471 |
+
"grad_norm": 0.8890084028244019,
|
| 472 |
+
"learning_rate": 4.0279250618593144e-05,
|
| 473 |
+
"loss": 0.4408,
|
| 474 |
+
"step": 550
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.5832449628844114,
|
| 478 |
+
"eval_loss": 0.6050440073013306,
|
| 479 |
+
"eval_runtime": 11.7965,
|
| 480 |
+
"eval_samples_per_second": 40.69,
|
| 481 |
+
"eval_steps_per_second": 2.543,
|
| 482 |
+
"step": 550
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 0.5938494167550371,
|
| 486 |
+
"grad_norm": 1.038818359375,
|
| 487 |
+
"learning_rate": 4.0102509720749383e-05,
|
| 488 |
+
"loss": 0.4529,
|
| 489 |
+
"step": 560
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.6044538706256628,
|
| 493 |
+
"grad_norm": 1.0575263500213623,
|
| 494 |
+
"learning_rate": 3.992576882290562e-05,
|
| 495 |
+
"loss": 0.4409,
|
| 496 |
+
"step": 570
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 0.6150583244962884,
|
| 500 |
+
"grad_norm": 0.9827993512153625,
|
| 501 |
+
"learning_rate": 3.974902792506186e-05,
|
| 502 |
+
"loss": 0.4132,
|
| 503 |
+
"step": 580
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 0.6256627783669141,
|
| 507 |
+
"grad_norm": 0.9469496011734009,
|
| 508 |
+
"learning_rate": 3.95722870272181e-05,
|
| 509 |
+
"loss": 0.4075,
|
| 510 |
+
"step": 590
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 0.6362672322375398,
|
| 514 |
+
"grad_norm": 0.9693032503128052,
|
| 515 |
+
"learning_rate": 3.939554612937434e-05,
|
| 516 |
+
"loss": 0.4533,
|
| 517 |
+
"step": 600
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"epoch": 0.6362672322375398,
|
| 521 |
+
"eval_loss": 0.5991437435150146,
|
| 522 |
+
"eval_runtime": 11.8081,
|
| 523 |
+
"eval_samples_per_second": 40.65,
|
| 524 |
+
"eval_steps_per_second": 2.541,
|
| 525 |
+
"step": 600
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.6468716861081655,
|
| 529 |
+
"grad_norm": 0.9771609306335449,
|
| 530 |
+
"learning_rate": 3.921880523153057e-05,
|
| 531 |
+
"loss": 0.4275,
|
| 532 |
+
"step": 610
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 0.6574761399787911,
|
| 536 |
+
"grad_norm": 0.9394034743309021,
|
| 537 |
+
"learning_rate": 3.904206433368682e-05,
|
| 538 |
+
"loss": 0.4066,
|
| 539 |
+
"step": 620
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 0.6680805938494168,
|
| 543 |
+
"grad_norm": 0.885517954826355,
|
| 544 |
+
"learning_rate": 3.886532343584305e-05,
|
| 545 |
+
"loss": 0.4071,
|
| 546 |
+
"step": 630
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 0.6786850477200425,
|
| 550 |
+
"grad_norm": 0.9775238633155823,
|
| 551 |
+
"learning_rate": 3.86885825379993e-05,
|
| 552 |
+
"loss": 0.4234,
|
| 553 |
+
"step": 640
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 0.689289501590668,
|
| 557 |
+
"grad_norm": 0.9256358742713928,
|
| 558 |
+
"learning_rate": 3.851184164015553e-05,
|
| 559 |
+
"loss": 0.4186,
|
| 560 |
+
"step": 650
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 0.689289501590668,
|
| 564 |
+
"eval_loss": 0.5974680781364441,
|
| 565 |
+
"eval_runtime": 11.8062,
|
| 566 |
+
"eval_samples_per_second": 40.657,
|
| 567 |
+
"eval_steps_per_second": 2.541,
|
| 568 |
+
"step": 650
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 0.6998939554612937,
|
| 572 |
+
"grad_norm": 0.9220837354660034,
|
| 573 |
+
"learning_rate": 3.8335100742311775e-05,
|
| 574 |
+
"loss": 0.4264,
|
| 575 |
+
"step": 660
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 0.7104984093319194,
|
| 579 |
+
"grad_norm": 1.0769790410995483,
|
| 580 |
+
"learning_rate": 3.8158359844468015e-05,
|
| 581 |
+
"loss": 0.4166,
|
| 582 |
+
"step": 670
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 0.721102863202545,
|
| 586 |
+
"grad_norm": 0.9368733763694763,
|
| 587 |
+
"learning_rate": 3.7981618946624254e-05,
|
| 588 |
+
"loss": 0.4296,
|
| 589 |
+
"step": 680
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 0.7317073170731707,
|
| 593 |
+
"grad_norm": 1.0023365020751953,
|
| 594 |
+
"learning_rate": 3.780487804878049e-05,
|
| 595 |
+
"loss": 0.4534,
|
| 596 |
+
"step": 690
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 0.7423117709437964,
|
| 600 |
+
"grad_norm": 1.062111258506775,
|
| 601 |
+
"learning_rate": 3.7628137150936725e-05,
|
| 602 |
+
"loss": 0.4378,
|
| 603 |
+
"step": 700
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 0.7423117709437964,
|
| 607 |
+
"eval_loss": 0.5889919400215149,
|
| 608 |
+
"eval_runtime": 11.8116,
|
| 609 |
+
"eval_samples_per_second": 40.638,
|
| 610 |
+
"eval_steps_per_second": 2.54,
|
| 611 |
+
"step": 700
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.7529162248144221,
|
| 615 |
+
"grad_norm": 1.0798842906951904,
|
| 616 |
+
"learning_rate": 3.745139625309297e-05,
|
| 617 |
+
"loss": 0.4168,
|
| 618 |
+
"step": 710
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.7635206786850477,
|
| 622 |
+
"grad_norm": 1.0573209524154663,
|
| 623 |
+
"learning_rate": 3.7274655355249204e-05,
|
| 624 |
+
"loss": 0.4244,
|
| 625 |
+
"step": 720
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.7741251325556734,
|
| 629 |
+
"grad_norm": 0.9914817810058594,
|
| 630 |
+
"learning_rate": 3.709791445740545e-05,
|
| 631 |
+
"loss": 0.4332,
|
| 632 |
+
"step": 730
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.7847295864262991,
|
| 636 |
+
"grad_norm": 1.0201358795166016,
|
| 637 |
+
"learning_rate": 3.692117355956168e-05,
|
| 638 |
+
"loss": 0.4225,
|
| 639 |
+
"step": 740
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.7953340402969247,
|
| 643 |
+
"grad_norm": 1.011526346206665,
|
| 644 |
+
"learning_rate": 3.674443266171793e-05,
|
| 645 |
+
"loss": 0.4069,
|
| 646 |
+
"step": 750
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.7953340402969247,
|
| 650 |
+
"eval_loss": 0.5948487520217896,
|
| 651 |
+
"eval_runtime": 11.8194,
|
| 652 |
+
"eval_samples_per_second": 40.611,
|
| 653 |
+
"eval_steps_per_second": 2.538,
|
| 654 |
+
"step": 750
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.8059384941675504,
|
| 658 |
+
"grad_norm": 0.9645175933837891,
|
| 659 |
+
"learning_rate": 3.656769176387416e-05,
|
| 660 |
+
"loss": 0.3833,
|
| 661 |
+
"step": 760
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.8165429480381761,
|
| 665 |
+
"grad_norm": 0.9826123118400574,
|
| 666 |
+
"learning_rate": 3.63909508660304e-05,
|
| 667 |
+
"loss": 0.4019,
|
| 668 |
+
"step": 770
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.8271474019088016,
|
| 672 |
+
"grad_norm": 0.957275927066803,
|
| 673 |
+
"learning_rate": 3.621420996818664e-05,
|
| 674 |
+
"loss": 0.4083,
|
| 675 |
+
"step": 780
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.8377518557794273,
|
| 679 |
+
"grad_norm": 1.0057812929153442,
|
| 680 |
+
"learning_rate": 3.603746907034288e-05,
|
| 681 |
+
"loss": 0.4218,
|
| 682 |
+
"step": 790
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.848356309650053,
|
| 686 |
+
"grad_norm": 1.0474872589111328,
|
| 687 |
+
"learning_rate": 3.586072817249912e-05,
|
| 688 |
+
"loss": 0.4224,
|
| 689 |
+
"step": 800
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.848356309650053,
|
| 693 |
+
"eval_loss": 0.5902166962623596,
|
| 694 |
+
"eval_runtime": 11.8122,
|
| 695 |
+
"eval_samples_per_second": 40.636,
|
| 696 |
+
"eval_steps_per_second": 2.54,
|
| 697 |
+
"step": 800
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.8589607635206787,
|
| 701 |
+
"grad_norm": 1.1121183633804321,
|
| 702 |
+
"learning_rate": 3.5683987274655356e-05,
|
| 703 |
+
"loss": 0.4035,
|
| 704 |
+
"step": 810
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.8695652173913043,
|
| 708 |
+
"grad_norm": 1.078808069229126,
|
| 709 |
+
"learning_rate": 3.5507246376811596e-05,
|
| 710 |
+
"loss": 0.3987,
|
| 711 |
+
"step": 820
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.88016967126193,
|
| 715 |
+
"grad_norm": 0.9879220724105835,
|
| 716 |
+
"learning_rate": 3.5330505478967835e-05,
|
| 717 |
+
"loss": 0.4107,
|
| 718 |
+
"step": 830
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 0.8907741251325557,
|
| 722 |
+
"grad_norm": 1.0545059442520142,
|
| 723 |
+
"learning_rate": 3.5153764581124074e-05,
|
| 724 |
+
"loss": 0.412,
|
| 725 |
+
"step": 840
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 0.9013785790031813,
|
| 729 |
+
"grad_norm": 1.0051729679107666,
|
| 730 |
+
"learning_rate": 3.497702368328031e-05,
|
| 731 |
+
"loss": 0.3962,
|
| 732 |
+
"step": 850
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 0.9013785790031813,
|
| 736 |
+
"eval_loss": 0.586068868637085,
|
| 737 |
+
"eval_runtime": 11.7963,
|
| 738 |
+
"eval_samples_per_second": 40.691,
|
| 739 |
+
"eval_steps_per_second": 2.543,
|
| 740 |
+
"step": 850
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 0.911983032873807,
|
| 744 |
+
"grad_norm": 1.0309350490570068,
|
| 745 |
+
"learning_rate": 3.480028278543655e-05,
|
| 746 |
+
"loss": 0.405,
|
| 747 |
+
"step": 860
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.9225874867444327,
|
| 751 |
+
"grad_norm": 1.063778281211853,
|
| 752 |
+
"learning_rate": 3.462354188759279e-05,
|
| 753 |
+
"loss": 0.4034,
|
| 754 |
+
"step": 870
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 0.9331919406150583,
|
| 758 |
+
"grad_norm": 1.0570268630981445,
|
| 759 |
+
"learning_rate": 3.444680098974903e-05,
|
| 760 |
+
"loss": 0.4038,
|
| 761 |
+
"step": 880
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 0.943796394485684,
|
| 765 |
+
"grad_norm": 1.0920844078063965,
|
| 766 |
+
"learning_rate": 3.427006009190527e-05,
|
| 767 |
+
"loss": 0.3996,
|
| 768 |
+
"step": 890
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 0.9544008483563097,
|
| 772 |
+
"grad_norm": 0.9112839698791504,
|
| 773 |
+
"learning_rate": 3.409331919406151e-05,
|
| 774 |
+
"loss": 0.3855,
|
| 775 |
+
"step": 900
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 0.9544008483563097,
|
| 779 |
+
"eval_loss": 0.5862192511558533,
|
| 780 |
+
"eval_runtime": 11.7865,
|
| 781 |
+
"eval_samples_per_second": 40.725,
|
| 782 |
+
"eval_steps_per_second": 2.545,
|
| 783 |
+
"step": 900
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 0.9650053022269353,
|
| 787 |
+
"grad_norm": 1.0250121355056763,
|
| 788 |
+
"learning_rate": 3.391657829621775e-05,
|
| 789 |
+
"loss": 0.4219,
|
| 790 |
+
"step": 910
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 0.975609756097561,
|
| 794 |
+
"grad_norm": 1.045753836631775,
|
| 795 |
+
"learning_rate": 3.373983739837399e-05,
|
| 796 |
+
"loss": 0.3936,
|
| 797 |
+
"step": 920
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 0.9862142099681867,
|
| 801 |
+
"grad_norm": 1.0251036882400513,
|
| 802 |
+
"learning_rate": 3.356309650053022e-05,
|
| 803 |
+
"loss": 0.3798,
|
| 804 |
+
"step": 930
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 0.9968186638388123,
|
| 808 |
+
"grad_norm": 1.0625455379486084,
|
| 809 |
+
"learning_rate": 3.3386355602686466e-05,
|
| 810 |
+
"loss": 0.3779,
|
| 811 |
+
"step": 940
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 1.007423117709438,
|
| 815 |
+
"grad_norm": 1.050057291984558,
|
| 816 |
+
"learning_rate": 3.32096147048427e-05,
|
| 817 |
+
"loss": 0.3676,
|
| 818 |
+
"step": 950
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 1.007423117709438,
|
| 822 |
+
"eval_loss": 0.5891817212104797,
|
| 823 |
+
"eval_runtime": 11.7414,
|
| 824 |
+
"eval_samples_per_second": 40.881,
|
| 825 |
+
"eval_steps_per_second": 2.555,
|
| 826 |
+
"step": 950
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 1.0180275715800637,
|
| 830 |
+
"grad_norm": 1.109527826309204,
|
| 831 |
+
"learning_rate": 3.3032873806998944e-05,
|
| 832 |
+
"loss": 0.3532,
|
| 833 |
+
"step": 960
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 1.0286320254506893,
|
| 837 |
+
"grad_norm": 1.2735576629638672,
|
| 838 |
+
"learning_rate": 3.285613290915518e-05,
|
| 839 |
+
"loss": 0.3804,
|
| 840 |
+
"step": 970
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 1.039236479321315,
|
| 844 |
+
"grad_norm": 1.079765796661377,
|
| 845 |
+
"learning_rate": 3.267939201131142e-05,
|
| 846 |
+
"loss": 0.352,
|
| 847 |
+
"step": 980
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 1.0498409331919407,
|
| 851 |
+
"grad_norm": 1.069228172302246,
|
| 852 |
+
"learning_rate": 3.2502651113467655e-05,
|
| 853 |
+
"loss": 0.3402,
|
| 854 |
+
"step": 990
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 1.0604453870625663,
|
| 858 |
+
"grad_norm": 1.2578569650650024,
|
| 859 |
+
"learning_rate": 3.2325910215623894e-05,
|
| 860 |
+
"loss": 0.3541,
|
| 861 |
+
"step": 1000
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 1.0604453870625663,
|
| 865 |
+
"eval_loss": 0.5981893539428711,
|
| 866 |
+
"eval_runtime": 11.7382,
|
| 867 |
+
"eval_samples_per_second": 40.892,
|
| 868 |
+
"eval_steps_per_second": 2.556,
|
| 869 |
+
"step": 1000
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 1.0710498409331919,
|
| 873 |
+
"grad_norm": 1.1604409217834473,
|
| 874 |
+
"learning_rate": 3.2149169317780133e-05,
|
| 875 |
+
"loss": 0.3274,
|
| 876 |
+
"step": 1010
|
| 877 |
+
},
|
| 878 |
+
{
|
| 879 |
+
"epoch": 1.0816542948038177,
|
| 880 |
+
"grad_norm": 1.135129690170288,
|
| 881 |
+
"learning_rate": 3.197242841993637e-05,
|
| 882 |
+
"loss": 0.3528,
|
| 883 |
+
"step": 1020
|
| 884 |
+
},
|
| 885 |
+
{
|
| 886 |
+
"epoch": 1.0922587486744433,
|
| 887 |
+
"grad_norm": 1.1334470510482788,
|
| 888 |
+
"learning_rate": 3.179568752209262e-05,
|
| 889 |
+
"loss": 0.3472,
|
| 890 |
+
"step": 1030
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 1.1028632025450689,
|
| 894 |
+
"grad_norm": 1.1980904340744019,
|
| 895 |
+
"learning_rate": 3.161894662424885e-05,
|
| 896 |
+
"loss": 0.343,
|
| 897 |
+
"step": 1040
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 1.1134676564156947,
|
| 901 |
+
"grad_norm": 1.144959568977356,
|
| 902 |
+
"learning_rate": 3.14422057264051e-05,
|
| 903 |
+
"loss": 0.3447,
|
| 904 |
+
"step": 1050
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"epoch": 1.1134676564156947,
|
| 908 |
+
"eval_loss": 0.5998801589012146,
|
| 909 |
+
"eval_runtime": 11.7594,
|
| 910 |
+
"eval_samples_per_second": 40.818,
|
| 911 |
+
"eval_steps_per_second": 2.551,
|
| 912 |
+
"step": 1050
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 1.1240721102863203,
|
| 916 |
+
"grad_norm": 1.1883800029754639,
|
| 917 |
+
"learning_rate": 3.126546482856133e-05,
|
| 918 |
+
"loss": 0.3353,
|
| 919 |
+
"step": 1060
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 1.1346765641569458,
|
| 923 |
+
"grad_norm": 1.0962867736816406,
|
| 924 |
+
"learning_rate": 3.108872393071757e-05,
|
| 925 |
+
"loss": 0.3726,
|
| 926 |
+
"step": 1070
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 1.1452810180275717,
|
| 930 |
+
"grad_norm": 1.3056061267852783,
|
| 931 |
+
"learning_rate": 3.091198303287381e-05,
|
| 932 |
+
"loss": 0.3317,
|
| 933 |
+
"step": 1080
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 1.1558854718981972,
|
| 937 |
+
"grad_norm": 1.1041945219039917,
|
| 938 |
+
"learning_rate": 3.073524213503005e-05,
|
| 939 |
+
"loss": 0.3509,
|
| 940 |
+
"step": 1090
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 1.1664899257688228,
|
| 944 |
+
"grad_norm": 1.1359084844589233,
|
| 945 |
+
"learning_rate": 3.0558501237186286e-05,
|
| 946 |
+
"loss": 0.3424,
|
| 947 |
+
"step": 1100
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 1.1664899257688228,
|
| 951 |
+
"eval_loss": 0.6033491492271423,
|
| 952 |
+
"eval_runtime": 11.8171,
|
| 953 |
+
"eval_samples_per_second": 40.619,
|
| 954 |
+
"eval_steps_per_second": 2.539,
|
| 955 |
+
"step": 1100
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 1.1770943796394486,
|
| 959 |
+
"grad_norm": 1.2678911685943604,
|
| 960 |
+
"learning_rate": 3.0381760339342525e-05,
|
| 961 |
+
"loss": 0.3421,
|
| 962 |
+
"step": 1110
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 1.1876988335100742,
|
| 966 |
+
"grad_norm": 1.2048425674438477,
|
| 967 |
+
"learning_rate": 3.0205019441498768e-05,
|
| 968 |
+
"loss": 0.3238,
|
| 969 |
+
"step": 1120
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 1.1983032873806998,
|
| 973 |
+
"grad_norm": 1.120171308517456,
|
| 974 |
+
"learning_rate": 3.0028278543655004e-05,
|
| 975 |
+
"loss": 0.328,
|
| 976 |
+
"step": 1130
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 1.2089077412513256,
|
| 980 |
+
"grad_norm": 1.0923452377319336,
|
| 981 |
+
"learning_rate": 2.985153764581124e-05,
|
| 982 |
+
"loss": 0.3567,
|
| 983 |
+
"step": 1140
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 1.2195121951219512,
|
| 987 |
+
"grad_norm": 1.0582720041275024,
|
| 988 |
+
"learning_rate": 2.9674796747967482e-05,
|
| 989 |
+
"loss": 0.3431,
|
| 990 |
+
"step": 1150
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 1.2195121951219512,
|
| 994 |
+
"eval_loss": 0.6016908288002014,
|
| 995 |
+
"eval_runtime": 11.8175,
|
| 996 |
+
"eval_samples_per_second": 40.618,
|
| 997 |
+
"eval_steps_per_second": 2.539,
|
| 998 |
+
"step": 1150
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 1.2301166489925768,
|
| 1002 |
+
"grad_norm": 1.304275393486023,
|
| 1003 |
+
"learning_rate": 2.9498055850123718e-05,
|
| 1004 |
+
"loss": 0.3363,
|
| 1005 |
+
"step": 1160
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 1.2407211028632026,
|
| 1009 |
+
"grad_norm": 1.3723812103271484,
|
| 1010 |
+
"learning_rate": 2.932131495227996e-05,
|
| 1011 |
+
"loss": 0.3487,
|
| 1012 |
+
"step": 1170
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"epoch": 1.2513255567338282,
|
| 1016 |
+
"grad_norm": 1.195857286453247,
|
| 1017 |
+
"learning_rate": 2.9144574054436196e-05,
|
| 1018 |
+
"loss": 0.3313,
|
| 1019 |
+
"step": 1180
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 1.2619300106044538,
|
| 1023 |
+
"grad_norm": 1.2628227472305298,
|
| 1024 |
+
"learning_rate": 2.896783315659244e-05,
|
| 1025 |
+
"loss": 0.3469,
|
| 1026 |
+
"step": 1190
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 1.2725344644750796,
|
| 1030 |
+
"grad_norm": 1.398179531097412,
|
| 1031 |
+
"learning_rate": 2.8791092258748675e-05,
|
| 1032 |
+
"loss": 0.3304,
|
| 1033 |
+
"step": 1200
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 1.2725344644750796,
|
| 1037 |
+
"eval_loss": 0.6067756414413452,
|
| 1038 |
+
"eval_runtime": 11.8179,
|
| 1039 |
+
"eval_samples_per_second": 40.616,
|
| 1040 |
+
"eval_steps_per_second": 2.539,
|
| 1041 |
+
"step": 1200
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 1.2831389183457051,
|
| 1045 |
+
"grad_norm": 1.351558804512024,
|
| 1046 |
+
"learning_rate": 2.8614351360904917e-05,
|
| 1047 |
+
"loss": 0.3349,
|
| 1048 |
+
"step": 1210
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 1.2937433722163307,
|
| 1052 |
+
"grad_norm": 1.0469820499420166,
|
| 1053 |
+
"learning_rate": 2.8437610463061153e-05,
|
| 1054 |
+
"loss": 0.3253,
|
| 1055 |
+
"step": 1220
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 1.3043478260869565,
|
| 1059 |
+
"grad_norm": 1.205822467803955,
|
| 1060 |
+
"learning_rate": 2.826086956521739e-05,
|
| 1061 |
+
"loss": 0.3245,
|
| 1062 |
+
"step": 1230
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 1.3149522799575821,
|
| 1066 |
+
"grad_norm": 1.1349923610687256,
|
| 1067 |
+
"learning_rate": 2.808412866737363e-05,
|
| 1068 |
+
"loss": 0.3225,
|
| 1069 |
+
"step": 1240
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 1.3255567338282077,
|
| 1073 |
+
"grad_norm": 1.2688688039779663,
|
| 1074 |
+
"learning_rate": 2.790738776952987e-05,
|
| 1075 |
+
"loss": 0.341,
|
| 1076 |
+
"step": 1250
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 1.3255567338282077,
|
| 1080 |
+
"eval_loss": 0.6084305047988892,
|
| 1081 |
+
"eval_runtime": 11.8165,
|
| 1082 |
+
"eval_samples_per_second": 40.621,
|
| 1083 |
+
"eval_steps_per_second": 2.539,
|
| 1084 |
+
"step": 1250
|
| 1085 |
+
},
|
| 1086 |
+
{
|
| 1087 |
+
"epoch": 1.3361611876988335,
|
| 1088 |
+
"grad_norm": 1.3045439720153809,
|
| 1089 |
+
"learning_rate": 2.773064687168611e-05,
|
| 1090 |
+
"loss": 0.3352,
|
| 1091 |
+
"step": 1260
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 1.346765641569459,
|
| 1095 |
+
"grad_norm": 1.314754843711853,
|
| 1096 |
+
"learning_rate": 2.755390597384235e-05,
|
| 1097 |
+
"loss": 0.3388,
|
| 1098 |
+
"step": 1270
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 1.357370095440085,
|
| 1102 |
+
"grad_norm": 1.3320605754852295,
|
| 1103 |
+
"learning_rate": 2.7377165075998588e-05,
|
| 1104 |
+
"loss": 0.3353,
|
| 1105 |
+
"step": 1280
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 1.3679745493107105,
|
| 1109 |
+
"grad_norm": 1.239930272102356,
|
| 1110 |
+
"learning_rate": 2.7200424178154827e-05,
|
| 1111 |
+
"loss": 0.3447,
|
| 1112 |
+
"step": 1290
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 1.378579003181336,
|
| 1116 |
+
"grad_norm": 1.227774739265442,
|
| 1117 |
+
"learning_rate": 2.7023683280311063e-05,
|
| 1118 |
+
"loss": 0.332,
|
| 1119 |
+
"step": 1300
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 1.378579003181336,
|
| 1123 |
+
"eval_loss": 0.6087238192558289,
|
| 1124 |
+
"eval_runtime": 11.8173,
|
| 1125 |
+
"eval_samples_per_second": 40.618,
|
| 1126 |
+
"eval_steps_per_second": 2.539,
|
| 1127 |
+
"step": 1300
|
| 1128 |
+
},
|
| 1129 |
+
{
|
| 1130 |
+
"epoch": 1.389183457051962,
|
| 1131 |
+
"grad_norm": 1.2262154817581177,
|
| 1132 |
+
"learning_rate": 2.6846942382467306e-05,
|
| 1133 |
+
"loss": 0.326,
|
| 1134 |
+
"step": 1310
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 1.3997879109225875,
|
| 1138 |
+
"grad_norm": 1.4143425226211548,
|
| 1139 |
+
"learning_rate": 2.667020148462354e-05,
|
| 1140 |
+
"loss": 0.329,
|
| 1141 |
+
"step": 1320
|
| 1142 |
+
},
|
| 1143 |
+
{
|
| 1144 |
+
"epoch": 1.4103923647932133,
|
| 1145 |
+
"grad_norm": 1.548729658126831,
|
| 1146 |
+
"learning_rate": 2.6493460586779784e-05,
|
| 1147 |
+
"loss": 0.3286,
|
| 1148 |
+
"step": 1330
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 1.4209968186638389,
|
| 1152 |
+
"grad_norm": 1.2641792297363281,
|
| 1153 |
+
"learning_rate": 2.631671968893602e-05,
|
| 1154 |
+
"loss": 0.3134,
|
| 1155 |
+
"step": 1340
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 1.4316012725344645,
|
| 1159 |
+
"grad_norm": 1.302757978439331,
|
| 1160 |
+
"learning_rate": 2.6139978791092262e-05,
|
| 1161 |
+
"loss": 0.3056,
|
| 1162 |
+
"step": 1350
|
| 1163 |
+
},
|
| 1164 |
+
{
|
| 1165 |
+
"epoch": 1.4316012725344645,
|
| 1166 |
+
"eval_loss": 0.6126307249069214,
|
| 1167 |
+
"eval_runtime": 11.796,
|
| 1168 |
+
"eval_samples_per_second": 40.692,
|
| 1169 |
+
"eval_steps_per_second": 2.543,
|
| 1170 |
+
"step": 1350
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 1.4422057264050903,
|
| 1174 |
+
"grad_norm": 1.2385451793670654,
|
| 1175 |
+
"learning_rate": 2.5963237893248498e-05,
|
| 1176 |
+
"loss": 0.3352,
|
| 1177 |
+
"step": 1360
|
| 1178 |
+
},
|
| 1179 |
+
{
|
| 1180 |
+
"epoch": 1.4528101802757158,
|
| 1181 |
+
"grad_norm": 1.226826786994934,
|
| 1182 |
+
"learning_rate": 2.5786496995404734e-05,
|
| 1183 |
+
"loss": 0.3293,
|
| 1184 |
+
"step": 1370
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 1.4634146341463414,
|
| 1188 |
+
"grad_norm": 1.1468507051467896,
|
| 1189 |
+
"learning_rate": 2.5609756097560977e-05,
|
| 1190 |
+
"loss": 0.3271,
|
| 1191 |
+
"step": 1380
|
| 1192 |
+
},
|
| 1193 |
+
{
|
| 1194 |
+
"epoch": 1.4740190880169672,
|
| 1195 |
+
"grad_norm": 1.4662965536117554,
|
| 1196 |
+
"learning_rate": 2.5433015199717212e-05,
|
| 1197 |
+
"loss": 0.3285,
|
| 1198 |
+
"step": 1390
|
| 1199 |
+
},
|
| 1200 |
+
{
|
| 1201 |
+
"epoch": 1.4846235418875928,
|
| 1202 |
+
"grad_norm": 1.3143432140350342,
|
| 1203 |
+
"learning_rate": 2.5256274301873455e-05,
|
| 1204 |
+
"loss": 0.3271,
|
| 1205 |
+
"step": 1400
|
| 1206 |
+
},
|
| 1207 |
+
{
|
| 1208 |
+
"epoch": 1.4846235418875928,
|
| 1209 |
+
"eval_loss": 0.6134337186813354,
|
| 1210 |
+
"eval_runtime": 11.777,
|
| 1211 |
+
"eval_samples_per_second": 40.757,
|
| 1212 |
+
"eval_steps_per_second": 2.547,
|
| 1213 |
+
"step": 1400
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 1.4952279957582184,
|
| 1217 |
+
"grad_norm": 1.2217501401901245,
|
| 1218 |
+
"learning_rate": 2.507953340402969e-05,
|
| 1219 |
+
"loss": 0.3093,
|
| 1220 |
+
"step": 1410
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 1.5058324496288442,
|
| 1224 |
+
"grad_norm": 1.479797124862671,
|
| 1225 |
+
"learning_rate": 2.4902792506185933e-05,
|
| 1226 |
+
"loss": 0.3044,
|
| 1227 |
+
"step": 1420
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 1.5164369034994698,
|
| 1231 |
+
"grad_norm": 1.2942014932632446,
|
| 1232 |
+
"learning_rate": 2.4726051608342173e-05,
|
| 1233 |
+
"loss": 0.3279,
|
| 1234 |
+
"step": 1430
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 1.5270413573700954,
|
| 1238 |
+
"grad_norm": 1.194472074508667,
|
| 1239 |
+
"learning_rate": 2.4549310710498412e-05,
|
| 1240 |
+
"loss": 0.3124,
|
| 1241 |
+
"step": 1440
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 1.5376458112407212,
|
| 1245 |
+
"grad_norm": 1.3158146142959595,
|
| 1246 |
+
"learning_rate": 2.437256981265465e-05,
|
| 1247 |
+
"loss": 0.3174,
|
| 1248 |
+
"step": 1450
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 1.5376458112407212,
|
| 1252 |
+
"eval_loss": 0.612784206867218,
|
| 1253 |
+
"eval_runtime": 11.7301,
|
| 1254 |
+
"eval_samples_per_second": 40.92,
|
| 1255 |
+
"eval_steps_per_second": 2.558,
|
| 1256 |
+
"step": 1450
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 1.5482502651113468,
|
| 1260 |
+
"grad_norm": 1.2772356271743774,
|
| 1261 |
+
"learning_rate": 2.419582891481089e-05,
|
| 1262 |
+
"loss": 0.3233,
|
| 1263 |
+
"step": 1460
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 1.5588547189819724,
|
| 1267 |
+
"grad_norm": 1.2930830717086792,
|
| 1268 |
+
"learning_rate": 2.401908801696713e-05,
|
| 1269 |
+
"loss": 0.3193,
|
| 1270 |
+
"step": 1470
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 1.5694591728525982,
|
| 1274 |
+
"grad_norm": 1.3090952634811401,
|
| 1275 |
+
"learning_rate": 2.3842347119123365e-05,
|
| 1276 |
+
"loss": 0.3169,
|
| 1277 |
+
"step": 1480
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 1.5800636267232238,
|
| 1281 |
+
"grad_norm": 1.2926676273345947,
|
| 1282 |
+
"learning_rate": 2.3665606221279604e-05,
|
| 1283 |
+
"loss": 0.3046,
|
| 1284 |
+
"step": 1490
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 1.5906680805938493,
|
| 1288 |
+
"grad_norm": 1.358901023864746,
|
| 1289 |
+
"learning_rate": 2.3488865323435844e-05,
|
| 1290 |
+
"loss": 0.318,
|
| 1291 |
+
"step": 1500
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 1.5906680805938493,
|
| 1295 |
+
"eval_loss": 0.6163415908813477,
|
| 1296 |
+
"eval_runtime": 11.7301,
|
| 1297 |
+
"eval_samples_per_second": 40.92,
|
| 1298 |
+
"eval_steps_per_second": 2.558,
|
| 1299 |
+
"step": 1500
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 1.6012725344644752,
|
| 1303 |
+
"grad_norm": 1.4036508798599243,
|
| 1304 |
+
"learning_rate": 2.3312124425592083e-05,
|
| 1305 |
+
"loss": 0.3163,
|
| 1306 |
+
"step": 1510
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 1.6118769883351007,
|
| 1310 |
+
"grad_norm": 1.2453142404556274,
|
| 1311 |
+
"learning_rate": 2.3135383527748322e-05,
|
| 1312 |
+
"loss": 0.2934,
|
| 1313 |
+
"step": 1520
|
| 1314 |
+
},
|
| 1315 |
+
{
|
| 1316 |
+
"epoch": 1.6224814422057263,
|
| 1317 |
+
"grad_norm": 1.5171256065368652,
|
| 1318 |
+
"learning_rate": 2.295864262990456e-05,
|
| 1319 |
+
"loss": 0.3186,
|
| 1320 |
+
"step": 1530
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"epoch": 1.6330858960763521,
|
| 1324 |
+
"grad_norm": 1.4850494861602783,
|
| 1325 |
+
"learning_rate": 2.27819017320608e-05,
|
| 1326 |
+
"loss": 0.3206,
|
| 1327 |
+
"step": 1540
|
| 1328 |
+
},
|
| 1329 |
+
{
|
| 1330 |
+
"epoch": 1.6436903499469777,
|
| 1331 |
+
"grad_norm": 1.475541353225708,
|
| 1332 |
+
"learning_rate": 2.260516083421704e-05,
|
| 1333 |
+
"loss": 0.3218,
|
| 1334 |
+
"step": 1550
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 1.6436903499469777,
|
| 1338 |
+
"eval_loss": 0.616825520992279,
|
| 1339 |
+
"eval_runtime": 11.7336,
|
| 1340 |
+
"eval_samples_per_second": 40.908,
|
| 1341 |
+
"eval_steps_per_second": 2.557,
|
| 1342 |
+
"step": 1550
|
| 1343 |
+
},
|
| 1344 |
+
{
|
| 1345 |
+
"epoch": 1.6542948038176033,
|
| 1346 |
+
"grad_norm": 1.401365041732788,
|
| 1347 |
+
"learning_rate": 2.2428419936373275e-05,
|
| 1348 |
+
"loss": 0.3423,
|
| 1349 |
+
"step": 1560
|
| 1350 |
+
},
|
| 1351 |
+
{
|
| 1352 |
+
"epoch": 1.664899257688229,
|
| 1353 |
+
"grad_norm": 1.2514119148254395,
|
| 1354 |
+
"learning_rate": 2.2251679038529514e-05,
|
| 1355 |
+
"loss": 0.3146,
|
| 1356 |
+
"step": 1570
|
| 1357 |
+
},
|
| 1358 |
+
{
|
| 1359 |
+
"epoch": 1.6755037115588547,
|
| 1360 |
+
"grad_norm": 1.2970105409622192,
|
| 1361 |
+
"learning_rate": 2.2074938140685754e-05,
|
| 1362 |
+
"loss": 0.3229,
|
| 1363 |
+
"step": 1580
|
| 1364 |
+
},
|
| 1365 |
+
{
|
| 1366 |
+
"epoch": 1.6861081654294803,
|
| 1367 |
+
"grad_norm": 1.398328185081482,
|
| 1368 |
+
"learning_rate": 2.1898197242841996e-05,
|
| 1369 |
+
"loss": 0.3194,
|
| 1370 |
+
"step": 1590
|
| 1371 |
+
},
|
| 1372 |
+
{
|
| 1373 |
+
"epoch": 1.696712619300106,
|
| 1374 |
+
"grad_norm": 1.5763297080993652,
|
| 1375 |
+
"learning_rate": 2.1721456344998235e-05,
|
| 1376 |
+
"loss": 0.3169,
|
| 1377 |
+
"step": 1600
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 1.696712619300106,
|
| 1381 |
+
"eval_loss": 0.6218429207801819,
|
| 1382 |
+
"eval_runtime": 11.7407,
|
| 1383 |
+
"eval_samples_per_second": 40.883,
|
| 1384 |
+
"eval_steps_per_second": 2.555,
|
| 1385 |
+
"step": 1600
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 1.7073170731707317,
|
| 1389 |
+
"grad_norm": 1.5781402587890625,
|
| 1390 |
+
"learning_rate": 2.1544715447154475e-05,
|
| 1391 |
+
"loss": 0.3123,
|
| 1392 |
+
"step": 1610
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 1.7179215270413573,
|
| 1396 |
+
"grad_norm": 1.2571287155151367,
|
| 1397 |
+
"learning_rate": 2.1367974549310714e-05,
|
| 1398 |
+
"loss": 0.3023,
|
| 1399 |
+
"step": 1620
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 1.728525980911983,
|
| 1403 |
+
"grad_norm": 1.4663057327270508,
|
| 1404 |
+
"learning_rate": 2.1191233651466953e-05,
|
| 1405 |
+
"loss": 0.3142,
|
| 1406 |
+
"step": 1630
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 1.7391304347826086,
|
| 1410 |
+
"grad_norm": 1.5726102590560913,
|
| 1411 |
+
"learning_rate": 2.101449275362319e-05,
|
| 1412 |
+
"loss": 0.3264,
|
| 1413 |
+
"step": 1640
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 1.7497348886532342,
|
| 1417 |
+
"grad_norm": 1.2078590393066406,
|
| 1418 |
+
"learning_rate": 2.0837751855779428e-05,
|
| 1419 |
+
"loss": 0.3001,
|
| 1420 |
+
"step": 1650
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 1.7497348886532342,
|
| 1424 |
+
"eval_loss": 0.6163042187690735,
|
| 1425 |
+
"eval_runtime": 11.7879,
|
| 1426 |
+
"eval_samples_per_second": 40.72,
|
| 1427 |
+
"eval_steps_per_second": 2.545,
|
| 1428 |
+
"step": 1650
|
| 1429 |
+
},
|
| 1430 |
+
{
|
| 1431 |
+
"epoch": 1.76033934252386,
|
| 1432 |
+
"grad_norm": 1.3106614351272583,
|
| 1433 |
+
"learning_rate": 2.0661010957935667e-05,
|
| 1434 |
+
"loss": 0.3055,
|
| 1435 |
+
"step": 1660
|
| 1436 |
+
},
|
| 1437 |
+
{
|
| 1438 |
+
"epoch": 1.7709437963944858,
|
| 1439 |
+
"grad_norm": 1.281083345413208,
|
| 1440 |
+
"learning_rate": 2.0484270060091906e-05,
|
| 1441 |
+
"loss": 0.3163,
|
| 1442 |
+
"step": 1670
|
| 1443 |
+
},
|
| 1444 |
+
{
|
| 1445 |
+
"epoch": 1.7815482502651112,
|
| 1446 |
+
"grad_norm": 1.3612393140792847,
|
| 1447 |
+
"learning_rate": 2.0307529162248146e-05,
|
| 1448 |
+
"loss": 0.3142,
|
| 1449 |
+
"step": 1680
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 1.792152704135737,
|
| 1453 |
+
"grad_norm": 1.5603421926498413,
|
| 1454 |
+
"learning_rate": 2.0130788264404385e-05,
|
| 1455 |
+
"loss": 0.3106,
|
| 1456 |
+
"step": 1690
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"epoch": 1.8027571580063628,
|
| 1460 |
+
"grad_norm": 1.4833933115005493,
|
| 1461 |
+
"learning_rate": 1.9954047366560624e-05,
|
| 1462 |
+
"loss": 0.3006,
|
| 1463 |
+
"step": 1700
|
| 1464 |
+
},
|
| 1465 |
+
{
|
| 1466 |
+
"epoch": 1.8027571580063628,
|
| 1467 |
+
"eval_loss": 0.622329831123352,
|
| 1468 |
+
"eval_runtime": 11.8048,
|
| 1469 |
+
"eval_samples_per_second": 40.662,
|
| 1470 |
+
"eval_steps_per_second": 2.541,
|
| 1471 |
+
"step": 1700
|
| 1472 |
+
},
|
| 1473 |
+
{
|
| 1474 |
+
"epoch": 1.8133616118769882,
|
| 1475 |
+
"grad_norm": 1.4772926568984985,
|
| 1476 |
+
"learning_rate": 1.977730646871686e-05,
|
| 1477 |
+
"loss": 0.3083,
|
| 1478 |
+
"step": 1710
|
| 1479 |
+
},
|
| 1480 |
+
{
|
| 1481 |
+
"epoch": 1.823966065747614,
|
| 1482 |
+
"grad_norm": 1.4501652717590332,
|
| 1483 |
+
"learning_rate": 1.96005655708731e-05,
|
| 1484 |
+
"loss": 0.3019,
|
| 1485 |
+
"step": 1720
|
| 1486 |
+
},
|
| 1487 |
+
{
|
| 1488 |
+
"epoch": 1.8345705196182398,
|
| 1489 |
+
"grad_norm": 1.4683219194412231,
|
| 1490 |
+
"learning_rate": 1.9423824673029338e-05,
|
| 1491 |
+
"loss": 0.3045,
|
| 1492 |
+
"step": 1730
|
| 1493 |
+
},
|
| 1494 |
+
{
|
| 1495 |
+
"epoch": 1.8451749734888652,
|
| 1496 |
+
"grad_norm": 1.5032085180282593,
|
| 1497 |
+
"learning_rate": 1.9247083775185577e-05,
|
| 1498 |
+
"loss": 0.306,
|
| 1499 |
+
"step": 1740
|
| 1500 |
+
},
|
| 1501 |
+
{
|
| 1502 |
+
"epoch": 1.855779427359491,
|
| 1503 |
+
"grad_norm": 1.564963936805725,
|
| 1504 |
+
"learning_rate": 1.9070342877341817e-05,
|
| 1505 |
+
"loss": 0.2907,
|
| 1506 |
+
"step": 1750
|
| 1507 |
+
},
|
| 1508 |
+
{
|
| 1509 |
+
"epoch": 1.855779427359491,
|
| 1510 |
+
"eval_loss": 0.6292106509208679,
|
| 1511 |
+
"eval_runtime": 11.8242,
|
| 1512 |
+
"eval_samples_per_second": 40.595,
|
| 1513 |
+
"eval_steps_per_second": 2.537,
|
| 1514 |
+
"step": 1750
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 1.8663838812301168,
|
| 1518 |
+
"grad_norm": 1.4046026468276978,
|
| 1519 |
+
"learning_rate": 1.8893601979498056e-05,
|
| 1520 |
+
"loss": 0.2924,
|
| 1521 |
+
"step": 1760
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 1.8769883351007424,
|
| 1525 |
+
"grad_norm": 1.4110816717147827,
|
| 1526 |
+
"learning_rate": 1.8716861081654298e-05,
|
| 1527 |
+
"loss": 0.2994,
|
| 1528 |
+
"step": 1770
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 1.887592788971368,
|
| 1532 |
+
"grad_norm": 1.3285332918167114,
|
| 1533 |
+
"learning_rate": 1.8540120183810537e-05,
|
| 1534 |
+
"loss": 0.323,
|
| 1535 |
+
"step": 1780
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 1.8981972428419938,
|
| 1539 |
+
"grad_norm": 1.4293811321258545,
|
| 1540 |
+
"learning_rate": 1.8363379285966773e-05,
|
| 1541 |
+
"loss": 0.2913,
|
| 1542 |
+
"step": 1790
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 1.9088016967126193,
|
| 1546 |
+
"grad_norm": 1.4230468273162842,
|
| 1547 |
+
"learning_rate": 1.8186638388123012e-05,
|
| 1548 |
+
"loss": 0.3066,
|
| 1549 |
+
"step": 1800
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 1.9088016967126193,
|
| 1553 |
+
"eval_loss": 0.6281366348266602,
|
| 1554 |
+
"eval_runtime": 11.8237,
|
| 1555 |
+
"eval_samples_per_second": 40.597,
|
| 1556 |
+
"eval_steps_per_second": 2.537,
|
| 1557 |
+
"step": 1800
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 1.919406150583245,
|
| 1561 |
+
"grad_norm": 1.412109375,
|
| 1562 |
+
"learning_rate": 1.800989749027925e-05,
|
| 1563 |
+
"loss": 0.2954,
|
| 1564 |
+
"step": 1810
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 1.9300106044538707,
|
| 1568 |
+
"grad_norm": 1.5206971168518066,
|
| 1569 |
+
"learning_rate": 1.783315659243549e-05,
|
| 1570 |
+
"loss": 0.3058,
|
| 1571 |
+
"step": 1820
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 1.9406150583244963,
|
| 1575 |
+
"grad_norm": 1.4795233011245728,
|
| 1576 |
+
"learning_rate": 1.765641569459173e-05,
|
| 1577 |
+
"loss": 0.2862,
|
| 1578 |
+
"step": 1830
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 1.951219512195122,
|
| 1582 |
+
"grad_norm": 1.3603821992874146,
|
| 1583 |
+
"learning_rate": 1.747967479674797e-05,
|
| 1584 |
+
"loss": 0.3028,
|
| 1585 |
+
"step": 1840
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 1.9618239660657477,
|
| 1589 |
+
"grad_norm": 1.678951621055603,
|
| 1590 |
+
"learning_rate": 1.730293389890421e-05,
|
| 1591 |
+
"loss": 0.2936,
|
| 1592 |
+
"step": 1850
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 1.9618239660657477,
|
| 1596 |
+
"eval_loss": 0.6346422433853149,
|
| 1597 |
+
"eval_runtime": 11.8206,
|
| 1598 |
+
"eval_samples_per_second": 40.607,
|
| 1599 |
+
"eval_steps_per_second": 2.538,
|
| 1600 |
+
"step": 1850
|
| 1601 |
+
},
|
| 1602 |
+
{
|
| 1603 |
+
"epoch": 1.9724284199363733,
|
| 1604 |
+
"grad_norm": 1.6259334087371826,
|
| 1605 |
+
"learning_rate": 1.7126193001060444e-05,
|
| 1606 |
+
"loss": 0.2911,
|
| 1607 |
+
"step": 1860
|
| 1608 |
+
},
|
| 1609 |
+
{
|
| 1610 |
+
"epoch": 1.9830328738069989,
|
| 1611 |
+
"grad_norm": 1.3375662565231323,
|
| 1612 |
+
"learning_rate": 1.6949452103216683e-05,
|
| 1613 |
+
"loss": 0.3002,
|
| 1614 |
+
"step": 1870
|
| 1615 |
+
},
|
| 1616 |
+
{
|
| 1617 |
+
"epoch": 1.9936373276776247,
|
| 1618 |
+
"grad_norm": 1.552260398864746,
|
| 1619 |
+
"learning_rate": 1.6772711205372923e-05,
|
| 1620 |
+
"loss": 0.3017,
|
| 1621 |
+
"step": 1880
|
| 1622 |
+
},
|
| 1623 |
+
{
|
| 1624 |
+
"epoch": 2.00424178154825,
|
| 1625 |
+
"grad_norm": 1.1149572134017944,
|
| 1626 |
+
"learning_rate": 1.6595970307529162e-05,
|
| 1627 |
+
"loss": 0.2835,
|
| 1628 |
+
"step": 1890
|
| 1629 |
+
},
|
| 1630 |
+
{
|
| 1631 |
+
"epoch": 2.014846235418876,
|
| 1632 |
+
"grad_norm": 1.3478857278823853,
|
| 1633 |
+
"learning_rate": 1.64192294096854e-05,
|
| 1634 |
+
"loss": 0.252,
|
| 1635 |
+
"step": 1900
|
| 1636 |
+
},
|
| 1637 |
+
{
|
| 1638 |
+
"epoch": 2.014846235418876,
|
| 1639 |
+
"eval_loss": 0.6588704586029053,
|
| 1640 |
+
"eval_runtime": 11.8124,
|
| 1641 |
+
"eval_samples_per_second": 40.635,
|
| 1642 |
+
"eval_steps_per_second": 2.54,
|
| 1643 |
+
"step": 1900
|
| 1644 |
+
},
|
| 1645 |
+
{
|
| 1646 |
+
"epoch": 2.0254506892895017,
|
| 1647 |
+
"grad_norm": 1.616431474685669,
|
| 1648 |
+
"learning_rate": 1.624248851184164e-05,
|
| 1649 |
+
"loss": 0.2482,
|
| 1650 |
+
"step": 1910
|
| 1651 |
+
},
|
| 1652 |
+
{
|
| 1653 |
+
"epoch": 2.0360551431601275,
|
| 1654 |
+
"grad_norm": 1.3447093963623047,
|
| 1655 |
+
"learning_rate": 1.606574761399788e-05,
|
| 1656 |
+
"loss": 0.2516,
|
| 1657 |
+
"step": 1920
|
| 1658 |
+
},
|
| 1659 |
+
{
|
| 1660 |
+
"epoch": 2.046659597030753,
|
| 1661 |
+
"grad_norm": 1.4798699617385864,
|
| 1662 |
+
"learning_rate": 1.588900671615412e-05,
|
| 1663 |
+
"loss": 0.2583,
|
| 1664 |
+
"step": 1930
|
| 1665 |
+
},
|
| 1666 |
+
{
|
| 1667 |
+
"epoch": 2.0572640509013786,
|
| 1668 |
+
"grad_norm": 1.5262929201126099,
|
| 1669 |
+
"learning_rate": 1.5712265818310358e-05,
|
| 1670 |
+
"loss": 0.2527,
|
| 1671 |
+
"step": 1940
|
| 1672 |
+
},
|
| 1673 |
+
{
|
| 1674 |
+
"epoch": 2.0678685047720045,
|
| 1675 |
+
"grad_norm": 1.406010389328003,
|
| 1676 |
+
"learning_rate": 1.5535524920466597e-05,
|
| 1677 |
+
"loss": 0.2604,
|
| 1678 |
+
"step": 1950
|
| 1679 |
+
},
|
| 1680 |
+
{
|
| 1681 |
+
"epoch": 2.0678685047720045,
|
| 1682 |
+
"eval_loss": 0.6790052652359009,
|
| 1683 |
+
"eval_runtime": 11.7975,
|
| 1684 |
+
"eval_samples_per_second": 40.687,
|
| 1685 |
+
"eval_steps_per_second": 2.543,
|
| 1686 |
+
"step": 1950
|
| 1687 |
+
},
|
| 1688 |
+
{
|
| 1689 |
+
"epoch": 2.07847295864263,
|
| 1690 |
+
"grad_norm": 1.5734636783599854,
|
| 1691 |
+
"learning_rate": 1.5358784022622836e-05,
|
| 1692 |
+
"loss": 0.2465,
|
| 1693 |
+
"step": 1960
|
| 1694 |
+
},
|
| 1695 |
+
{
|
| 1696 |
+
"epoch": 2.0890774125132556,
|
| 1697 |
+
"grad_norm": 1.4714436531066895,
|
| 1698 |
+
"learning_rate": 1.5182043124779075e-05,
|
| 1699 |
+
"loss": 0.2478,
|
| 1700 |
+
"step": 1970
|
| 1701 |
+
},
|
| 1702 |
+
{
|
| 1703 |
+
"epoch": 2.0996818663838814,
|
| 1704 |
+
"grad_norm": 1.4968727827072144,
|
| 1705 |
+
"learning_rate": 1.5005302226935314e-05,
|
| 1706 |
+
"loss": 0.2466,
|
| 1707 |
+
"step": 1980
|
| 1708 |
+
},
|
| 1709 |
+
{
|
| 1710 |
+
"epoch": 2.110286320254507,
|
| 1711 |
+
"grad_norm": 1.3938302993774414,
|
| 1712 |
+
"learning_rate": 1.4828561329091554e-05,
|
| 1713 |
+
"loss": 0.2453,
|
| 1714 |
+
"step": 1990
|
| 1715 |
+
},
|
| 1716 |
+
{
|
| 1717 |
+
"epoch": 2.1208907741251326,
|
| 1718 |
+
"grad_norm": 1.419122338294983,
|
| 1719 |
+
"learning_rate": 1.4651820431247793e-05,
|
| 1720 |
+
"loss": 0.2533,
|
| 1721 |
+
"step": 2000
|
| 1722 |
+
},
|
| 1723 |
+
{
|
| 1724 |
+
"epoch": 2.1208907741251326,
|
| 1725 |
+
"eval_loss": 0.6880776882171631,
|
| 1726 |
+
"eval_runtime": 11.7687,
|
| 1727 |
+
"eval_samples_per_second": 40.786,
|
| 1728 |
+
"eval_steps_per_second": 2.549,
|
| 1729 |
+
"step": 2000
|
| 1730 |
+
},
|
| 1731 |
+
{
|
| 1732 |
+
"epoch": 2.1314952279957584,
|
| 1733 |
+
"grad_norm": 1.4001387357711792,
|
| 1734 |
+
"learning_rate": 1.4475079533404029e-05,
|
| 1735 |
+
"loss": 0.2494,
|
| 1736 |
+
"step": 2010
|
| 1737 |
+
},
|
| 1738 |
+
{
|
| 1739 |
+
"epoch": 2.1420996818663838,
|
| 1740 |
+
"grad_norm": 1.849181056022644,
|
| 1741 |
+
"learning_rate": 1.4298338635560268e-05,
|
| 1742 |
+
"loss": 0.2483,
|
| 1743 |
+
"step": 2020
|
| 1744 |
+
},
|
| 1745 |
+
{
|
| 1746 |
+
"epoch": 2.1527041357370096,
|
| 1747 |
+
"grad_norm": 1.5286574363708496,
|
| 1748 |
+
"learning_rate": 1.4121597737716507e-05,
|
| 1749 |
+
"loss": 0.2551,
|
| 1750 |
+
"step": 2030
|
| 1751 |
+
},
|
| 1752 |
+
{
|
| 1753 |
+
"epoch": 2.1633085896076354,
|
| 1754 |
+
"grad_norm": 1.3997042179107666,
|
| 1755 |
+
"learning_rate": 1.3944856839872746e-05,
|
| 1756 |
+
"loss": 0.255,
|
| 1757 |
+
"step": 2040
|
| 1758 |
+
},
|
| 1759 |
+
{
|
| 1760 |
+
"epoch": 2.1739130434782608,
|
| 1761 |
+
"grad_norm": 1.5057164430618286,
|
| 1762 |
+
"learning_rate": 1.3768115942028985e-05,
|
| 1763 |
+
"loss": 0.2548,
|
| 1764 |
+
"step": 2050
|
| 1765 |
+
},
|
| 1766 |
+
{
|
| 1767 |
+
"epoch": 2.1739130434782608,
|
| 1768 |
+
"eval_loss": 0.6825365424156189,
|
| 1769 |
+
"eval_runtime": 11.7292,
|
| 1770 |
+
"eval_samples_per_second": 40.924,
|
| 1771 |
+
"eval_steps_per_second": 2.558,
|
| 1772 |
+
"step": 2050
|
| 1773 |
+
},
|
| 1774 |
+
{
|
| 1775 |
+
"epoch": 2.1845174973488866,
|
| 1776 |
+
"grad_norm": 1.3889409303665161,
|
| 1777 |
+
"learning_rate": 1.3591375044185226e-05,
|
| 1778 |
+
"loss": 0.2484,
|
| 1779 |
+
"step": 2060
|
| 1780 |
+
},
|
| 1781 |
+
{
|
| 1782 |
+
"epoch": 2.1951219512195124,
|
| 1783 |
+
"grad_norm": 1.4697638750076294,
|
| 1784 |
+
"learning_rate": 1.3414634146341466e-05,
|
| 1785 |
+
"loss": 0.253,
|
| 1786 |
+
"step": 2070
|
| 1787 |
+
},
|
| 1788 |
+
{
|
| 1789 |
+
"epoch": 2.2057264050901377,
|
| 1790 |
+
"grad_norm": 1.5195242166519165,
|
| 1791 |
+
"learning_rate": 1.3237893248497705e-05,
|
| 1792 |
+
"loss": 0.2489,
|
| 1793 |
+
"step": 2080
|
| 1794 |
+
},
|
| 1795 |
+
{
|
| 1796 |
+
"epoch": 2.2163308589607635,
|
| 1797 |
+
"grad_norm": 1.5031260251998901,
|
| 1798 |
+
"learning_rate": 1.306115235065394e-05,
|
| 1799 |
+
"loss": 0.2416,
|
| 1800 |
+
"step": 2090
|
| 1801 |
+
},
|
| 1802 |
+
{
|
| 1803 |
+
"epoch": 2.2269353128313893,
|
| 1804 |
+
"grad_norm": 1.3110672235488892,
|
| 1805 |
+
"learning_rate": 1.288441145281018e-05,
|
| 1806 |
+
"loss": 0.2451,
|
| 1807 |
+
"step": 2100
|
| 1808 |
+
},
|
| 1809 |
+
{
|
| 1810 |
+
"epoch": 2.2269353128313893,
|
| 1811 |
+
"eval_loss": 0.6959334015846252,
|
| 1812 |
+
"eval_runtime": 11.7439,
|
| 1813 |
+
"eval_samples_per_second": 40.872,
|
| 1814 |
+
"eval_steps_per_second": 2.555,
|
| 1815 |
+
"step": 2100
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 2.2375397667020147,
|
| 1819 |
+
"grad_norm": 1.697758674621582,
|
| 1820 |
+
"learning_rate": 1.2707670554966419e-05,
|
| 1821 |
+
"loss": 0.2512,
|
| 1822 |
+
"step": 2110
|
| 1823 |
+
},
|
| 1824 |
+
{
|
| 1825 |
+
"epoch": 2.2481442205726405,
|
| 1826 |
+
"grad_norm": 1.7751915454864502,
|
| 1827 |
+
"learning_rate": 1.2530929657122658e-05,
|
| 1828 |
+
"loss": 0.2524,
|
| 1829 |
+
"step": 2120
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 2.2587486744432663,
|
| 1833 |
+
"grad_norm": 1.584010362625122,
|
| 1834 |
+
"learning_rate": 1.2354188759278897e-05,
|
| 1835 |
+
"loss": 0.2446,
|
| 1836 |
+
"step": 2130
|
| 1837 |
+
},
|
| 1838 |
+
{
|
| 1839 |
+
"epoch": 2.2693531283138917,
|
| 1840 |
+
"grad_norm": 1.5257493257522583,
|
| 1841 |
+
"learning_rate": 1.2177447861435136e-05,
|
| 1842 |
+
"loss": 0.2545,
|
| 1843 |
+
"step": 2140
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 2.2799575821845175,
|
| 1847 |
+
"grad_norm": 1.5823898315429688,
|
| 1848 |
+
"learning_rate": 1.2000706963591376e-05,
|
| 1849 |
+
"loss": 0.2391,
|
| 1850 |
+
"step": 2150
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 2.2799575821845175,
|
| 1854 |
+
"eval_loss": 0.6994083523750305,
|
| 1855 |
+
"eval_runtime": 11.7357,
|
| 1856 |
+
"eval_samples_per_second": 40.901,
|
| 1857 |
+
"eval_steps_per_second": 2.556,
|
| 1858 |
+
"step": 2150
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 2.2905620360551433,
|
| 1862 |
+
"grad_norm": 1.5830985307693481,
|
| 1863 |
+
"learning_rate": 1.1823966065747615e-05,
|
| 1864 |
+
"loss": 0.2454,
|
| 1865 |
+
"step": 2160
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 2.3011664899257687,
|
| 1869 |
+
"grad_norm": 1.6037838459014893,
|
| 1870 |
+
"learning_rate": 1.1647225167903854e-05,
|
| 1871 |
+
"loss": 0.2418,
|
| 1872 |
+
"step": 2170
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 2.3117709437963945,
|
| 1876 |
+
"grad_norm": 1.6492226123809814,
|
| 1877 |
+
"learning_rate": 1.1470484270060093e-05,
|
| 1878 |
+
"loss": 0.2536,
|
| 1879 |
+
"step": 2180
|
| 1880 |
+
},
|
| 1881 |
+
{
|
| 1882 |
+
"epoch": 2.3223753976670203,
|
| 1883 |
+
"grad_norm": 1.5775914192199707,
|
| 1884 |
+
"learning_rate": 1.129374337221633e-05,
|
| 1885 |
+
"loss": 0.2508,
|
| 1886 |
+
"step": 2190
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 2.3329798515376456,
|
| 1890 |
+
"grad_norm": 1.4473241567611694,
|
| 1891 |
+
"learning_rate": 1.111700247437257e-05,
|
| 1892 |
+
"loss": 0.2425,
|
| 1893 |
+
"step": 2200
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 2.3329798515376456,
|
| 1897 |
+
"eval_loss": 0.7015684843063354,
|
| 1898 |
+
"eval_runtime": 11.7856,
|
| 1899 |
+
"eval_samples_per_second": 40.728,
|
| 1900 |
+
"eval_steps_per_second": 2.545,
|
| 1901 |
+
"step": 2200
|
| 1902 |
+
},
|
| 1903 |
+
{
|
| 1904 |
+
"epoch": 2.3435843054082715,
|
| 1905 |
+
"grad_norm": 1.5466115474700928,
|
| 1906 |
+
"learning_rate": 1.0940261576528809e-05,
|
| 1907 |
+
"loss": 0.2409,
|
| 1908 |
+
"step": 2210
|
| 1909 |
+
},
|
| 1910 |
+
{
|
| 1911 |
+
"epoch": 2.3541887592788973,
|
| 1912 |
+
"grad_norm": 1.5728662014007568,
|
| 1913 |
+
"learning_rate": 1.0763520678685048e-05,
|
| 1914 |
+
"loss": 0.2495,
|
| 1915 |
+
"step": 2220
|
| 1916 |
+
},
|
| 1917 |
+
{
|
| 1918 |
+
"epoch": 2.3647932131495226,
|
| 1919 |
+
"grad_norm": 1.6017048358917236,
|
| 1920 |
+
"learning_rate": 1.0586779780841287e-05,
|
| 1921 |
+
"loss": 0.2441,
|
| 1922 |
+
"step": 2230
|
| 1923 |
+
},
|
| 1924 |
+
{
|
| 1925 |
+
"epoch": 2.3753976670201484,
|
| 1926 |
+
"grad_norm": 1.5967800617218018,
|
| 1927 |
+
"learning_rate": 1.0410038882997527e-05,
|
| 1928 |
+
"loss": 0.2403,
|
| 1929 |
+
"step": 2240
|
| 1930 |
+
},
|
| 1931 |
+
{
|
| 1932 |
+
"epoch": 2.3860021208907742,
|
| 1933 |
+
"grad_norm": 1.6465519666671753,
|
| 1934 |
+
"learning_rate": 1.0233297985153766e-05,
|
| 1935 |
+
"loss": 0.2461,
|
| 1936 |
+
"step": 2250
|
| 1937 |
+
},
|
| 1938 |
+
{
|
| 1939 |
+
"epoch": 2.3860021208907742,
|
| 1940 |
+
"eval_loss": 0.7029215693473816,
|
| 1941 |
+
"eval_runtime": 11.7953,
|
| 1942 |
+
"eval_samples_per_second": 40.694,
|
| 1943 |
+
"eval_steps_per_second": 2.543,
|
| 1944 |
+
"step": 2250
|
| 1945 |
+
},
|
| 1946 |
+
{
|
| 1947 |
+
"epoch": 2.3966065747613996,
|
| 1948 |
+
"grad_norm": 1.6651562452316284,
|
| 1949 |
+
"learning_rate": 1.0056557087310003e-05,
|
| 1950 |
+
"loss": 0.2502,
|
| 1951 |
+
"step": 2260
|
| 1952 |
+
},
|
| 1953 |
+
{
|
| 1954 |
+
"epoch": 2.4072110286320254,
|
| 1955 |
+
"grad_norm": 1.7012617588043213,
|
| 1956 |
+
"learning_rate": 9.879816189466243e-06,
|
| 1957 |
+
"loss": 0.2451,
|
| 1958 |
+
"step": 2270
|
| 1959 |
+
},
|
| 1960 |
+
{
|
| 1961 |
+
"epoch": 2.417815482502651,
|
| 1962 |
+
"grad_norm": 1.3896822929382324,
|
| 1963 |
+
"learning_rate": 9.703075291622482e-06,
|
| 1964 |
+
"loss": 0.2427,
|
| 1965 |
+
"step": 2280
|
| 1966 |
+
},
|
| 1967 |
+
{
|
| 1968 |
+
"epoch": 2.4284199363732766,
|
| 1969 |
+
"grad_norm": 1.630419135093689,
|
| 1970 |
+
"learning_rate": 9.526334393778721e-06,
|
| 1971 |
+
"loss": 0.2458,
|
| 1972 |
+
"step": 2290
|
| 1973 |
+
},
|
| 1974 |
+
{
|
| 1975 |
+
"epoch": 2.4390243902439024,
|
| 1976 |
+
"grad_norm": 1.7764724493026733,
|
| 1977 |
+
"learning_rate": 9.34959349593496e-06,
|
| 1978 |
+
"loss": 0.2513,
|
| 1979 |
+
"step": 2300
|
| 1980 |
+
},
|
| 1981 |
+
{
|
| 1982 |
+
"epoch": 2.4390243902439024,
|
| 1983 |
+
"eval_loss": 0.7068365812301636,
|
| 1984 |
+
"eval_runtime": 11.831,
|
| 1985 |
+
"eval_samples_per_second": 40.571,
|
| 1986 |
+
"eval_steps_per_second": 2.536,
|
| 1987 |
+
"step": 2300
|
| 1988 |
+
},
|
| 1989 |
+
{
|
| 1990 |
+
"epoch": 2.449628844114528,
|
| 1991 |
+
"grad_norm": 1.625576376914978,
|
| 1992 |
+
"learning_rate": 9.1728525980912e-06,
|
| 1993 |
+
"loss": 0.2308,
|
| 1994 |
+
"step": 2310
|
| 1995 |
+
},
|
| 1996 |
+
{
|
| 1997 |
+
"epoch": 2.4602332979851536,
|
| 1998 |
+
"grad_norm": 1.5538599491119385,
|
| 1999 |
+
"learning_rate": 8.996111700247438e-06,
|
| 2000 |
+
"loss": 0.237,
|
| 2001 |
+
"step": 2320
|
| 2002 |
+
},
|
| 2003 |
+
{
|
| 2004 |
+
"epoch": 2.4708377518557794,
|
| 2005 |
+
"grad_norm": 1.629430890083313,
|
| 2006 |
+
"learning_rate": 8.819370802403678e-06,
|
| 2007 |
+
"loss": 0.2476,
|
| 2008 |
+
"step": 2330
|
| 2009 |
+
},
|
| 2010 |
+
{
|
| 2011 |
+
"epoch": 2.481442205726405,
|
| 2012 |
+
"grad_norm": 1.4249067306518555,
|
| 2013 |
+
"learning_rate": 8.642629904559915e-06,
|
| 2014 |
+
"loss": 0.2433,
|
| 2015 |
+
"step": 2340
|
| 2016 |
+
},
|
| 2017 |
+
{
|
| 2018 |
+
"epoch": 2.4920466595970305,
|
| 2019 |
+
"grad_norm": 1.839856743812561,
|
| 2020 |
+
"learning_rate": 8.465889006716154e-06,
|
| 2021 |
+
"loss": 0.2461,
|
| 2022 |
+
"step": 2350
|
| 2023 |
+
},
|
| 2024 |
+
{
|
| 2025 |
+
"epoch": 2.4920466595970305,
|
| 2026 |
+
"eval_loss": 0.70945805311203,
|
| 2027 |
+
"eval_runtime": 11.8218,
|
| 2028 |
+
"eval_samples_per_second": 40.603,
|
| 2029 |
+
"eval_steps_per_second": 2.538,
|
| 2030 |
+
"step": 2350
|
| 2031 |
+
},
|
| 2032 |
+
{
|
| 2033 |
+
"epoch": 2.5026511134676563,
|
| 2034 |
+
"grad_norm": 1.5814393758773804,
|
| 2035 |
+
"learning_rate": 8.289148108872394e-06,
|
| 2036 |
+
"loss": 0.2473,
|
| 2037 |
+
"step": 2360
|
| 2038 |
+
},
|
| 2039 |
+
{
|
| 2040 |
+
"epoch": 2.513255567338282,
|
| 2041 |
+
"grad_norm": 1.6166481971740723,
|
| 2042 |
+
"learning_rate": 8.112407211028633e-06,
|
| 2043 |
+
"loss": 0.2288,
|
| 2044 |
+
"step": 2370
|
| 2045 |
+
},
|
| 2046 |
+
{
|
| 2047 |
+
"epoch": 2.5238600212089075,
|
| 2048 |
+
"grad_norm": 1.8309824466705322,
|
| 2049 |
+
"learning_rate": 7.93566631318487e-06,
|
| 2050 |
+
"loss": 0.237,
|
| 2051 |
+
"step": 2380
|
| 2052 |
+
},
|
| 2053 |
+
{
|
| 2054 |
+
"epoch": 2.5344644750795333,
|
| 2055 |
+
"grad_norm": 1.424099326133728,
|
| 2056 |
+
"learning_rate": 7.758925415341111e-06,
|
| 2057 |
+
"loss": 0.2356,
|
| 2058 |
+
"step": 2390
|
| 2059 |
+
},
|
| 2060 |
+
{
|
| 2061 |
+
"epoch": 2.545068928950159,
|
| 2062 |
+
"grad_norm": 1.739981770515442,
|
| 2063 |
+
"learning_rate": 7.5821845174973494e-06,
|
| 2064 |
+
"loss": 0.2423,
|
| 2065 |
+
"step": 2400
|
| 2066 |
+
},
|
| 2067 |
+
{
|
| 2068 |
+
"epoch": 2.545068928950159,
|
| 2069 |
+
"eval_loss": 0.7186661958694458,
|
| 2070 |
+
"eval_runtime": 11.8286,
|
| 2071 |
+
"eval_samples_per_second": 40.58,
|
| 2072 |
+
"eval_steps_per_second": 2.536,
|
| 2073 |
+
"step": 2400
|
| 2074 |
+
},
|
| 2075 |
+
{
|
| 2076 |
+
"epoch": 2.5556733828207845,
|
| 2077 |
+
"grad_norm": 1.5067882537841797,
|
| 2078 |
+
"learning_rate": 7.405443619653588e-06,
|
| 2079 |
+
"loss": 0.236,
|
| 2080 |
+
"step": 2410
|
| 2081 |
+
},
|
| 2082 |
+
{
|
| 2083 |
+
"epoch": 2.5662778366914103,
|
| 2084 |
+
"grad_norm": 1.5540106296539307,
|
| 2085 |
+
"learning_rate": 7.228702721809827e-06,
|
| 2086 |
+
"loss": 0.2429,
|
| 2087 |
+
"step": 2420
|
| 2088 |
+
},
|
| 2089 |
+
{
|
| 2090 |
+
"epoch": 2.576882290562036,
|
| 2091 |
+
"grad_norm": 1.6112455129623413,
|
| 2092 |
+
"learning_rate": 7.051961823966066e-06,
|
| 2093 |
+
"loss": 0.2424,
|
| 2094 |
+
"step": 2430
|
| 2095 |
+
},
|
| 2096 |
+
{
|
| 2097 |
+
"epoch": 2.5874867444326615,
|
| 2098 |
+
"grad_norm": 1.5903056859970093,
|
| 2099 |
+
"learning_rate": 6.875220926122305e-06,
|
| 2100 |
+
"loss": 0.2294,
|
| 2101 |
+
"step": 2440
|
| 2102 |
+
},
|
| 2103 |
+
{
|
| 2104 |
+
"epoch": 2.5980911983032873,
|
| 2105 |
+
"grad_norm": 1.6822096109390259,
|
| 2106 |
+
"learning_rate": 6.698480028278544e-06,
|
| 2107 |
+
"loss": 0.2396,
|
| 2108 |
+
"step": 2450
|
| 2109 |
+
},
|
| 2110 |
+
{
|
| 2111 |
+
"epoch": 2.5980911983032873,
|
| 2112 |
+
"eval_loss": 0.7170704007148743,
|
| 2113 |
+
"eval_runtime": 11.8266,
|
| 2114 |
+
"eval_samples_per_second": 40.587,
|
| 2115 |
+
"eval_steps_per_second": 2.537,
|
| 2116 |
+
"step": 2450
|
| 2117 |
+
},
|
| 2118 |
+
{
|
| 2119 |
+
"epoch": 2.608695652173913,
|
| 2120 |
+
"grad_norm": 1.7476707696914673,
|
| 2121 |
+
"learning_rate": 6.521739130434783e-06,
|
| 2122 |
+
"loss": 0.2436,
|
| 2123 |
+
"step": 2460
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 2.6193001060445384,
|
| 2127 |
+
"grad_norm": 1.7933710813522339,
|
| 2128 |
+
"learning_rate": 6.344998232591022e-06,
|
| 2129 |
+
"loss": 0.233,
|
| 2130 |
+
"step": 2470
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 2.6299045599151643,
|
| 2134 |
+
"grad_norm": 1.711031198501587,
|
| 2135 |
+
"learning_rate": 6.16825733474726e-06,
|
| 2136 |
+
"loss": 0.2369,
|
| 2137 |
+
"step": 2480
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 2.64050901378579,
|
| 2141 |
+
"grad_norm": 1.534862995147705,
|
| 2142 |
+
"learning_rate": 5.9915164369035e-06,
|
| 2143 |
+
"loss": 0.2405,
|
| 2144 |
+
"step": 2490
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 2.6511134676564154,
|
| 2148 |
+
"grad_norm": 1.6238676309585571,
|
| 2149 |
+
"learning_rate": 5.814775539059739e-06,
|
| 2150 |
+
"loss": 0.2325,
|
| 2151 |
+
"step": 2500
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 2.6511134676564154,
|
| 2155 |
+
"eval_loss": 0.7247666716575623,
|
| 2156 |
+
"eval_runtime": 11.7989,
|
| 2157 |
+
"eval_samples_per_second": 40.682,
|
| 2158 |
+
"eval_steps_per_second": 2.543,
|
| 2159 |
+
"step": 2500
|
| 2160 |
+
}
|
| 2161 |
+
],
|
| 2162 |
+
"logging_steps": 10,
|
| 2163 |
+
"max_steps": 2829,
|
| 2164 |
+
"num_input_tokens_seen": 0,
|
| 2165 |
+
"num_train_epochs": 3,
|
| 2166 |
+
"save_steps": 100,
|
| 2167 |
+
"stateful_callbacks": {
|
| 2168 |
+
"TrainerControl": {
|
| 2169 |
+
"args": {
|
| 2170 |
+
"should_epoch_stop": false,
|
| 2171 |
+
"should_evaluate": false,
|
| 2172 |
+
"should_log": false,
|
| 2173 |
+
"should_save": true,
|
| 2174 |
+
"should_training_stop": false
|
| 2175 |
+
},
|
| 2176 |
+
"attributes": {}
|
| 2177 |
+
}
|
| 2178 |
+
},
|
| 2179 |
+
"total_flos": 2.578514127786885e+17,
|
| 2180 |
+
"train_batch_size": 16,
|
| 2181 |
+
"trial_name": null,
|
| 2182 |
+
"trial_params": null
|
| 2183 |
+
}
|
checkpoint-2500/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:872835407be2a0a95214d9cc3b7966660b3e25cbfda85f13ed9adad96c071793
|
| 3 |
+
size 5880
|
checkpoint-2500/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|