Upload 11 files
Browse files- README.md +202 -0
- adapter_config.json +30 -0
- adapter_model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +6 -0
- spiece.model +3 -0
- tokenizer_config.json +47 -0
- trainer_state.json +2441 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: AI-Sweden-Models/gpt-sw3-6.7b-v2
|
| 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 0.13.0
|
adapter_config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "AI-Sweden-Models/gpt-sw3-6.7b-v2",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 16,
|
| 14 |
+
"lora_dropout": 0.05,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 16,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"c_attn",
|
| 24 |
+
"c_proj",
|
| 25 |
+
"c_fc"
|
| 26 |
+
],
|
| 27 |
+
"task_type": "CAUSAL_LM",
|
| 28 |
+
"use_dora": false,
|
| 29 |
+
"use_rslora": false
|
| 30 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d7459e6f06f617230aec563dcd37ab106c4bd7ca027a4fdd7f118f6a13e00b02
|
| 3 |
+
size 134251152
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0dc63dc6582ed72a8c54ee2b648953464edc0590f2c8716d4d3479251a88c639
|
| 3 |
+
size 268650821
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f1a6a7b3a05edd1aa60a0a113a03dd8eaf8587365d04eda8c86c534ce491b855
|
| 3 |
+
size 14575
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7f4edc55e3da6801fc049b132aa9b77ec6f52d51437b3555f8562647f677f14f
|
| 3 |
+
size 627
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"eos_token": "<|endoftext|>",
|
| 4 |
+
"pad_token": "<pad>",
|
| 5 |
+
"unk_token": "<unk>"
|
| 6 |
+
}
|
spiece.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f4bda2cd84ff0ac659cda40e746c55f47ee3e57cf18471670ad26998c28be52d
|
| 3 |
+
size 1071955
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<pad>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<unk>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "<s>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "<|endoftext|>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
}
|
| 35 |
+
},
|
| 36 |
+
"bos_token": "<s>",
|
| 37 |
+
"clean_up_tokenization_spaces": true,
|
| 38 |
+
"do_lower_case": false,
|
| 39 |
+
"eos_token": "<|endoftext|>",
|
| 40 |
+
"keep_accents": false,
|
| 41 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 42 |
+
"pad_token": "<pad>",
|
| 43 |
+
"remove_space": false,
|
| 44 |
+
"sp_model_kwargs": {},
|
| 45 |
+
"tokenizer_class": "GPTSw3Tokenizer",
|
| 46 |
+
"unk_token": "<unk>"
|
| 47 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2441 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.9676393598144797,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 28000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.007027283427908856,
|
| 13 |
+
"grad_norm": 0.45293834805488586,
|
| 14 |
+
"learning_rate": 0.0001995548787630315,
|
| 15 |
+
"loss": 0.8897,
|
| 16 |
+
"step": 100
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.014054566855817713,
|
| 20 |
+
"grad_norm": 0.5474397540092468,
|
| 21 |
+
"learning_rate": 0.00019908633009253836,
|
| 22 |
+
"loss": 0.7035,
|
| 23 |
+
"step": 200
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.02108185028372657,
|
| 27 |
+
"grad_norm": 0.38776981830596924,
|
| 28 |
+
"learning_rate": 0.00019861778142204523,
|
| 29 |
+
"loss": 0.6916,
|
| 30 |
+
"step": 300
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.028109133711635426,
|
| 34 |
+
"grad_norm": 0.39987438917160034,
|
| 35 |
+
"learning_rate": 0.00019814923275155208,
|
| 36 |
+
"loss": 0.6724,
|
| 37 |
+
"step": 400
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.03513641713954428,
|
| 41 |
+
"grad_norm": 0.4090868830680847,
|
| 42 |
+
"learning_rate": 0.00019768068408105893,
|
| 43 |
+
"loss": 0.6842,
|
| 44 |
+
"step": 500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.03513641713954428,
|
| 48 |
+
"eval_loss": 0.6561594605445862,
|
| 49 |
+
"eval_runtime": 192.4196,
|
| 50 |
+
"eval_samples_per_second": 65.737,
|
| 51 |
+
"eval_steps_per_second": 8.222,
|
| 52 |
+
"step": 500
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.04216370056745314,
|
| 56 |
+
"grad_norm": 0.46690303087234497,
|
| 57 |
+
"learning_rate": 0.00019721213541056578,
|
| 58 |
+
"loss": 0.6738,
|
| 59 |
+
"step": 600
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.049190983995361995,
|
| 63 |
+
"grad_norm": 0.48969191312789917,
|
| 64 |
+
"learning_rate": 0.00019674358674007263,
|
| 65 |
+
"loss": 0.662,
|
| 66 |
+
"step": 700
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.05621826742327085,
|
| 70 |
+
"grad_norm": 0.3667367100715637,
|
| 71 |
+
"learning_rate": 0.00019627503806957949,
|
| 72 |
+
"loss": 0.6646,
|
| 73 |
+
"step": 800
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.06324555085117971,
|
| 77 |
+
"grad_norm": 0.40032121539115906,
|
| 78 |
+
"learning_rate": 0.00019580648939908634,
|
| 79 |
+
"loss": 0.6564,
|
| 80 |
+
"step": 900
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.07027283427908856,
|
| 84 |
+
"grad_norm": 0.3847985565662384,
|
| 85 |
+
"learning_rate": 0.00019533794072859319,
|
| 86 |
+
"loss": 0.6511,
|
| 87 |
+
"step": 1000
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.07027283427908856,
|
| 91 |
+
"eval_loss": 0.6426891684532166,
|
| 92 |
+
"eval_runtime": 192.091,
|
| 93 |
+
"eval_samples_per_second": 65.849,
|
| 94 |
+
"eval_steps_per_second": 8.236,
|
| 95 |
+
"step": 1000
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.07730011770699742,
|
| 99 |
+
"grad_norm": 0.40991073846817017,
|
| 100 |
+
"learning_rate": 0.00019486939205810004,
|
| 101 |
+
"loss": 0.6495,
|
| 102 |
+
"step": 1100
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.08432740113490628,
|
| 106 |
+
"grad_norm": 0.44681239128112793,
|
| 107 |
+
"learning_rate": 0.00019440084338760689,
|
| 108 |
+
"loss": 0.6516,
|
| 109 |
+
"step": 1200
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.09135468456281513,
|
| 113 |
+
"grad_norm": 0.4842969477176666,
|
| 114 |
+
"learning_rate": 0.00019393229471711376,
|
| 115 |
+
"loss": 0.6614,
|
| 116 |
+
"step": 1300
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.09838196799072399,
|
| 120 |
+
"grad_norm": 0.4123075008392334,
|
| 121 |
+
"learning_rate": 0.00019346374604662061,
|
| 122 |
+
"loss": 0.636,
|
| 123 |
+
"step": 1400
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.10540925141863285,
|
| 127 |
+
"grad_norm": 0.45350509881973267,
|
| 128 |
+
"learning_rate": 0.00019299519737612746,
|
| 129 |
+
"loss": 0.6429,
|
| 130 |
+
"step": 1500
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.10540925141863285,
|
| 134 |
+
"eval_loss": 0.6345575451850891,
|
| 135 |
+
"eval_runtime": 192.5238,
|
| 136 |
+
"eval_samples_per_second": 65.701,
|
| 137 |
+
"eval_steps_per_second": 8.217,
|
| 138 |
+
"step": 1500
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.1124365348465417,
|
| 142 |
+
"grad_norm": 0.36109960079193115,
|
| 143 |
+
"learning_rate": 0.00019252664870563431,
|
| 144 |
+
"loss": 0.6542,
|
| 145 |
+
"step": 1600
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.11946381827445056,
|
| 149 |
+
"grad_norm": 0.3524057865142822,
|
| 150 |
+
"learning_rate": 0.00019205810003514116,
|
| 151 |
+
"loss": 0.6287,
|
| 152 |
+
"step": 1700
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.12649110170235942,
|
| 156 |
+
"grad_norm": 0.42591190338134766,
|
| 157 |
+
"learning_rate": 0.00019158955136464801,
|
| 158 |
+
"loss": 0.645,
|
| 159 |
+
"step": 1800
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.13351838513026826,
|
| 163 |
+
"grad_norm": 0.43938347697257996,
|
| 164 |
+
"learning_rate": 0.00019112100269415486,
|
| 165 |
+
"loss": 0.6444,
|
| 166 |
+
"step": 1900
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 0.14054566855817713,
|
| 170 |
+
"grad_norm": 0.44198718667030334,
|
| 171 |
+
"learning_rate": 0.00019065245402366172,
|
| 172 |
+
"loss": 0.643,
|
| 173 |
+
"step": 2000
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 0.14054566855817713,
|
| 177 |
+
"eval_loss": 0.6290879249572754,
|
| 178 |
+
"eval_runtime": 192.8097,
|
| 179 |
+
"eval_samples_per_second": 65.604,
|
| 180 |
+
"eval_steps_per_second": 8.205,
|
| 181 |
+
"step": 2000
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.14757295198608597,
|
| 185 |
+
"grad_norm": 0.39245936274528503,
|
| 186 |
+
"learning_rate": 0.00019018390535316857,
|
| 187 |
+
"loss": 0.65,
|
| 188 |
+
"step": 2100
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.15460023541399484,
|
| 192 |
+
"grad_norm": 0.46238473057746887,
|
| 193 |
+
"learning_rate": 0.00018971535668267542,
|
| 194 |
+
"loss": 0.6557,
|
| 195 |
+
"step": 2200
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.16162751884190368,
|
| 199 |
+
"grad_norm": 0.5030249357223511,
|
| 200 |
+
"learning_rate": 0.00018924680801218227,
|
| 201 |
+
"loss": 0.6384,
|
| 202 |
+
"step": 2300
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.16865480226981255,
|
| 206 |
+
"grad_norm": 0.4010857343673706,
|
| 207 |
+
"learning_rate": 0.00018877825934168914,
|
| 208 |
+
"loss": 0.6424,
|
| 209 |
+
"step": 2400
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.1756820856977214,
|
| 213 |
+
"grad_norm": 0.43222537636756897,
|
| 214 |
+
"learning_rate": 0.000188309710671196,
|
| 215 |
+
"loss": 0.6217,
|
| 216 |
+
"step": 2500
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 0.1756820856977214,
|
| 220 |
+
"eval_loss": 0.6259664297103882,
|
| 221 |
+
"eval_runtime": 196.2284,
|
| 222 |
+
"eval_samples_per_second": 64.461,
|
| 223 |
+
"eval_steps_per_second": 8.062,
|
| 224 |
+
"step": 2500
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.18270936912563027,
|
| 228 |
+
"grad_norm": 0.5106024742126465,
|
| 229 |
+
"learning_rate": 0.00018784116200070284,
|
| 230 |
+
"loss": 0.6367,
|
| 231 |
+
"step": 2600
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.1897366525535391,
|
| 235 |
+
"grad_norm": 0.463365763425827,
|
| 236 |
+
"learning_rate": 0.00018737261333020967,
|
| 237 |
+
"loss": 0.6392,
|
| 238 |
+
"step": 2700
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 0.19676393598144798,
|
| 242 |
+
"grad_norm": 0.46747493743896484,
|
| 243 |
+
"learning_rate": 0.00018690406465971652,
|
| 244 |
+
"loss": 0.6221,
|
| 245 |
+
"step": 2800
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 0.20379121940935682,
|
| 249 |
+
"grad_norm": 0.5577239394187927,
|
| 250 |
+
"learning_rate": 0.0001864355159892234,
|
| 251 |
+
"loss": 0.6313,
|
| 252 |
+
"step": 2900
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 0.2108185028372657,
|
| 256 |
+
"grad_norm": 0.3764529228210449,
|
| 257 |
+
"learning_rate": 0.00018596696731873024,
|
| 258 |
+
"loss": 0.6309,
|
| 259 |
+
"step": 3000
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 0.2108185028372657,
|
| 263 |
+
"eval_loss": 0.61882084608078,
|
| 264 |
+
"eval_runtime": 191.698,
|
| 265 |
+
"eval_samples_per_second": 65.984,
|
| 266 |
+
"eval_steps_per_second": 8.253,
|
| 267 |
+
"step": 3000
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.21784578626517453,
|
| 271 |
+
"grad_norm": 0.45881420373916626,
|
| 272 |
+
"learning_rate": 0.0001854984186482371,
|
| 273 |
+
"loss": 0.6177,
|
| 274 |
+
"step": 3100
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.2248730696930834,
|
| 278 |
+
"grad_norm": 0.366277277469635,
|
| 279 |
+
"learning_rate": 0.00018502986997774394,
|
| 280 |
+
"loss": 0.6217,
|
| 281 |
+
"step": 3200
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 0.23190035312099225,
|
| 285 |
+
"grad_norm": 0.5218221545219421,
|
| 286 |
+
"learning_rate": 0.0001845613213072508,
|
| 287 |
+
"loss": 0.6085,
|
| 288 |
+
"step": 3300
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 0.23892763654890112,
|
| 292 |
+
"grad_norm": 0.42059990763664246,
|
| 293 |
+
"learning_rate": 0.00018409277263675767,
|
| 294 |
+
"loss": 0.624,
|
| 295 |
+
"step": 3400
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 0.24595491997680996,
|
| 299 |
+
"grad_norm": 0.4570040702819824,
|
| 300 |
+
"learning_rate": 0.0001836242239662645,
|
| 301 |
+
"loss": 0.6151,
|
| 302 |
+
"step": 3500
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.24595491997680996,
|
| 306 |
+
"eval_loss": 0.6193254590034485,
|
| 307 |
+
"eval_runtime": 191.8558,
|
| 308 |
+
"eval_samples_per_second": 65.93,
|
| 309 |
+
"eval_steps_per_second": 8.246,
|
| 310 |
+
"step": 3500
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.25298220340471883,
|
| 314 |
+
"grad_norm": 0.42353853583335876,
|
| 315 |
+
"learning_rate": 0.00018315567529577135,
|
| 316 |
+
"loss": 0.6245,
|
| 317 |
+
"step": 3600
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.2600094868326277,
|
| 321 |
+
"grad_norm": 0.4249242842197418,
|
| 322 |
+
"learning_rate": 0.0001826871266252782,
|
| 323 |
+
"loss": 0.6323,
|
| 324 |
+
"step": 3700
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.2670367702605365,
|
| 328 |
+
"grad_norm": 0.48913854360580444,
|
| 329 |
+
"learning_rate": 0.00018221857795478505,
|
| 330 |
+
"loss": 0.6393,
|
| 331 |
+
"step": 3800
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.2740640536884454,
|
| 335 |
+
"grad_norm": 0.40342265367507935,
|
| 336 |
+
"learning_rate": 0.00018175002928429192,
|
| 337 |
+
"loss": 0.6241,
|
| 338 |
+
"step": 3900
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.28109133711635426,
|
| 342 |
+
"grad_norm": 0.46278470754623413,
|
| 343 |
+
"learning_rate": 0.00018128148061379877,
|
| 344 |
+
"loss": 0.6235,
|
| 345 |
+
"step": 4000
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.28109133711635426,
|
| 349 |
+
"eval_loss": 0.6143574714660645,
|
| 350 |
+
"eval_runtime": 192.2015,
|
| 351 |
+
"eval_samples_per_second": 65.811,
|
| 352 |
+
"eval_steps_per_second": 8.231,
|
| 353 |
+
"step": 4000
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.2881186205442631,
|
| 357 |
+
"grad_norm": 0.5402960777282715,
|
| 358 |
+
"learning_rate": 0.00018081293194330562,
|
| 359 |
+
"loss": 0.6106,
|
| 360 |
+
"step": 4100
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.29514590397217194,
|
| 364 |
+
"grad_norm": 0.49978354573249817,
|
| 365 |
+
"learning_rate": 0.00018034438327281247,
|
| 366 |
+
"loss": 0.6316,
|
| 367 |
+
"step": 4200
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.3021731874000808,
|
| 371 |
+
"grad_norm": 0.4171115458011627,
|
| 372 |
+
"learning_rate": 0.00017987583460231932,
|
| 373 |
+
"loss": 0.6329,
|
| 374 |
+
"step": 4300
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.3092004708279897,
|
| 378 |
+
"grad_norm": 0.48519599437713623,
|
| 379 |
+
"learning_rate": 0.00017940728593182617,
|
| 380 |
+
"loss": 0.6204,
|
| 381 |
+
"step": 4400
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.31622775425589855,
|
| 385 |
+
"grad_norm": 0.4046633243560791,
|
| 386 |
+
"learning_rate": 0.00017893873726133302,
|
| 387 |
+
"loss": 0.6291,
|
| 388 |
+
"step": 4500
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.31622775425589855,
|
| 392 |
+
"eval_loss": 0.6102128028869629,
|
| 393 |
+
"eval_runtime": 194.9353,
|
| 394 |
+
"eval_samples_per_second": 64.888,
|
| 395 |
+
"eval_steps_per_second": 8.116,
|
| 396 |
+
"step": 4500
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.32325503768380737,
|
| 400 |
+
"grad_norm": 0.5373474359512329,
|
| 401 |
+
"learning_rate": 0.00017847018859083988,
|
| 402 |
+
"loss": 0.6137,
|
| 403 |
+
"step": 4600
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 0.33028232111171624,
|
| 407 |
+
"grad_norm": 0.45230546593666077,
|
| 408 |
+
"learning_rate": 0.00017800163992034673,
|
| 409 |
+
"loss": 0.6254,
|
| 410 |
+
"step": 4700
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.3373096045396251,
|
| 414 |
+
"grad_norm": 0.5114957094192505,
|
| 415 |
+
"learning_rate": 0.00017753309124985358,
|
| 416 |
+
"loss": 0.6256,
|
| 417 |
+
"step": 4800
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.344336887967534,
|
| 421 |
+
"grad_norm": 0.5685564279556274,
|
| 422 |
+
"learning_rate": 0.00017706454257936045,
|
| 423 |
+
"loss": 0.6055,
|
| 424 |
+
"step": 4900
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 0.3513641713954428,
|
| 428 |
+
"grad_norm": 0.47926437854766846,
|
| 429 |
+
"learning_rate": 0.0001765959939088673,
|
| 430 |
+
"loss": 0.6151,
|
| 431 |
+
"step": 5000
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 0.3513641713954428,
|
| 435 |
+
"eval_loss": 0.6096778512001038,
|
| 436 |
+
"eval_runtime": 191.152,
|
| 437 |
+
"eval_samples_per_second": 66.172,
|
| 438 |
+
"eval_steps_per_second": 8.276,
|
| 439 |
+
"step": 5000
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 0.35839145482335166,
|
| 443 |
+
"grad_norm": 0.4746282696723938,
|
| 444 |
+
"learning_rate": 0.00017612744523837415,
|
| 445 |
+
"loss": 0.6122,
|
| 446 |
+
"step": 5100
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 0.36541873825126053,
|
| 450 |
+
"grad_norm": 0.43606746196746826,
|
| 451 |
+
"learning_rate": 0.000175658896567881,
|
| 452 |
+
"loss": 0.6087,
|
| 453 |
+
"step": 5200
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.37244602167916935,
|
| 457 |
+
"grad_norm": 0.6463629603385925,
|
| 458 |
+
"learning_rate": 0.00017519034789738785,
|
| 459 |
+
"loss": 0.6341,
|
| 460 |
+
"step": 5300
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 0.3794733051070782,
|
| 464 |
+
"grad_norm": 0.5722381472587585,
|
| 465 |
+
"learning_rate": 0.0001747217992268947,
|
| 466 |
+
"loss": 0.6224,
|
| 467 |
+
"step": 5400
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 0.3865005885349871,
|
| 471 |
+
"grad_norm": 0.45890772342681885,
|
| 472 |
+
"learning_rate": 0.00017425325055640155,
|
| 473 |
+
"loss": 0.611,
|
| 474 |
+
"step": 5500
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.3865005885349871,
|
| 478 |
+
"eval_loss": 0.6061792969703674,
|
| 479 |
+
"eval_runtime": 191.541,
|
| 480 |
+
"eval_samples_per_second": 66.038,
|
| 481 |
+
"eval_steps_per_second": 8.259,
|
| 482 |
+
"step": 5500
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 0.39352787196289596,
|
| 486 |
+
"grad_norm": 0.32096725702285767,
|
| 487 |
+
"learning_rate": 0.0001737847018859084,
|
| 488 |
+
"loss": 0.6031,
|
| 489 |
+
"step": 5600
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.4005551553908048,
|
| 493 |
+
"grad_norm": 0.46782708168029785,
|
| 494 |
+
"learning_rate": 0.00017331615321541525,
|
| 495 |
+
"loss": 0.5948,
|
| 496 |
+
"step": 5700
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 0.40758243881871364,
|
| 500 |
+
"grad_norm": 0.5056571364402771,
|
| 501 |
+
"learning_rate": 0.0001728476045449221,
|
| 502 |
+
"loss": 0.6142,
|
| 503 |
+
"step": 5800
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 0.4146097222466225,
|
| 507 |
+
"grad_norm": 0.5338990688323975,
|
| 508 |
+
"learning_rate": 0.00017237905587442898,
|
| 509 |
+
"loss": 0.6235,
|
| 510 |
+
"step": 5900
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 0.4216370056745314,
|
| 514 |
+
"grad_norm": 0.5611251592636108,
|
| 515 |
+
"learning_rate": 0.00017191050720393583,
|
| 516 |
+
"loss": 0.6064,
|
| 517 |
+
"step": 6000
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"epoch": 0.4216370056745314,
|
| 521 |
+
"eval_loss": 0.6039415001869202,
|
| 522 |
+
"eval_runtime": 192.9342,
|
| 523 |
+
"eval_samples_per_second": 65.561,
|
| 524 |
+
"eval_steps_per_second": 8.2,
|
| 525 |
+
"step": 6000
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.4286642891024402,
|
| 529 |
+
"grad_norm": 0.34663501381874084,
|
| 530 |
+
"learning_rate": 0.00017144195853344268,
|
| 531 |
+
"loss": 0.619,
|
| 532 |
+
"step": 6100
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 0.43569157253034907,
|
| 536 |
+
"grad_norm": 0.5357178449630737,
|
| 537 |
+
"learning_rate": 0.0001709734098629495,
|
| 538 |
+
"loss": 0.6148,
|
| 539 |
+
"step": 6200
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 0.44271885595825794,
|
| 543 |
+
"grad_norm": 0.49474236369132996,
|
| 544 |
+
"learning_rate": 0.00017050486119245636,
|
| 545 |
+
"loss": 0.6021,
|
| 546 |
+
"step": 6300
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 0.4497461393861668,
|
| 550 |
+
"grad_norm": 0.4276539981365204,
|
| 551 |
+
"learning_rate": 0.00017003631252196323,
|
| 552 |
+
"loss": 0.619,
|
| 553 |
+
"step": 6400
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 0.4567734228140756,
|
| 557 |
+
"grad_norm": 0.4469217360019684,
|
| 558 |
+
"learning_rate": 0.00016956776385147008,
|
| 559 |
+
"loss": 0.6044,
|
| 560 |
+
"step": 6500
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 0.4567734228140756,
|
| 564 |
+
"eval_loss": 0.6005575656890869,
|
| 565 |
+
"eval_runtime": 191.475,
|
| 566 |
+
"eval_samples_per_second": 66.061,
|
| 567 |
+
"eval_steps_per_second": 8.262,
|
| 568 |
+
"step": 6500
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 0.4638007062419845,
|
| 572 |
+
"grad_norm": 0.4944908916950226,
|
| 573 |
+
"learning_rate": 0.00016909921518097693,
|
| 574 |
+
"loss": 0.5871,
|
| 575 |
+
"step": 6600
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 0.47082798966989337,
|
| 579 |
+
"grad_norm": 0.6753395795822144,
|
| 580 |
+
"learning_rate": 0.00016863066651048378,
|
| 581 |
+
"loss": 0.6058,
|
| 582 |
+
"step": 6700
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 0.47785527309780224,
|
| 586 |
+
"grad_norm": 0.4985552132129669,
|
| 587 |
+
"learning_rate": 0.00016816211783999063,
|
| 588 |
+
"loss": 0.5935,
|
| 589 |
+
"step": 6800
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 0.48488255652571105,
|
| 593 |
+
"grad_norm": 0.47422492504119873,
|
| 594 |
+
"learning_rate": 0.0001676935691694975,
|
| 595 |
+
"loss": 0.6138,
|
| 596 |
+
"step": 6900
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 0.4919098399536199,
|
| 600 |
+
"grad_norm": 0.4696919620037079,
|
| 601 |
+
"learning_rate": 0.00016722502049900433,
|
| 602 |
+
"loss": 0.595,
|
| 603 |
+
"step": 7000
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 0.4919098399536199,
|
| 607 |
+
"eval_loss": 0.5999007225036621,
|
| 608 |
+
"eval_runtime": 192.1728,
|
| 609 |
+
"eval_samples_per_second": 65.821,
|
| 610 |
+
"eval_steps_per_second": 8.232,
|
| 611 |
+
"step": 7000
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.4989371233815288,
|
| 615 |
+
"grad_norm": 0.5600836873054504,
|
| 616 |
+
"learning_rate": 0.00016675647182851119,
|
| 617 |
+
"loss": 0.6183,
|
| 618 |
+
"step": 7100
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.5059644068094377,
|
| 622 |
+
"grad_norm": 0.600051760673523,
|
| 623 |
+
"learning_rate": 0.00016628792315801804,
|
| 624 |
+
"loss": 0.6035,
|
| 625 |
+
"step": 7200
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.5129916902373465,
|
| 629 |
+
"grad_norm": 0.4427150785923004,
|
| 630 |
+
"learning_rate": 0.00016581937448752489,
|
| 631 |
+
"loss": 0.5925,
|
| 632 |
+
"step": 7300
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.5200189736652554,
|
| 636 |
+
"grad_norm": 0.5799112319946289,
|
| 637 |
+
"learning_rate": 0.00016535082581703176,
|
| 638 |
+
"loss": 0.5938,
|
| 639 |
+
"step": 7400
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.5270462570931642,
|
| 643 |
+
"grad_norm": 0.5303583741188049,
|
| 644 |
+
"learning_rate": 0.0001648822771465386,
|
| 645 |
+
"loss": 0.6041,
|
| 646 |
+
"step": 7500
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.5270462570931642,
|
| 650 |
+
"eval_loss": 0.5995006561279297,
|
| 651 |
+
"eval_runtime": 192.153,
|
| 652 |
+
"eval_samples_per_second": 65.828,
|
| 653 |
+
"eval_steps_per_second": 8.233,
|
| 654 |
+
"step": 7500
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.534073540521073,
|
| 658 |
+
"grad_norm": 0.5901041030883789,
|
| 659 |
+
"learning_rate": 0.00016441372847604546,
|
| 660 |
+
"loss": 0.6089,
|
| 661 |
+
"step": 7600
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.541100823948982,
|
| 665 |
+
"grad_norm": 0.4662562608718872,
|
| 666 |
+
"learning_rate": 0.00016394517980555231,
|
| 667 |
+
"loss": 0.6041,
|
| 668 |
+
"step": 7700
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.5481281073768908,
|
| 672 |
+
"grad_norm": 0.578330934047699,
|
| 673 |
+
"learning_rate": 0.00016347663113505916,
|
| 674 |
+
"loss": 0.6042,
|
| 675 |
+
"step": 7800
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.5551553908047996,
|
| 679 |
+
"grad_norm": 0.4467080533504486,
|
| 680 |
+
"learning_rate": 0.00016300808246456601,
|
| 681 |
+
"loss": 0.6106,
|
| 682 |
+
"step": 7900
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.5621826742327085,
|
| 686 |
+
"grad_norm": 0.5268563628196716,
|
| 687 |
+
"learning_rate": 0.00016253953379407286,
|
| 688 |
+
"loss": 0.6064,
|
| 689 |
+
"step": 8000
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.5621826742327085,
|
| 693 |
+
"eval_loss": 0.5974312424659729,
|
| 694 |
+
"eval_runtime": 191.7777,
|
| 695 |
+
"eval_samples_per_second": 65.957,
|
| 696 |
+
"eval_steps_per_second": 8.249,
|
| 697 |
+
"step": 8000
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.5692099576606173,
|
| 701 |
+
"grad_norm": 0.5392386317253113,
|
| 702 |
+
"learning_rate": 0.00016207098512357971,
|
| 703 |
+
"loss": 0.5957,
|
| 704 |
+
"step": 8100
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.5762372410885263,
|
| 708 |
+
"grad_norm": 0.4071332812309265,
|
| 709 |
+
"learning_rate": 0.00016160243645308656,
|
| 710 |
+
"loss": 0.594,
|
| 711 |
+
"step": 8200
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.5832645245164351,
|
| 715 |
+
"grad_norm": 0.49810290336608887,
|
| 716 |
+
"learning_rate": 0.00016113388778259341,
|
| 717 |
+
"loss": 0.6087,
|
| 718 |
+
"step": 8300
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 0.5902918079443439,
|
| 722 |
+
"grad_norm": 0.5486442446708679,
|
| 723 |
+
"learning_rate": 0.0001606653391121003,
|
| 724 |
+
"loss": 0.6068,
|
| 725 |
+
"step": 8400
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 0.5973190913722528,
|
| 729 |
+
"grad_norm": 0.4476531147956848,
|
| 730 |
+
"learning_rate": 0.00016019679044160714,
|
| 731 |
+
"loss": 0.6008,
|
| 732 |
+
"step": 8500
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 0.5973190913722528,
|
| 736 |
+
"eval_loss": 0.5947303175926208,
|
| 737 |
+
"eval_runtime": 191.9868,
|
| 738 |
+
"eval_samples_per_second": 65.885,
|
| 739 |
+
"eval_steps_per_second": 8.24,
|
| 740 |
+
"step": 8500
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 0.6043463748001616,
|
| 744 |
+
"grad_norm": 0.46748480200767517,
|
| 745 |
+
"learning_rate": 0.000159728241771114,
|
| 746 |
+
"loss": 0.6073,
|
| 747 |
+
"step": 8600
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.6113736582280704,
|
| 751 |
+
"grad_norm": 0.3768276870250702,
|
| 752 |
+
"learning_rate": 0.00015925969310062084,
|
| 753 |
+
"loss": 0.6025,
|
| 754 |
+
"step": 8700
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 0.6184009416559794,
|
| 758 |
+
"grad_norm": 0.4775266647338867,
|
| 759 |
+
"learning_rate": 0.0001587911444301277,
|
| 760 |
+
"loss": 0.6139,
|
| 761 |
+
"step": 8800
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 0.6254282250838882,
|
| 765 |
+
"grad_norm": 0.595317542552948,
|
| 766 |
+
"learning_rate": 0.00015832259575963452,
|
| 767 |
+
"loss": 0.606,
|
| 768 |
+
"step": 8900
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 0.6324555085117971,
|
| 772 |
+
"grad_norm": 0.5021831393241882,
|
| 773 |
+
"learning_rate": 0.0001578540470891414,
|
| 774 |
+
"loss": 0.6141,
|
| 775 |
+
"step": 9000
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 0.6324555085117971,
|
| 779 |
+
"eval_loss": 0.5933237671852112,
|
| 780 |
+
"eval_runtime": 191.7573,
|
| 781 |
+
"eval_samples_per_second": 65.964,
|
| 782 |
+
"eval_steps_per_second": 8.25,
|
| 783 |
+
"step": 9000
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 0.6394827919397059,
|
| 787 |
+
"grad_norm": 0.4338054955005646,
|
| 788 |
+
"learning_rate": 0.00015738549841864824,
|
| 789 |
+
"loss": 0.6081,
|
| 790 |
+
"step": 9100
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 0.6465100753676147,
|
| 794 |
+
"grad_norm": 0.5167454481124878,
|
| 795 |
+
"learning_rate": 0.0001569169497481551,
|
| 796 |
+
"loss": 0.5881,
|
| 797 |
+
"step": 9200
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 0.6535373587955237,
|
| 801 |
+
"grad_norm": 0.4964050054550171,
|
| 802 |
+
"learning_rate": 0.00015644840107766194,
|
| 803 |
+
"loss": 0.6227,
|
| 804 |
+
"step": 9300
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 0.6605646422234325,
|
| 808 |
+
"grad_norm": 0.5711501240730286,
|
| 809 |
+
"learning_rate": 0.0001559798524071688,
|
| 810 |
+
"loss": 0.5927,
|
| 811 |
+
"step": 9400
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 0.6675919256513413,
|
| 815 |
+
"grad_norm": 0.4459337890148163,
|
| 816 |
+
"learning_rate": 0.00015551130373667567,
|
| 817 |
+
"loss": 0.5921,
|
| 818 |
+
"step": 9500
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 0.6675919256513413,
|
| 822 |
+
"eval_loss": 0.593291163444519,
|
| 823 |
+
"eval_runtime": 191.3053,
|
| 824 |
+
"eval_samples_per_second": 66.119,
|
| 825 |
+
"eval_steps_per_second": 8.27,
|
| 826 |
+
"step": 9500
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 0.6746192090792502,
|
| 830 |
+
"grad_norm": 0.5358896255493164,
|
| 831 |
+
"learning_rate": 0.00015504275506618252,
|
| 832 |
+
"loss": 0.595,
|
| 833 |
+
"step": 9600
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 0.681646492507159,
|
| 837 |
+
"grad_norm": 0.5215060114860535,
|
| 838 |
+
"learning_rate": 0.00015457420639568935,
|
| 839 |
+
"loss": 0.6073,
|
| 840 |
+
"step": 9700
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 0.688673775935068,
|
| 844 |
+
"grad_norm": 0.43110188841819763,
|
| 845 |
+
"learning_rate": 0.0001541056577251962,
|
| 846 |
+
"loss": 0.5947,
|
| 847 |
+
"step": 9800
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 0.6957010593629768,
|
| 851 |
+
"grad_norm": 0.7894725799560547,
|
| 852 |
+
"learning_rate": 0.00015363710905470305,
|
| 853 |
+
"loss": 0.6036,
|
| 854 |
+
"step": 9900
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 0.7027283427908856,
|
| 858 |
+
"grad_norm": 0.40468016266822815,
|
| 859 |
+
"learning_rate": 0.00015316856038420992,
|
| 860 |
+
"loss": 0.5662,
|
| 861 |
+
"step": 10000
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 0.7027283427908856,
|
| 865 |
+
"eval_loss": 0.5914621949195862,
|
| 866 |
+
"eval_runtime": 191.9924,
|
| 867 |
+
"eval_samples_per_second": 65.883,
|
| 868 |
+
"eval_steps_per_second": 8.24,
|
| 869 |
+
"step": 10000
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 0.7097556262187945,
|
| 873 |
+
"grad_norm": 0.520021915435791,
|
| 874 |
+
"learning_rate": 0.00015270001171371677,
|
| 875 |
+
"loss": 0.6024,
|
| 876 |
+
"step": 10100
|
| 877 |
+
},
|
| 878 |
+
{
|
| 879 |
+
"epoch": 0.7167829096467033,
|
| 880 |
+
"grad_norm": 0.5001341700553894,
|
| 881 |
+
"learning_rate": 0.00015223146304322362,
|
| 882 |
+
"loss": 0.6039,
|
| 883 |
+
"step": 10200
|
| 884 |
+
},
|
| 885 |
+
{
|
| 886 |
+
"epoch": 0.7238101930746121,
|
| 887 |
+
"grad_norm": 0.5081097483634949,
|
| 888 |
+
"learning_rate": 0.00015176291437273047,
|
| 889 |
+
"loss": 0.5995,
|
| 890 |
+
"step": 10300
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 0.7308374765025211,
|
| 894 |
+
"grad_norm": 0.7181329131126404,
|
| 895 |
+
"learning_rate": 0.00015129436570223732,
|
| 896 |
+
"loss": 0.5885,
|
| 897 |
+
"step": 10400
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 0.7378647599304299,
|
| 901 |
+
"grad_norm": 0.5525663495063782,
|
| 902 |
+
"learning_rate": 0.00015082581703174417,
|
| 903 |
+
"loss": 0.6117,
|
| 904 |
+
"step": 10500
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"epoch": 0.7378647599304299,
|
| 908 |
+
"eval_loss": 0.5893301963806152,
|
| 909 |
+
"eval_runtime": 191.2328,
|
| 910 |
+
"eval_samples_per_second": 66.145,
|
| 911 |
+
"eval_steps_per_second": 8.273,
|
| 912 |
+
"step": 10500
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.7448920433583387,
|
| 916 |
+
"grad_norm": 0.41122502088546753,
|
| 917 |
+
"learning_rate": 0.00015035726836125102,
|
| 918 |
+
"loss": 0.6135,
|
| 919 |
+
"step": 10600
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.7519193267862476,
|
| 923 |
+
"grad_norm": 0.501287043094635,
|
| 924 |
+
"learning_rate": 0.00014988871969075787,
|
| 925 |
+
"loss": 0.6045,
|
| 926 |
+
"step": 10700
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.7589466102141564,
|
| 930 |
+
"grad_norm": 0.4683501720428467,
|
| 931 |
+
"learning_rate": 0.00014942017102026472,
|
| 932 |
+
"loss": 0.6044,
|
| 933 |
+
"step": 10800
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.7659738936420654,
|
| 937 |
+
"grad_norm": 0.5879314541816711,
|
| 938 |
+
"learning_rate": 0.00014895162234977158,
|
| 939 |
+
"loss": 0.5979,
|
| 940 |
+
"step": 10900
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.7730011770699742,
|
| 944 |
+
"grad_norm": 0.4201727509498596,
|
| 945 |
+
"learning_rate": 0.00014848307367927845,
|
| 946 |
+
"loss": 0.6133,
|
| 947 |
+
"step": 11000
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.7730011770699742,
|
| 951 |
+
"eval_loss": 0.5890333652496338,
|
| 952 |
+
"eval_runtime": 191.871,
|
| 953 |
+
"eval_samples_per_second": 65.925,
|
| 954 |
+
"eval_steps_per_second": 8.245,
|
| 955 |
+
"step": 11000
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 0.780028460497883,
|
| 959 |
+
"grad_norm": 0.4720204770565033,
|
| 960 |
+
"learning_rate": 0.0001480145250087853,
|
| 961 |
+
"loss": 0.5926,
|
| 962 |
+
"step": 11100
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.7870557439257919,
|
| 966 |
+
"grad_norm": 0.4714803695678711,
|
| 967 |
+
"learning_rate": 0.00014754597633829215,
|
| 968 |
+
"loss": 0.5936,
|
| 969 |
+
"step": 11200
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.7940830273537007,
|
| 973 |
+
"grad_norm": 0.44766145944595337,
|
| 974 |
+
"learning_rate": 0.000147077427667799,
|
| 975 |
+
"loss": 0.5898,
|
| 976 |
+
"step": 11300
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 0.8011103107816095,
|
| 980 |
+
"grad_norm": 0.5793395638465881,
|
| 981 |
+
"learning_rate": 0.00014660887899730585,
|
| 982 |
+
"loss": 0.5792,
|
| 983 |
+
"step": 11400
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 0.8081375942095185,
|
| 987 |
+
"grad_norm": 0.5724961757659912,
|
| 988 |
+
"learning_rate": 0.0001461403303268127,
|
| 989 |
+
"loss": 0.5976,
|
| 990 |
+
"step": 11500
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 0.8081375942095185,
|
| 994 |
+
"eval_loss": 0.5884692072868347,
|
| 995 |
+
"eval_runtime": 192.9015,
|
| 996 |
+
"eval_samples_per_second": 65.572,
|
| 997 |
+
"eval_steps_per_second": 8.201,
|
| 998 |
+
"step": 11500
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 0.8151648776374273,
|
| 1002 |
+
"grad_norm": 0.4588712751865387,
|
| 1003 |
+
"learning_rate": 0.00014567178165631955,
|
| 1004 |
+
"loss": 0.5876,
|
| 1005 |
+
"step": 11600
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 0.8221921610653362,
|
| 1009 |
+
"grad_norm": 0.5474816560745239,
|
| 1010 |
+
"learning_rate": 0.0001452032329858264,
|
| 1011 |
+
"loss": 0.6004,
|
| 1012 |
+
"step": 11700
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"epoch": 0.829219444493245,
|
| 1016 |
+
"grad_norm": 0.480760395526886,
|
| 1017 |
+
"learning_rate": 0.00014473468431533325,
|
| 1018 |
+
"loss": 0.6027,
|
| 1019 |
+
"step": 11800
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 0.8362467279211538,
|
| 1023 |
+
"grad_norm": 0.44635719060897827,
|
| 1024 |
+
"learning_rate": 0.0001442661356448401,
|
| 1025 |
+
"loss": 0.5955,
|
| 1026 |
+
"step": 11900
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 0.8432740113490628,
|
| 1030 |
+
"grad_norm": 0.370127409696579,
|
| 1031 |
+
"learning_rate": 0.00014379758697434698,
|
| 1032 |
+
"loss": 0.5873,
|
| 1033 |
+
"step": 12000
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 0.8432740113490628,
|
| 1037 |
+
"eval_loss": 0.5867401361465454,
|
| 1038 |
+
"eval_runtime": 191.0689,
|
| 1039 |
+
"eval_samples_per_second": 66.201,
|
| 1040 |
+
"eval_steps_per_second": 8.28,
|
| 1041 |
+
"step": 12000
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 0.8503012947769716,
|
| 1045 |
+
"grad_norm": 0.5330467224121094,
|
| 1046 |
+
"learning_rate": 0.00014332903830385383,
|
| 1047 |
+
"loss": 0.6036,
|
| 1048 |
+
"step": 12100
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 0.8573285782048804,
|
| 1052 |
+
"grad_norm": 0.516147255897522,
|
| 1053 |
+
"learning_rate": 0.00014286048963336068,
|
| 1054 |
+
"loss": 0.5808,
|
| 1055 |
+
"step": 12200
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 0.8643558616327893,
|
| 1059 |
+
"grad_norm": 0.5745691061019897,
|
| 1060 |
+
"learning_rate": 0.00014239194096286753,
|
| 1061 |
+
"loss": 0.6026,
|
| 1062 |
+
"step": 12300
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 0.8713831450606981,
|
| 1066 |
+
"grad_norm": 0.5167753100395203,
|
| 1067 |
+
"learning_rate": 0.00014192339229237436,
|
| 1068 |
+
"loss": 0.5858,
|
| 1069 |
+
"step": 12400
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 0.8784104284886071,
|
| 1073 |
+
"grad_norm": 0.644183874130249,
|
| 1074 |
+
"learning_rate": 0.00014145484362188123,
|
| 1075 |
+
"loss": 0.6009,
|
| 1076 |
+
"step": 12500
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 0.8784104284886071,
|
| 1080 |
+
"eval_loss": 0.585637629032135,
|
| 1081 |
+
"eval_runtime": 192.0709,
|
| 1082 |
+
"eval_samples_per_second": 65.856,
|
| 1083 |
+
"eval_steps_per_second": 8.237,
|
| 1084 |
+
"step": 12500
|
| 1085 |
+
},
|
| 1086 |
+
{
|
| 1087 |
+
"epoch": 0.8854377119165159,
|
| 1088 |
+
"grad_norm": 0.5942461490631104,
|
| 1089 |
+
"learning_rate": 0.00014098629495138808,
|
| 1090 |
+
"loss": 0.5872,
|
| 1091 |
+
"step": 12600
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.8924649953444247,
|
| 1095 |
+
"grad_norm": 0.5303371548652649,
|
| 1096 |
+
"learning_rate": 0.00014051774628089493,
|
| 1097 |
+
"loss": 0.603,
|
| 1098 |
+
"step": 12700
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.8994922787723336,
|
| 1102 |
+
"grad_norm": 0.6340320706367493,
|
| 1103 |
+
"learning_rate": 0.00014004919761040178,
|
| 1104 |
+
"loss": 0.5967,
|
| 1105 |
+
"step": 12800
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.9065195622002424,
|
| 1109 |
+
"grad_norm": 0.3721257150173187,
|
| 1110 |
+
"learning_rate": 0.00013958064893990863,
|
| 1111 |
+
"loss": 0.5951,
|
| 1112 |
+
"step": 12900
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.9135468456281512,
|
| 1116 |
+
"grad_norm": 0.5798757672309875,
|
| 1117 |
+
"learning_rate": 0.0001391121002694155,
|
| 1118 |
+
"loss": 0.5872,
|
| 1119 |
+
"step": 13000
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.9135468456281512,
|
| 1123 |
+
"eval_loss": 0.5851631164550781,
|
| 1124 |
+
"eval_runtime": 191.7607,
|
| 1125 |
+
"eval_samples_per_second": 65.962,
|
| 1126 |
+
"eval_steps_per_second": 8.25,
|
| 1127 |
+
"step": 13000
|
| 1128 |
+
},
|
| 1129 |
+
{
|
| 1130 |
+
"epoch": 0.9205741290560602,
|
| 1131 |
+
"grad_norm": 0.49079081416130066,
|
| 1132 |
+
"learning_rate": 0.00013864355159892236,
|
| 1133 |
+
"loss": 0.5945,
|
| 1134 |
+
"step": 13100
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 0.927601412483969,
|
| 1138 |
+
"grad_norm": 0.6511490941047668,
|
| 1139 |
+
"learning_rate": 0.00013817500292842918,
|
| 1140 |
+
"loss": 0.5967,
|
| 1141 |
+
"step": 13200
|
| 1142 |
+
},
|
| 1143 |
+
{
|
| 1144 |
+
"epoch": 0.9346286959118779,
|
| 1145 |
+
"grad_norm": 0.6914525032043457,
|
| 1146 |
+
"learning_rate": 0.00013770645425793603,
|
| 1147 |
+
"loss": 0.595,
|
| 1148 |
+
"step": 13300
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 0.9416559793397867,
|
| 1152 |
+
"grad_norm": 0.5525299310684204,
|
| 1153 |
+
"learning_rate": 0.00013723790558744289,
|
| 1154 |
+
"loss": 0.5994,
|
| 1155 |
+
"step": 13400
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 0.9486832627676955,
|
| 1159 |
+
"grad_norm": 0.5471107363700867,
|
| 1160 |
+
"learning_rate": 0.00013676935691694976,
|
| 1161 |
+
"loss": 0.5778,
|
| 1162 |
+
"step": 13500
|
| 1163 |
+
},
|
| 1164 |
+
{
|
| 1165 |
+
"epoch": 0.9486832627676955,
|
| 1166 |
+
"eval_loss": 0.5845098495483398,
|
| 1167 |
+
"eval_runtime": 192.0133,
|
| 1168 |
+
"eval_samples_per_second": 65.876,
|
| 1169 |
+
"eval_steps_per_second": 8.239,
|
| 1170 |
+
"step": 13500
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 0.9557105461956045,
|
| 1174 |
+
"grad_norm": 0.6058303117752075,
|
| 1175 |
+
"learning_rate": 0.0001363008082464566,
|
| 1176 |
+
"loss": 0.6011,
|
| 1177 |
+
"step": 13600
|
| 1178 |
+
},
|
| 1179 |
+
{
|
| 1180 |
+
"epoch": 0.9627378296235133,
|
| 1181 |
+
"grad_norm": 0.5132064819335938,
|
| 1182 |
+
"learning_rate": 0.00013583225957596346,
|
| 1183 |
+
"loss": 0.5814,
|
| 1184 |
+
"step": 13700
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 0.9697651130514221,
|
| 1188 |
+
"grad_norm": 0.42012500762939453,
|
| 1189 |
+
"learning_rate": 0.0001353637109054703,
|
| 1190 |
+
"loss": 0.5834,
|
| 1191 |
+
"step": 13800
|
| 1192 |
+
},
|
| 1193 |
+
{
|
| 1194 |
+
"epoch": 0.976792396479331,
|
| 1195 |
+
"grad_norm": 0.5156047344207764,
|
| 1196 |
+
"learning_rate": 0.00013489516223497716,
|
| 1197 |
+
"loss": 0.5912,
|
| 1198 |
+
"step": 13900
|
| 1199 |
+
},
|
| 1200 |
+
{
|
| 1201 |
+
"epoch": 0.9838196799072398,
|
| 1202 |
+
"grad_norm": 0.578301727771759,
|
| 1203 |
+
"learning_rate": 0.00013442661356448404,
|
| 1204 |
+
"loss": 0.5888,
|
| 1205 |
+
"step": 14000
|
| 1206 |
+
},
|
| 1207 |
+
{
|
| 1208 |
+
"epoch": 0.9838196799072398,
|
| 1209 |
+
"eval_loss": 0.5840687155723572,
|
| 1210 |
+
"eval_runtime": 191.6947,
|
| 1211 |
+
"eval_samples_per_second": 65.985,
|
| 1212 |
+
"eval_steps_per_second": 8.253,
|
| 1213 |
+
"step": 14000
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.9908469633351488,
|
| 1217 |
+
"grad_norm": 0.5532825589179993,
|
| 1218 |
+
"learning_rate": 0.00013395806489399086,
|
| 1219 |
+
"loss": 0.5951,
|
| 1220 |
+
"step": 14100
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 0.9978742467630576,
|
| 1224 |
+
"grad_norm": 0.7117305994033813,
|
| 1225 |
+
"learning_rate": 0.00013348951622349771,
|
| 1226 |
+
"loss": 0.6017,
|
| 1227 |
+
"step": 14200
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 1.0049015301909665,
|
| 1231 |
+
"grad_norm": 0.4331432580947876,
|
| 1232 |
+
"learning_rate": 0.00013302096755300456,
|
| 1233 |
+
"loss": 0.535,
|
| 1234 |
+
"step": 14300
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 1.0119288136188753,
|
| 1238 |
+
"grad_norm": 0.5378111004829407,
|
| 1239 |
+
"learning_rate": 0.00013255241888251141,
|
| 1240 |
+
"loss": 0.5451,
|
| 1241 |
+
"step": 14400
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 1.0189560970467841,
|
| 1245 |
+
"grad_norm": 0.5767349600791931,
|
| 1246 |
+
"learning_rate": 0.0001320838702120183,
|
| 1247 |
+
"loss": 0.5469,
|
| 1248 |
+
"step": 14500
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 1.0189560970467841,
|
| 1252 |
+
"eval_loss": 0.5859206318855286,
|
| 1253 |
+
"eval_runtime": 192.2055,
|
| 1254 |
+
"eval_samples_per_second": 65.81,
|
| 1255 |
+
"eval_steps_per_second": 8.231,
|
| 1256 |
+
"step": 14500
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 1.025983380474693,
|
| 1260 |
+
"grad_norm": 0.5575023889541626,
|
| 1261 |
+
"learning_rate": 0.00013161532154152514,
|
| 1262 |
+
"loss": 0.5449,
|
| 1263 |
+
"step": 14600
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 1.0330106639026018,
|
| 1267 |
+
"grad_norm": 0.5510827302932739,
|
| 1268 |
+
"learning_rate": 0.000131146772871032,
|
| 1269 |
+
"loss": 0.5339,
|
| 1270 |
+
"step": 14700
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 1.0400379473305108,
|
| 1274 |
+
"grad_norm": 0.5780773758888245,
|
| 1275 |
+
"learning_rate": 0.00013067822420053884,
|
| 1276 |
+
"loss": 0.5334,
|
| 1277 |
+
"step": 14800
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 1.0470652307584196,
|
| 1281 |
+
"grad_norm": 0.6217513084411621,
|
| 1282 |
+
"learning_rate": 0.0001302096755300457,
|
| 1283 |
+
"loss": 0.5404,
|
| 1284 |
+
"step": 14900
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 1.0540925141863284,
|
| 1288 |
+
"grad_norm": 0.5290889739990234,
|
| 1289 |
+
"learning_rate": 0.00012974112685955254,
|
| 1290 |
+
"loss": 0.5368,
|
| 1291 |
+
"step": 15000
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 1.0540925141863284,
|
| 1295 |
+
"eval_loss": 0.5861626863479614,
|
| 1296 |
+
"eval_runtime": 192.0995,
|
| 1297 |
+
"eval_samples_per_second": 65.846,
|
| 1298 |
+
"eval_steps_per_second": 8.235,
|
| 1299 |
+
"step": 15000
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 1.0611197976142372,
|
| 1303 |
+
"grad_norm": 0.5673081278800964,
|
| 1304 |
+
"learning_rate": 0.0001292725781890594,
|
| 1305 |
+
"loss": 0.5381,
|
| 1306 |
+
"step": 15100
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 1.068147081042146,
|
| 1310 |
+
"grad_norm": 0.4198685884475708,
|
| 1311 |
+
"learning_rate": 0.00012880402951856624,
|
| 1312 |
+
"loss": 0.5379,
|
| 1313 |
+
"step": 15200
|
| 1314 |
+
},
|
| 1315 |
+
{
|
| 1316 |
+
"epoch": 1.075174364470055,
|
| 1317 |
+
"grad_norm": 0.45610734820365906,
|
| 1318 |
+
"learning_rate": 0.0001283354808480731,
|
| 1319 |
+
"loss": 0.5349,
|
| 1320 |
+
"step": 15300
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"epoch": 1.082201647897964,
|
| 1324 |
+
"grad_norm": 0.5499436259269714,
|
| 1325 |
+
"learning_rate": 0.00012786693217757994,
|
| 1326 |
+
"loss": 0.5411,
|
| 1327 |
+
"step": 15400
|
| 1328 |
+
},
|
| 1329 |
+
{
|
| 1330 |
+
"epoch": 1.0892289313258727,
|
| 1331 |
+
"grad_norm": 0.6300696730613708,
|
| 1332 |
+
"learning_rate": 0.0001273983835070868,
|
| 1333 |
+
"loss": 0.546,
|
| 1334 |
+
"step": 15500
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 1.0892289313258727,
|
| 1338 |
+
"eval_loss": 0.5862005352973938,
|
| 1339 |
+
"eval_runtime": 191.9358,
|
| 1340 |
+
"eval_samples_per_second": 65.902,
|
| 1341 |
+
"eval_steps_per_second": 8.242,
|
| 1342 |
+
"step": 15500
|
| 1343 |
+
},
|
| 1344 |
+
{
|
| 1345 |
+
"epoch": 1.0962562147537815,
|
| 1346 |
+
"grad_norm": 0.6075917482376099,
|
| 1347 |
+
"learning_rate": 0.00012692983483659367,
|
| 1348 |
+
"loss": 0.5417,
|
| 1349 |
+
"step": 15600
|
| 1350 |
+
},
|
| 1351 |
+
{
|
| 1352 |
+
"epoch": 1.1032834981816904,
|
| 1353 |
+
"grad_norm": 0.46201905608177185,
|
| 1354 |
+
"learning_rate": 0.00012646128616610052,
|
| 1355 |
+
"loss": 0.5283,
|
| 1356 |
+
"step": 15700
|
| 1357 |
+
},
|
| 1358 |
+
{
|
| 1359 |
+
"epoch": 1.1103107816095992,
|
| 1360 |
+
"grad_norm": 0.4050121605396271,
|
| 1361 |
+
"learning_rate": 0.00012599273749560737,
|
| 1362 |
+
"loss": 0.5479,
|
| 1363 |
+
"step": 15800
|
| 1364 |
+
},
|
| 1365 |
+
{
|
| 1366 |
+
"epoch": 1.1173380650375082,
|
| 1367 |
+
"grad_norm": 0.4577913284301758,
|
| 1368 |
+
"learning_rate": 0.0001255241888251142,
|
| 1369 |
+
"loss": 0.5452,
|
| 1370 |
+
"step": 15900
|
| 1371 |
+
},
|
| 1372 |
+
{
|
| 1373 |
+
"epoch": 1.124365348465417,
|
| 1374 |
+
"grad_norm": 0.4985063672065735,
|
| 1375 |
+
"learning_rate": 0.00012505564015462105,
|
| 1376 |
+
"loss": 0.5444,
|
| 1377 |
+
"step": 16000
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 1.124365348465417,
|
| 1381 |
+
"eval_loss": 0.5855303406715393,
|
| 1382 |
+
"eval_runtime": 191.4632,
|
| 1383 |
+
"eval_samples_per_second": 66.065,
|
| 1384 |
+
"eval_steps_per_second": 8.263,
|
| 1385 |
+
"step": 16000
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 1.1313926318933258,
|
| 1389 |
+
"grad_norm": 0.4636366665363312,
|
| 1390 |
+
"learning_rate": 0.00012458709148412792,
|
| 1391 |
+
"loss": 0.5352,
|
| 1392 |
+
"step": 16100
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 1.1384199153212347,
|
| 1396 |
+
"grad_norm": 0.5733815431594849,
|
| 1397 |
+
"learning_rate": 0.00012411854281363477,
|
| 1398 |
+
"loss": 0.5339,
|
| 1399 |
+
"step": 16200
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 1.1454471987491435,
|
| 1403 |
+
"grad_norm": 0.5225148797035217,
|
| 1404 |
+
"learning_rate": 0.00012364999414314162,
|
| 1405 |
+
"loss": 0.5356,
|
| 1406 |
+
"step": 16300
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 1.1524744821770523,
|
| 1410 |
+
"grad_norm": 0.5425903797149658,
|
| 1411 |
+
"learning_rate": 0.00012318144547264847,
|
| 1412 |
+
"loss": 0.544,
|
| 1413 |
+
"step": 16400
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 1.1595017656049613,
|
| 1417 |
+
"grad_norm": 0.49336591362953186,
|
| 1418 |
+
"learning_rate": 0.00012271289680215532,
|
| 1419 |
+
"loss": 0.5386,
|
| 1420 |
+
"step": 16500
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 1.1595017656049613,
|
| 1424 |
+
"eval_loss": 0.5844515562057495,
|
| 1425 |
+
"eval_runtime": 195.2478,
|
| 1426 |
+
"eval_samples_per_second": 64.784,
|
| 1427 |
+
"eval_steps_per_second": 8.103,
|
| 1428 |
+
"step": 16500
|
| 1429 |
+
},
|
| 1430 |
+
{
|
| 1431 |
+
"epoch": 1.1665290490328701,
|
| 1432 |
+
"grad_norm": 0.45879772305488586,
|
| 1433 |
+
"learning_rate": 0.0001222443481316622,
|
| 1434 |
+
"loss": 0.5334,
|
| 1435 |
+
"step": 16600
|
| 1436 |
+
},
|
| 1437 |
+
{
|
| 1438 |
+
"epoch": 1.173556332460779,
|
| 1439 |
+
"grad_norm": 0.4931933879852295,
|
| 1440 |
+
"learning_rate": 0.00012177579946116904,
|
| 1441 |
+
"loss": 0.5362,
|
| 1442 |
+
"step": 16700
|
| 1443 |
+
},
|
| 1444 |
+
{
|
| 1445 |
+
"epoch": 1.1805836158886878,
|
| 1446 |
+
"grad_norm": 0.7223409414291382,
|
| 1447 |
+
"learning_rate": 0.00012130725079067589,
|
| 1448 |
+
"loss": 0.5331,
|
| 1449 |
+
"step": 16800
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 1.1876108993165966,
|
| 1453 |
+
"grad_norm": 0.4814956784248352,
|
| 1454 |
+
"learning_rate": 0.00012083870212018274,
|
| 1455 |
+
"loss": 0.5279,
|
| 1456 |
+
"step": 16900
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"epoch": 1.1946381827445056,
|
| 1460 |
+
"grad_norm": 0.5712910294532776,
|
| 1461 |
+
"learning_rate": 0.00012037015344968959,
|
| 1462 |
+
"loss": 0.5269,
|
| 1463 |
+
"step": 17000
|
| 1464 |
+
},
|
| 1465 |
+
{
|
| 1466 |
+
"epoch": 1.1946381827445056,
|
| 1467 |
+
"eval_loss": 0.5852189660072327,
|
| 1468 |
+
"eval_runtime": 191.4648,
|
| 1469 |
+
"eval_samples_per_second": 66.064,
|
| 1470 |
+
"eval_steps_per_second": 8.263,
|
| 1471 |
+
"step": 17000
|
| 1472 |
+
},
|
| 1473 |
+
{
|
| 1474 |
+
"epoch": 1.2016654661724144,
|
| 1475 |
+
"grad_norm": 0.5194661021232605,
|
| 1476 |
+
"learning_rate": 0.00011990160477919645,
|
| 1477 |
+
"loss": 0.5456,
|
| 1478 |
+
"step": 17100
|
| 1479 |
+
},
|
| 1480 |
+
{
|
| 1481 |
+
"epoch": 1.2086927496003232,
|
| 1482 |
+
"grad_norm": 0.42699483036994934,
|
| 1483 |
+
"learning_rate": 0.0001194330561087033,
|
| 1484 |
+
"loss": 0.5519,
|
| 1485 |
+
"step": 17200
|
| 1486 |
+
},
|
| 1487 |
+
{
|
| 1488 |
+
"epoch": 1.215720033028232,
|
| 1489 |
+
"grad_norm": 0.49879905581474304,
|
| 1490 |
+
"learning_rate": 0.00011896450743821015,
|
| 1491 |
+
"loss": 0.5327,
|
| 1492 |
+
"step": 17300
|
| 1493 |
+
},
|
| 1494 |
+
{
|
| 1495 |
+
"epoch": 1.2227473164561409,
|
| 1496 |
+
"grad_norm": 0.7226296663284302,
|
| 1497 |
+
"learning_rate": 0.000118495958767717,
|
| 1498 |
+
"loss": 0.545,
|
| 1499 |
+
"step": 17400
|
| 1500 |
+
},
|
| 1501 |
+
{
|
| 1502 |
+
"epoch": 1.22977459988405,
|
| 1503 |
+
"grad_norm": 0.5727146863937378,
|
| 1504 |
+
"learning_rate": 0.00011802741009722384,
|
| 1505 |
+
"loss": 0.5428,
|
| 1506 |
+
"step": 17500
|
| 1507 |
+
},
|
| 1508 |
+
{
|
| 1509 |
+
"epoch": 1.22977459988405,
|
| 1510 |
+
"eval_loss": 0.5834037065505981,
|
| 1511 |
+
"eval_runtime": 191.7102,
|
| 1512 |
+
"eval_samples_per_second": 65.98,
|
| 1513 |
+
"eval_steps_per_second": 8.252,
|
| 1514 |
+
"step": 17500
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 1.2368018833119587,
|
| 1518 |
+
"grad_norm": 0.6738116145133972,
|
| 1519 |
+
"learning_rate": 0.00011755886142673072,
|
| 1520 |
+
"loss": 0.5494,
|
| 1521 |
+
"step": 17600
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 1.2438291667398675,
|
| 1525 |
+
"grad_norm": 0.5708216428756714,
|
| 1526 |
+
"learning_rate": 0.00011709031275623757,
|
| 1527 |
+
"loss": 0.5321,
|
| 1528 |
+
"step": 17700
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 1.2508564501677764,
|
| 1532 |
+
"grad_norm": 0.7585426568984985,
|
| 1533 |
+
"learning_rate": 0.00011662176408574442,
|
| 1534 |
+
"loss": 0.5405,
|
| 1535 |
+
"step": 17800
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 1.2578837335956852,
|
| 1539 |
+
"grad_norm": 0.48215654492378235,
|
| 1540 |
+
"learning_rate": 0.00011615321541525125,
|
| 1541 |
+
"loss": 0.5317,
|
| 1542 |
+
"step": 17900
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 1.2649110170235942,
|
| 1546 |
+
"grad_norm": 0.7234981060028076,
|
| 1547 |
+
"learning_rate": 0.0001156846667447581,
|
| 1548 |
+
"loss": 0.5198,
|
| 1549 |
+
"step": 18000
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 1.2649110170235942,
|
| 1553 |
+
"eval_loss": 0.583666980266571,
|
| 1554 |
+
"eval_runtime": 191.0164,
|
| 1555 |
+
"eval_samples_per_second": 66.219,
|
| 1556 |
+
"eval_steps_per_second": 8.282,
|
| 1557 |
+
"step": 18000
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 1.271938300451503,
|
| 1561 |
+
"grad_norm": 0.6166390180587769,
|
| 1562 |
+
"learning_rate": 0.00011521611807426498,
|
| 1563 |
+
"loss": 0.5391,
|
| 1564 |
+
"step": 18100
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 1.2789655838794118,
|
| 1568 |
+
"grad_norm": 0.5026915669441223,
|
| 1569 |
+
"learning_rate": 0.00011474756940377183,
|
| 1570 |
+
"loss": 0.5453,
|
| 1571 |
+
"step": 18200
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 1.2859928673073207,
|
| 1575 |
+
"grad_norm": 0.44040101766586304,
|
| 1576 |
+
"learning_rate": 0.00011427902073327867,
|
| 1577 |
+
"loss": 0.5459,
|
| 1578 |
+
"step": 18300
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 1.2930201507352295,
|
| 1582 |
+
"grad_norm": 0.4429463744163513,
|
| 1583 |
+
"learning_rate": 0.00011381047206278552,
|
| 1584 |
+
"loss": 0.5302,
|
| 1585 |
+
"step": 18400
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 1.3000474341631385,
|
| 1589 |
+
"grad_norm": 0.5252630710601807,
|
| 1590 |
+
"learning_rate": 0.00011334192339229237,
|
| 1591 |
+
"loss": 0.5373,
|
| 1592 |
+
"step": 18500
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 1.3000474341631385,
|
| 1596 |
+
"eval_loss": 0.5821723341941833,
|
| 1597 |
+
"eval_runtime": 191.389,
|
| 1598 |
+
"eval_samples_per_second": 66.091,
|
| 1599 |
+
"eval_steps_per_second": 8.266,
|
| 1600 |
+
"step": 18500
|
| 1601 |
+
},
|
| 1602 |
+
{
|
| 1603 |
+
"epoch": 1.3070747175910473,
|
| 1604 |
+
"grad_norm": 0.590726912021637,
|
| 1605 |
+
"learning_rate": 0.00011287337472179925,
|
| 1606 |
+
"loss": 0.5382,
|
| 1607 |
+
"step": 18600
|
| 1608 |
+
},
|
| 1609 |
+
{
|
| 1610 |
+
"epoch": 1.3141020010189561,
|
| 1611 |
+
"grad_norm": 0.6306003928184509,
|
| 1612 |
+
"learning_rate": 0.00011240482605130608,
|
| 1613 |
+
"loss": 0.5199,
|
| 1614 |
+
"step": 18700
|
| 1615 |
+
},
|
| 1616 |
+
{
|
| 1617 |
+
"epoch": 1.321129284446865,
|
| 1618 |
+
"grad_norm": 0.5457239151000977,
|
| 1619 |
+
"learning_rate": 0.00011193627738081293,
|
| 1620 |
+
"loss": 0.5318,
|
| 1621 |
+
"step": 18800
|
| 1622 |
+
},
|
| 1623 |
+
{
|
| 1624 |
+
"epoch": 1.3281565678747738,
|
| 1625 |
+
"grad_norm": 0.5287586450576782,
|
| 1626 |
+
"learning_rate": 0.00011146772871031978,
|
| 1627 |
+
"loss": 0.545,
|
| 1628 |
+
"step": 18900
|
| 1629 |
+
},
|
| 1630 |
+
{
|
| 1631 |
+
"epoch": 1.3351838513026828,
|
| 1632 |
+
"grad_norm": 0.5725194811820984,
|
| 1633 |
+
"learning_rate": 0.00011099918003982663,
|
| 1634 |
+
"loss": 0.5439,
|
| 1635 |
+
"step": 19000
|
| 1636 |
+
},
|
| 1637 |
+
{
|
| 1638 |
+
"epoch": 1.3351838513026828,
|
| 1639 |
+
"eval_loss": 0.5815557241439819,
|
| 1640 |
+
"eval_runtime": 191.8001,
|
| 1641 |
+
"eval_samples_per_second": 65.949,
|
| 1642 |
+
"eval_steps_per_second": 8.248,
|
| 1643 |
+
"step": 19000
|
| 1644 |
+
},
|
| 1645 |
+
{
|
| 1646 |
+
"epoch": 1.3422111347305914,
|
| 1647 |
+
"grad_norm": 0.6155562400817871,
|
| 1648 |
+
"learning_rate": 0.0001105306313693335,
|
| 1649 |
+
"loss": 0.5337,
|
| 1650 |
+
"step": 19100
|
| 1651 |
+
},
|
| 1652 |
+
{
|
| 1653 |
+
"epoch": 1.3492384181585004,
|
| 1654 |
+
"grad_norm": 0.45534420013427734,
|
| 1655 |
+
"learning_rate": 0.00011006208269884035,
|
| 1656 |
+
"loss": 0.5437,
|
| 1657 |
+
"step": 19200
|
| 1658 |
+
},
|
| 1659 |
+
{
|
| 1660 |
+
"epoch": 1.3562657015864092,
|
| 1661 |
+
"grad_norm": 0.5221378803253174,
|
| 1662 |
+
"learning_rate": 0.0001095935340283472,
|
| 1663 |
+
"loss": 0.5433,
|
| 1664 |
+
"step": 19300
|
| 1665 |
+
},
|
| 1666 |
+
{
|
| 1667 |
+
"epoch": 1.363292985014318,
|
| 1668 |
+
"grad_norm": 0.6740151047706604,
|
| 1669 |
+
"learning_rate": 0.00010912498535785405,
|
| 1670 |
+
"loss": 0.5315,
|
| 1671 |
+
"step": 19400
|
| 1672 |
+
},
|
| 1673 |
+
{
|
| 1674 |
+
"epoch": 1.3703202684422269,
|
| 1675 |
+
"grad_norm": 0.5568748116493225,
|
| 1676 |
+
"learning_rate": 0.0001086564366873609,
|
| 1677 |
+
"loss": 0.5442,
|
| 1678 |
+
"step": 19500
|
| 1679 |
+
},
|
| 1680 |
+
{
|
| 1681 |
+
"epoch": 1.3703202684422269,
|
| 1682 |
+
"eval_loss": 0.5810661911964417,
|
| 1683 |
+
"eval_runtime": 193.8958,
|
| 1684 |
+
"eval_samples_per_second": 65.236,
|
| 1685 |
+
"eval_steps_per_second": 8.159,
|
| 1686 |
+
"step": 19500
|
| 1687 |
+
},
|
| 1688 |
+
{
|
| 1689 |
+
"epoch": 1.3773475518701357,
|
| 1690 |
+
"grad_norm": 0.6538209915161133,
|
| 1691 |
+
"learning_rate": 0.00010818788801686776,
|
| 1692 |
+
"loss": 0.5485,
|
| 1693 |
+
"step": 19600
|
| 1694 |
+
},
|
| 1695 |
+
{
|
| 1696 |
+
"epoch": 1.3843748352980447,
|
| 1697 |
+
"grad_norm": 0.3977202773094177,
|
| 1698 |
+
"learning_rate": 0.00010771933934637461,
|
| 1699 |
+
"loss": 0.551,
|
| 1700 |
+
"step": 19700
|
| 1701 |
+
},
|
| 1702 |
+
{
|
| 1703 |
+
"epoch": 1.3914021187259535,
|
| 1704 |
+
"grad_norm": 0.6462295651435852,
|
| 1705 |
+
"learning_rate": 0.00010725079067588146,
|
| 1706 |
+
"loss": 0.535,
|
| 1707 |
+
"step": 19800
|
| 1708 |
+
},
|
| 1709 |
+
{
|
| 1710 |
+
"epoch": 1.3984294021538624,
|
| 1711 |
+
"grad_norm": 0.6669672131538391,
|
| 1712 |
+
"learning_rate": 0.00010678224200538831,
|
| 1713 |
+
"loss": 0.5372,
|
| 1714 |
+
"step": 19900
|
| 1715 |
+
},
|
| 1716 |
+
{
|
| 1717 |
+
"epoch": 1.4054566855817712,
|
| 1718 |
+
"grad_norm": 0.672690749168396,
|
| 1719 |
+
"learning_rate": 0.00010631369333489516,
|
| 1720 |
+
"loss": 0.5562,
|
| 1721 |
+
"step": 20000
|
| 1722 |
+
},
|
| 1723 |
+
{
|
| 1724 |
+
"epoch": 1.4054566855817712,
|
| 1725 |
+
"eval_loss": 0.5803663730621338,
|
| 1726 |
+
"eval_runtime": 191.2217,
|
| 1727 |
+
"eval_samples_per_second": 66.148,
|
| 1728 |
+
"eval_steps_per_second": 8.273,
|
| 1729 |
+
"step": 20000
|
| 1730 |
+
},
|
| 1731 |
+
{
|
| 1732 |
+
"epoch": 1.41248396900968,
|
| 1733 |
+
"grad_norm": 0.5990594029426575,
|
| 1734 |
+
"learning_rate": 0.00010584514466440203,
|
| 1735 |
+
"loss": 0.5402,
|
| 1736 |
+
"step": 20100
|
| 1737 |
+
},
|
| 1738 |
+
{
|
| 1739 |
+
"epoch": 1.419511252437589,
|
| 1740 |
+
"grad_norm": 0.7736939787864685,
|
| 1741 |
+
"learning_rate": 0.00010537659599390888,
|
| 1742 |
+
"loss": 0.5514,
|
| 1743 |
+
"step": 20200
|
| 1744 |
+
},
|
| 1745 |
+
{
|
| 1746 |
+
"epoch": 1.4265385358654978,
|
| 1747 |
+
"grad_norm": 0.7517827749252319,
|
| 1748 |
+
"learning_rate": 0.00010490804732341573,
|
| 1749 |
+
"loss": 0.5199,
|
| 1750 |
+
"step": 20300
|
| 1751 |
+
},
|
| 1752 |
+
{
|
| 1753 |
+
"epoch": 1.4335658192934067,
|
| 1754 |
+
"grad_norm": 0.40587854385375977,
|
| 1755 |
+
"learning_rate": 0.00010443949865292258,
|
| 1756 |
+
"loss": 0.5453,
|
| 1757 |
+
"step": 20400
|
| 1758 |
+
},
|
| 1759 |
+
{
|
| 1760 |
+
"epoch": 1.4405931027213155,
|
| 1761 |
+
"grad_norm": 0.5752481818199158,
|
| 1762 |
+
"learning_rate": 0.00010397094998242943,
|
| 1763 |
+
"loss": 0.5327,
|
| 1764 |
+
"step": 20500
|
| 1765 |
+
},
|
| 1766 |
+
{
|
| 1767 |
+
"epoch": 1.4405931027213155,
|
| 1768 |
+
"eval_loss": 0.5793671607971191,
|
| 1769 |
+
"eval_runtime": 191.4019,
|
| 1770 |
+
"eval_samples_per_second": 66.086,
|
| 1771 |
+
"eval_steps_per_second": 8.265,
|
| 1772 |
+
"step": 20500
|
| 1773 |
+
},
|
| 1774 |
+
{
|
| 1775 |
+
"epoch": 1.4476203861492243,
|
| 1776 |
+
"grad_norm": 0.5109778642654419,
|
| 1777 |
+
"learning_rate": 0.00010350240131193629,
|
| 1778 |
+
"loss": 0.534,
|
| 1779 |
+
"step": 20600
|
| 1780 |
+
},
|
| 1781 |
+
{
|
| 1782 |
+
"epoch": 1.4546476695771333,
|
| 1783 |
+
"grad_norm": 0.5415691137313843,
|
| 1784 |
+
"learning_rate": 0.00010303385264144314,
|
| 1785 |
+
"loss": 0.5346,
|
| 1786 |
+
"step": 20700
|
| 1787 |
+
},
|
| 1788 |
+
{
|
| 1789 |
+
"epoch": 1.4616749530050421,
|
| 1790 |
+
"grad_norm": 0.6798147559165955,
|
| 1791 |
+
"learning_rate": 0.00010256530397094999,
|
| 1792 |
+
"loss": 0.5389,
|
| 1793 |
+
"step": 20800
|
| 1794 |
+
},
|
| 1795 |
+
{
|
| 1796 |
+
"epoch": 1.468702236432951,
|
| 1797 |
+
"grad_norm": 0.5930722951889038,
|
| 1798 |
+
"learning_rate": 0.00010209675530045684,
|
| 1799 |
+
"loss": 0.5553,
|
| 1800 |
+
"step": 20900
|
| 1801 |
+
},
|
| 1802 |
+
{
|
| 1803 |
+
"epoch": 1.4757295198608598,
|
| 1804 |
+
"grad_norm": 0.46035194396972656,
|
| 1805 |
+
"learning_rate": 0.00010162820662996368,
|
| 1806 |
+
"loss": 0.5488,
|
| 1807 |
+
"step": 21000
|
| 1808 |
+
},
|
| 1809 |
+
{
|
| 1810 |
+
"epoch": 1.4757295198608598,
|
| 1811 |
+
"eval_loss": 0.5797436833381653,
|
| 1812 |
+
"eval_runtime": 191.1985,
|
| 1813 |
+
"eval_samples_per_second": 66.156,
|
| 1814 |
+
"eval_steps_per_second": 8.274,
|
| 1815 |
+
"step": 21000
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 1.4827568032887686,
|
| 1819 |
+
"grad_norm": 0.6289058327674866,
|
| 1820 |
+
"learning_rate": 0.00010115965795947056,
|
| 1821 |
+
"loss": 0.5373,
|
| 1822 |
+
"step": 21100
|
| 1823 |
+
},
|
| 1824 |
+
{
|
| 1825 |
+
"epoch": 1.4897840867166776,
|
| 1826 |
+
"grad_norm": 0.5587871670722961,
|
| 1827 |
+
"learning_rate": 0.0001006911092889774,
|
| 1828 |
+
"loss": 0.5433,
|
| 1829 |
+
"step": 21200
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 1.4968113701445864,
|
| 1833 |
+
"grad_norm": 0.6402022838592529,
|
| 1834 |
+
"learning_rate": 0.00010022256061848426,
|
| 1835 |
+
"loss": 0.5369,
|
| 1836 |
+
"step": 21300
|
| 1837 |
+
},
|
| 1838 |
+
{
|
| 1839 |
+
"epoch": 1.5038386535724952,
|
| 1840 |
+
"grad_norm": 0.7074068784713745,
|
| 1841 |
+
"learning_rate": 9.975401194799109e-05,
|
| 1842 |
+
"loss": 0.5422,
|
| 1843 |
+
"step": 21400
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 1.510865937000404,
|
| 1847 |
+
"grad_norm": 0.6283564567565918,
|
| 1848 |
+
"learning_rate": 9.928546327749796e-05,
|
| 1849 |
+
"loss": 0.53,
|
| 1850 |
+
"step": 21500
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 1.510865937000404,
|
| 1854 |
+
"eval_loss": 0.5776032209396362,
|
| 1855 |
+
"eval_runtime": 195.2716,
|
| 1856 |
+
"eval_samples_per_second": 64.776,
|
| 1857 |
+
"eval_steps_per_second": 8.102,
|
| 1858 |
+
"step": 21500
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 1.5178932204283129,
|
| 1862 |
+
"grad_norm": 0.5513471961021423,
|
| 1863 |
+
"learning_rate": 9.881691460700481e-05,
|
| 1864 |
+
"loss": 0.5363,
|
| 1865 |
+
"step": 21600
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 1.524920503856222,
|
| 1869 |
+
"grad_norm": 0.6834294199943542,
|
| 1870 |
+
"learning_rate": 9.834836593651166e-05,
|
| 1871 |
+
"loss": 0.5357,
|
| 1872 |
+
"step": 21700
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 1.5319477872841305,
|
| 1876 |
+
"grad_norm": 0.5920292139053345,
|
| 1877 |
+
"learning_rate": 9.787981726601851e-05,
|
| 1878 |
+
"loss": 0.5425,
|
| 1879 |
+
"step": 21800
|
| 1880 |
+
},
|
| 1881 |
+
{
|
| 1882 |
+
"epoch": 1.5389750707120395,
|
| 1883 |
+
"grad_norm": 0.7391265630722046,
|
| 1884 |
+
"learning_rate": 9.741126859552536e-05,
|
| 1885 |
+
"loss": 0.5536,
|
| 1886 |
+
"step": 21900
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 1.5460023541399484,
|
| 1890 |
+
"grad_norm": 0.59616619348526,
|
| 1891 |
+
"learning_rate": 9.694271992503222e-05,
|
| 1892 |
+
"loss": 0.5266,
|
| 1893 |
+
"step": 22000
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 1.5460023541399484,
|
| 1897 |
+
"eval_loss": 0.5772854089736938,
|
| 1898 |
+
"eval_runtime": 191.6654,
|
| 1899 |
+
"eval_samples_per_second": 65.995,
|
| 1900 |
+
"eval_steps_per_second": 8.254,
|
| 1901 |
+
"step": 22000
|
| 1902 |
+
},
|
| 1903 |
+
{
|
| 1904 |
+
"epoch": 1.5530296375678572,
|
| 1905 |
+
"grad_norm": 0.7118886709213257,
|
| 1906 |
+
"learning_rate": 9.647417125453907e-05,
|
| 1907 |
+
"loss": 0.5402,
|
| 1908 |
+
"step": 22100
|
| 1909 |
+
},
|
| 1910 |
+
{
|
| 1911 |
+
"epoch": 1.5600569209957662,
|
| 1912 |
+
"grad_norm": 0.5848612189292908,
|
| 1913 |
+
"learning_rate": 9.600562258404592e-05,
|
| 1914 |
+
"loss": 0.5471,
|
| 1915 |
+
"step": 22200
|
| 1916 |
+
},
|
| 1917 |
+
{
|
| 1918 |
+
"epoch": 1.5670842044236748,
|
| 1919 |
+
"grad_norm": 0.6379753947257996,
|
| 1920 |
+
"learning_rate": 9.553707391355277e-05,
|
| 1921 |
+
"loss": 0.5319,
|
| 1922 |
+
"step": 22300
|
| 1923 |
+
},
|
| 1924 |
+
{
|
| 1925 |
+
"epoch": 1.5741114878515838,
|
| 1926 |
+
"grad_norm": 0.5326395630836487,
|
| 1927 |
+
"learning_rate": 9.506852524305962e-05,
|
| 1928 |
+
"loss": 0.5362,
|
| 1929 |
+
"step": 22400
|
| 1930 |
+
},
|
| 1931 |
+
{
|
| 1932 |
+
"epoch": 1.5811387712794926,
|
| 1933 |
+
"grad_norm": 0.44863948225975037,
|
| 1934 |
+
"learning_rate": 9.459997657256649e-05,
|
| 1935 |
+
"loss": 0.5339,
|
| 1936 |
+
"step": 22500
|
| 1937 |
+
},
|
| 1938 |
+
{
|
| 1939 |
+
"epoch": 1.5811387712794926,
|
| 1940 |
+
"eval_loss": 0.5767233371734619,
|
| 1941 |
+
"eval_runtime": 191.4103,
|
| 1942 |
+
"eval_samples_per_second": 66.083,
|
| 1943 |
+
"eval_steps_per_second": 8.265,
|
| 1944 |
+
"step": 22500
|
| 1945 |
+
},
|
| 1946 |
+
{
|
| 1947 |
+
"epoch": 1.5881660547074015,
|
| 1948 |
+
"grad_norm": 0.6882546544075012,
|
| 1949 |
+
"learning_rate": 9.413142790207334e-05,
|
| 1950 |
+
"loss": 0.5338,
|
| 1951 |
+
"step": 22600
|
| 1952 |
+
},
|
| 1953 |
+
{
|
| 1954 |
+
"epoch": 1.5951933381353105,
|
| 1955 |
+
"grad_norm": 0.6498861312866211,
|
| 1956 |
+
"learning_rate": 9.366287923158019e-05,
|
| 1957 |
+
"loss": 0.5449,
|
| 1958 |
+
"step": 22700
|
| 1959 |
+
},
|
| 1960 |
+
{
|
| 1961 |
+
"epoch": 1.602220621563219,
|
| 1962 |
+
"grad_norm": 0.5820225477218628,
|
| 1963 |
+
"learning_rate": 9.319433056108704e-05,
|
| 1964 |
+
"loss": 0.541,
|
| 1965 |
+
"step": 22800
|
| 1966 |
+
},
|
| 1967 |
+
{
|
| 1968 |
+
"epoch": 1.6092479049911281,
|
| 1969 |
+
"grad_norm": 0.6746723651885986,
|
| 1970 |
+
"learning_rate": 9.272578189059389e-05,
|
| 1971 |
+
"loss": 0.5437,
|
| 1972 |
+
"step": 22900
|
| 1973 |
+
},
|
| 1974 |
+
{
|
| 1975 |
+
"epoch": 1.616275188419037,
|
| 1976 |
+
"grad_norm": 0.6235536932945251,
|
| 1977 |
+
"learning_rate": 9.225723322010075e-05,
|
| 1978 |
+
"loss": 0.5332,
|
| 1979 |
+
"step": 23000
|
| 1980 |
+
},
|
| 1981 |
+
{
|
| 1982 |
+
"epoch": 1.616275188419037,
|
| 1983 |
+
"eval_loss": 0.575995683670044,
|
| 1984 |
+
"eval_runtime": 191.6609,
|
| 1985 |
+
"eval_samples_per_second": 65.997,
|
| 1986 |
+
"eval_steps_per_second": 8.254,
|
| 1987 |
+
"step": 23000
|
| 1988 |
+
},
|
| 1989 |
+
{
|
| 1990 |
+
"epoch": 1.6233024718469458,
|
| 1991 |
+
"grad_norm": 0.7106947898864746,
|
| 1992 |
+
"learning_rate": 9.17886845496076e-05,
|
| 1993 |
+
"loss": 0.5466,
|
| 1994 |
+
"step": 23100
|
| 1995 |
+
},
|
| 1996 |
+
{
|
| 1997 |
+
"epoch": 1.6303297552748546,
|
| 1998 |
+
"grad_norm": 0.5090802907943726,
|
| 1999 |
+
"learning_rate": 9.132013587911444e-05,
|
| 2000 |
+
"loss": 0.5244,
|
| 2001 |
+
"step": 23200
|
| 2002 |
+
},
|
| 2003 |
+
{
|
| 2004 |
+
"epoch": 1.6373570387027634,
|
| 2005 |
+
"grad_norm": 0.5423375368118286,
|
| 2006 |
+
"learning_rate": 9.08515872086213e-05,
|
| 2007 |
+
"loss": 0.5331,
|
| 2008 |
+
"step": 23300
|
| 2009 |
+
},
|
| 2010 |
+
{
|
| 2011 |
+
"epoch": 1.6443843221306724,
|
| 2012 |
+
"grad_norm": 0.40430954098701477,
|
| 2013 |
+
"learning_rate": 9.038303853812815e-05,
|
| 2014 |
+
"loss": 0.543,
|
| 2015 |
+
"step": 23400
|
| 2016 |
+
},
|
| 2017 |
+
{
|
| 2018 |
+
"epoch": 1.6514116055585812,
|
| 2019 |
+
"grad_norm": 0.5849967002868652,
|
| 2020 |
+
"learning_rate": 8.991448986763502e-05,
|
| 2021 |
+
"loss": 0.5313,
|
| 2022 |
+
"step": 23500
|
| 2023 |
+
},
|
| 2024 |
+
{
|
| 2025 |
+
"epoch": 1.6514116055585812,
|
| 2026 |
+
"eval_loss": 0.5759484171867371,
|
| 2027 |
+
"eval_runtime": 198.3535,
|
| 2028 |
+
"eval_samples_per_second": 63.77,
|
| 2029 |
+
"eval_steps_per_second": 7.976,
|
| 2030 |
+
"step": 23500
|
| 2031 |
+
},
|
| 2032 |
+
{
|
| 2033 |
+
"epoch": 1.65843888898649,
|
| 2034 |
+
"grad_norm": 0.642866849899292,
|
| 2035 |
+
"learning_rate": 8.944594119714185e-05,
|
| 2036 |
+
"loss": 0.5375,
|
| 2037 |
+
"step": 23600
|
| 2038 |
+
},
|
| 2039 |
+
{
|
| 2040 |
+
"epoch": 1.6654661724143989,
|
| 2041 |
+
"grad_norm": 0.4610786437988281,
|
| 2042 |
+
"learning_rate": 8.89773925266487e-05,
|
| 2043 |
+
"loss": 0.5262,
|
| 2044 |
+
"step": 23700
|
| 2045 |
+
},
|
| 2046 |
+
{
|
| 2047 |
+
"epoch": 1.6724934558423077,
|
| 2048 |
+
"grad_norm": 0.5731543302536011,
|
| 2049 |
+
"learning_rate": 8.850884385615557e-05,
|
| 2050 |
+
"loss": 0.5316,
|
| 2051 |
+
"step": 23800
|
| 2052 |
+
},
|
| 2053 |
+
{
|
| 2054 |
+
"epoch": 1.6795207392702167,
|
| 2055 |
+
"grad_norm": 0.6324673295021057,
|
| 2056 |
+
"learning_rate": 8.804029518566242e-05,
|
| 2057 |
+
"loss": 0.5391,
|
| 2058 |
+
"step": 23900
|
| 2059 |
+
},
|
| 2060 |
+
{
|
| 2061 |
+
"epoch": 1.6865480226981253,
|
| 2062 |
+
"grad_norm": 0.7439347505569458,
|
| 2063 |
+
"learning_rate": 8.757174651516927e-05,
|
| 2064 |
+
"loss": 0.5328,
|
| 2065 |
+
"step": 24000
|
| 2066 |
+
},
|
| 2067 |
+
{
|
| 2068 |
+
"epoch": 1.6865480226981253,
|
| 2069 |
+
"eval_loss": 0.5753322839736938,
|
| 2070 |
+
"eval_runtime": 191.1076,
|
| 2071 |
+
"eval_samples_per_second": 66.188,
|
| 2072 |
+
"eval_steps_per_second": 8.278,
|
| 2073 |
+
"step": 24000
|
| 2074 |
+
},
|
| 2075 |
+
{
|
| 2076 |
+
"epoch": 1.6935753061260344,
|
| 2077 |
+
"grad_norm": 0.5916799306869507,
|
| 2078 |
+
"learning_rate": 8.710319784467612e-05,
|
| 2079 |
+
"loss": 0.5357,
|
| 2080 |
+
"step": 24100
|
| 2081 |
+
},
|
| 2082 |
+
{
|
| 2083 |
+
"epoch": 1.7006025895539432,
|
| 2084 |
+
"grad_norm": 0.641130268573761,
|
| 2085 |
+
"learning_rate": 8.663464917418297e-05,
|
| 2086 |
+
"loss": 0.5413,
|
| 2087 |
+
"step": 24200
|
| 2088 |
+
},
|
| 2089 |
+
{
|
| 2090 |
+
"epoch": 1.707629872981852,
|
| 2091 |
+
"grad_norm": 0.5414934754371643,
|
| 2092 |
+
"learning_rate": 8.616610050368983e-05,
|
| 2093 |
+
"loss": 0.5372,
|
| 2094 |
+
"step": 24300
|
| 2095 |
+
},
|
| 2096 |
+
{
|
| 2097 |
+
"epoch": 1.714657156409761,
|
| 2098 |
+
"grad_norm": 0.5349559783935547,
|
| 2099 |
+
"learning_rate": 8.569755183319668e-05,
|
| 2100 |
+
"loss": 0.5248,
|
| 2101 |
+
"step": 24400
|
| 2102 |
+
},
|
| 2103 |
+
{
|
| 2104 |
+
"epoch": 1.7216844398376696,
|
| 2105 |
+
"grad_norm": 0.657092273235321,
|
| 2106 |
+
"learning_rate": 8.522900316270352e-05,
|
| 2107 |
+
"loss": 0.5323,
|
| 2108 |
+
"step": 24500
|
| 2109 |
+
},
|
| 2110 |
+
{
|
| 2111 |
+
"epoch": 1.7216844398376696,
|
| 2112 |
+
"eval_loss": 0.5741798281669617,
|
| 2113 |
+
"eval_runtime": 191.815,
|
| 2114 |
+
"eval_samples_per_second": 65.944,
|
| 2115 |
+
"eval_steps_per_second": 8.248,
|
| 2116 |
+
"step": 24500
|
| 2117 |
+
},
|
| 2118 |
+
{
|
| 2119 |
+
"epoch": 1.7287117232655786,
|
| 2120 |
+
"grad_norm": 0.5300177335739136,
|
| 2121 |
+
"learning_rate": 8.476045449221038e-05,
|
| 2122 |
+
"loss": 0.5396,
|
| 2123 |
+
"step": 24600
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 1.7357390066934875,
|
| 2127 |
+
"grad_norm": 0.5802739262580872,
|
| 2128 |
+
"learning_rate": 8.429190582171723e-05,
|
| 2129 |
+
"loss": 0.5343,
|
| 2130 |
+
"step": 24700
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 1.7427662901213963,
|
| 2134 |
+
"grad_norm": 0.5847595930099487,
|
| 2135 |
+
"learning_rate": 8.38233571512241e-05,
|
| 2136 |
+
"loss": 0.5337,
|
| 2137 |
+
"step": 24800
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 1.7497935735493053,
|
| 2141 |
+
"grad_norm": 0.5918022394180298,
|
| 2142 |
+
"learning_rate": 8.335480848073095e-05,
|
| 2143 |
+
"loss": 0.5332,
|
| 2144 |
+
"step": 24900
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 1.756820856977214,
|
| 2148 |
+
"grad_norm": 0.6495380997657776,
|
| 2149 |
+
"learning_rate": 8.288625981023778e-05,
|
| 2150 |
+
"loss": 0.5337,
|
| 2151 |
+
"step": 25000
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 1.756820856977214,
|
| 2155 |
+
"eval_loss": 0.5734357833862305,
|
| 2156 |
+
"eval_runtime": 191.5001,
|
| 2157 |
+
"eval_samples_per_second": 66.052,
|
| 2158 |
+
"eval_steps_per_second": 8.261,
|
| 2159 |
+
"step": 25000
|
| 2160 |
+
},
|
| 2161 |
+
{
|
| 2162 |
+
"epoch": 1.763848140405123,
|
| 2163 |
+
"grad_norm": 0.773017406463623,
|
| 2164 |
+
"learning_rate": 8.241771113974465e-05,
|
| 2165 |
+
"loss": 0.5195,
|
| 2166 |
+
"step": 25100
|
| 2167 |
+
},
|
| 2168 |
+
{
|
| 2169 |
+
"epoch": 1.7708754238330318,
|
| 2170 |
+
"grad_norm": 0.6224300861358643,
|
| 2171 |
+
"learning_rate": 8.19491624692515e-05,
|
| 2172 |
+
"loss": 0.5409,
|
| 2173 |
+
"step": 25200
|
| 2174 |
+
},
|
| 2175 |
+
{
|
| 2176 |
+
"epoch": 1.7779027072609406,
|
| 2177 |
+
"grad_norm": 0.561305582523346,
|
| 2178 |
+
"learning_rate": 8.148061379875836e-05,
|
| 2179 |
+
"loss": 0.5411,
|
| 2180 |
+
"step": 25300
|
| 2181 |
+
},
|
| 2182 |
+
{
|
| 2183 |
+
"epoch": 1.7849299906888496,
|
| 2184 |
+
"grad_norm": 0.5424569249153137,
|
| 2185 |
+
"learning_rate": 8.10120651282652e-05,
|
| 2186 |
+
"loss": 0.5385,
|
| 2187 |
+
"step": 25400
|
| 2188 |
+
},
|
| 2189 |
+
{
|
| 2190 |
+
"epoch": 1.7919572741167582,
|
| 2191 |
+
"grad_norm": 0.6570726037025452,
|
| 2192 |
+
"learning_rate": 8.054351645777205e-05,
|
| 2193 |
+
"loss": 0.5304,
|
| 2194 |
+
"step": 25500
|
| 2195 |
+
},
|
| 2196 |
+
{
|
| 2197 |
+
"epoch": 1.7919572741167582,
|
| 2198 |
+
"eval_loss": 0.5725218057632446,
|
| 2199 |
+
"eval_runtime": 191.5153,
|
| 2200 |
+
"eval_samples_per_second": 66.047,
|
| 2201 |
+
"eval_steps_per_second": 8.26,
|
| 2202 |
+
"step": 25500
|
| 2203 |
+
},
|
| 2204 |
+
{
|
| 2205 |
+
"epoch": 1.7989845575446672,
|
| 2206 |
+
"grad_norm": 0.619318962097168,
|
| 2207 |
+
"learning_rate": 8.007496778727891e-05,
|
| 2208 |
+
"loss": 0.5404,
|
| 2209 |
+
"step": 25600
|
| 2210 |
+
},
|
| 2211 |
+
{
|
| 2212 |
+
"epoch": 1.806011840972576,
|
| 2213 |
+
"grad_norm": 0.666038990020752,
|
| 2214 |
+
"learning_rate": 7.960641911678576e-05,
|
| 2215 |
+
"loss": 0.5367,
|
| 2216 |
+
"step": 25700
|
| 2217 |
+
},
|
| 2218 |
+
{
|
| 2219 |
+
"epoch": 1.8130391244004849,
|
| 2220 |
+
"grad_norm": 0.4837888777256012,
|
| 2221 |
+
"learning_rate": 7.913787044629261e-05,
|
| 2222 |
+
"loss": 0.5275,
|
| 2223 |
+
"step": 25800
|
| 2224 |
+
},
|
| 2225 |
+
{
|
| 2226 |
+
"epoch": 1.8200664078283937,
|
| 2227 |
+
"grad_norm": 0.5173748135566711,
|
| 2228 |
+
"learning_rate": 7.866932177579946e-05,
|
| 2229 |
+
"loss": 0.5159,
|
| 2230 |
+
"step": 25900
|
| 2231 |
+
},
|
| 2232 |
+
{
|
| 2233 |
+
"epoch": 1.8270936912563025,
|
| 2234 |
+
"grad_norm": 0.5783088207244873,
|
| 2235 |
+
"learning_rate": 7.820077310530631e-05,
|
| 2236 |
+
"loss": 0.526,
|
| 2237 |
+
"step": 26000
|
| 2238 |
+
},
|
| 2239 |
+
{
|
| 2240 |
+
"epoch": 1.8270936912563025,
|
| 2241 |
+
"eval_loss": 0.571327805519104,
|
| 2242 |
+
"eval_runtime": 191.7206,
|
| 2243 |
+
"eval_samples_per_second": 65.976,
|
| 2244 |
+
"eval_steps_per_second": 8.252,
|
| 2245 |
+
"step": 26000
|
| 2246 |
+
},
|
| 2247 |
+
{
|
| 2248 |
+
"epoch": 1.8341209746842115,
|
| 2249 |
+
"grad_norm": 0.4488949477672577,
|
| 2250 |
+
"learning_rate": 7.773222443481318e-05,
|
| 2251 |
+
"loss": 0.5264,
|
| 2252 |
+
"step": 26100
|
| 2253 |
+
},
|
| 2254 |
+
{
|
| 2255 |
+
"epoch": 1.8411482581121204,
|
| 2256 |
+
"grad_norm": 0.5412874817848206,
|
| 2257 |
+
"learning_rate": 7.726367576432003e-05,
|
| 2258 |
+
"loss": 0.5366,
|
| 2259 |
+
"step": 26200
|
| 2260 |
+
},
|
| 2261 |
+
{
|
| 2262 |
+
"epoch": 1.8481755415400292,
|
| 2263 |
+
"grad_norm": 0.5360791087150574,
|
| 2264 |
+
"learning_rate": 7.679512709382688e-05,
|
| 2265 |
+
"loss": 0.5277,
|
| 2266 |
+
"step": 26300
|
| 2267 |
+
},
|
| 2268 |
+
{
|
| 2269 |
+
"epoch": 1.855202824967938,
|
| 2270 |
+
"grad_norm": 0.5853073596954346,
|
| 2271 |
+
"learning_rate": 7.632657842333373e-05,
|
| 2272 |
+
"loss": 0.5221,
|
| 2273 |
+
"step": 26400
|
| 2274 |
+
},
|
| 2275 |
+
{
|
| 2276 |
+
"epoch": 1.8622301083958468,
|
| 2277 |
+
"grad_norm": 0.733930230140686,
|
| 2278 |
+
"learning_rate": 7.585802975284058e-05,
|
| 2279 |
+
"loss": 0.53,
|
| 2280 |
+
"step": 26500
|
| 2281 |
+
},
|
| 2282 |
+
{
|
| 2283 |
+
"epoch": 1.8622301083958468,
|
| 2284 |
+
"eval_loss": 0.5721610188484192,
|
| 2285 |
+
"eval_runtime": 191.5535,
|
| 2286 |
+
"eval_samples_per_second": 66.034,
|
| 2287 |
+
"eval_steps_per_second": 8.259,
|
| 2288 |
+
"step": 26500
|
| 2289 |
+
},
|
| 2290 |
+
{
|
| 2291 |
+
"epoch": 1.8692573918237558,
|
| 2292 |
+
"grad_norm": 0.5376147031784058,
|
| 2293 |
+
"learning_rate": 7.538948108234744e-05,
|
| 2294 |
+
"loss": 0.5203,
|
| 2295 |
+
"step": 26600
|
| 2296 |
+
},
|
| 2297 |
+
{
|
| 2298 |
+
"epoch": 1.8762846752516644,
|
| 2299 |
+
"grad_norm": 0.6613253951072693,
|
| 2300 |
+
"learning_rate": 7.492093241185428e-05,
|
| 2301 |
+
"loss": 0.5316,
|
| 2302 |
+
"step": 26700
|
| 2303 |
+
},
|
| 2304 |
+
{
|
| 2305 |
+
"epoch": 1.8833119586795735,
|
| 2306 |
+
"grad_norm": 0.6095169186592102,
|
| 2307 |
+
"learning_rate": 7.445238374136114e-05,
|
| 2308 |
+
"loss": 0.5396,
|
| 2309 |
+
"step": 26800
|
| 2310 |
+
},
|
| 2311 |
+
{
|
| 2312 |
+
"epoch": 1.8903392421074823,
|
| 2313 |
+
"grad_norm": 0.5879153609275818,
|
| 2314 |
+
"learning_rate": 7.398383507086799e-05,
|
| 2315 |
+
"loss": 0.5328,
|
| 2316 |
+
"step": 26900
|
| 2317 |
+
},
|
| 2318 |
+
{
|
| 2319 |
+
"epoch": 1.897366525535391,
|
| 2320 |
+
"grad_norm": 0.4561489522457123,
|
| 2321 |
+
"learning_rate": 7.351528640037484e-05,
|
| 2322 |
+
"loss": 0.5334,
|
| 2323 |
+
"step": 27000
|
| 2324 |
+
},
|
| 2325 |
+
{
|
| 2326 |
+
"epoch": 1.897366525535391,
|
| 2327 |
+
"eval_loss": 0.5708492398262024,
|
| 2328 |
+
"eval_runtime": 191.398,
|
| 2329 |
+
"eval_samples_per_second": 66.087,
|
| 2330 |
+
"eval_steps_per_second": 8.265,
|
| 2331 |
+
"step": 27000
|
| 2332 |
+
},
|
| 2333 |
+
{
|
| 2334 |
+
"epoch": 1.9043938089633001,
|
| 2335 |
+
"grad_norm": 1.0811113119125366,
|
| 2336 |
+
"learning_rate": 7.304673772988169e-05,
|
| 2337 |
+
"loss": 0.5299,
|
| 2338 |
+
"step": 27100
|
| 2339 |
+
},
|
| 2340 |
+
{
|
| 2341 |
+
"epoch": 1.9114210923912087,
|
| 2342 |
+
"grad_norm": 0.5830855965614319,
|
| 2343 |
+
"learning_rate": 7.257818905938854e-05,
|
| 2344 |
+
"loss": 0.5477,
|
| 2345 |
+
"step": 27200
|
| 2346 |
+
},
|
| 2347 |
+
{
|
| 2348 |
+
"epoch": 1.9184483758191178,
|
| 2349 |
+
"grad_norm": 0.6300702095031738,
|
| 2350 |
+
"learning_rate": 7.21096403888954e-05,
|
| 2351 |
+
"loss": 0.5481,
|
| 2352 |
+
"step": 27300
|
| 2353 |
+
},
|
| 2354 |
+
{
|
| 2355 |
+
"epoch": 1.9254756592470266,
|
| 2356 |
+
"grad_norm": 0.6268986463546753,
|
| 2357 |
+
"learning_rate": 7.164109171840226e-05,
|
| 2358 |
+
"loss": 0.5253,
|
| 2359 |
+
"step": 27400
|
| 2360 |
+
},
|
| 2361 |
+
{
|
| 2362 |
+
"epoch": 1.9325029426749354,
|
| 2363 |
+
"grad_norm": 0.6296914219856262,
|
| 2364 |
+
"learning_rate": 7.11725430479091e-05,
|
| 2365 |
+
"loss": 0.5233,
|
| 2366 |
+
"step": 27500
|
| 2367 |
+
},
|
| 2368 |
+
{
|
| 2369 |
+
"epoch": 1.9325029426749354,
|
| 2370 |
+
"eval_loss": 0.5700781941413879,
|
| 2371 |
+
"eval_runtime": 191.7014,
|
| 2372 |
+
"eval_samples_per_second": 65.983,
|
| 2373 |
+
"eval_steps_per_second": 8.252,
|
| 2374 |
+
"step": 27500
|
| 2375 |
+
},
|
| 2376 |
+
{
|
| 2377 |
+
"epoch": 1.9395302261028444,
|
| 2378 |
+
"grad_norm": 0.47624173760414124,
|
| 2379 |
+
"learning_rate": 7.070399437741596e-05,
|
| 2380 |
+
"loss": 0.54,
|
| 2381 |
+
"step": 27600
|
| 2382 |
+
},
|
| 2383 |
+
{
|
| 2384 |
+
"epoch": 1.946557509530753,
|
| 2385 |
+
"grad_norm": 0.6563848853111267,
|
| 2386 |
+
"learning_rate": 7.02354457069228e-05,
|
| 2387 |
+
"loss": 0.5273,
|
| 2388 |
+
"step": 27700
|
| 2389 |
+
},
|
| 2390 |
+
{
|
| 2391 |
+
"epoch": 1.953584792958662,
|
| 2392 |
+
"grad_norm": 0.6281931400299072,
|
| 2393 |
+
"learning_rate": 6.976689703642966e-05,
|
| 2394 |
+
"loss": 0.5265,
|
| 2395 |
+
"step": 27800
|
| 2396 |
+
},
|
| 2397 |
+
{
|
| 2398 |
+
"epoch": 1.9606120763865709,
|
| 2399 |
+
"grad_norm": 0.7378135323524475,
|
| 2400 |
+
"learning_rate": 6.929834836593652e-05,
|
| 2401 |
+
"loss": 0.5241,
|
| 2402 |
+
"step": 27900
|
| 2403 |
+
},
|
| 2404 |
+
{
|
| 2405 |
+
"epoch": 1.9676393598144797,
|
| 2406 |
+
"grad_norm": 0.5289490222930908,
|
| 2407 |
+
"learning_rate": 6.882979969544337e-05,
|
| 2408 |
+
"loss": 0.5327,
|
| 2409 |
+
"step": 28000
|
| 2410 |
+
},
|
| 2411 |
+
{
|
| 2412 |
+
"epoch": 1.9676393598144797,
|
| 2413 |
+
"eval_loss": 0.5690564513206482,
|
| 2414 |
+
"eval_runtime": 191.2308,
|
| 2415 |
+
"eval_samples_per_second": 66.145,
|
| 2416 |
+
"eval_steps_per_second": 8.273,
|
| 2417 |
+
"step": 28000
|
| 2418 |
+
}
|
| 2419 |
+
],
|
| 2420 |
+
"logging_steps": 100,
|
| 2421 |
+
"max_steps": 42690,
|
| 2422 |
+
"num_input_tokens_seen": 0,
|
| 2423 |
+
"num_train_epochs": 3,
|
| 2424 |
+
"save_steps": 1000,
|
| 2425 |
+
"stateful_callbacks": {
|
| 2426 |
+
"TrainerControl": {
|
| 2427 |
+
"args": {
|
| 2428 |
+
"should_epoch_stop": false,
|
| 2429 |
+
"should_evaluate": false,
|
| 2430 |
+
"should_log": false,
|
| 2431 |
+
"should_save": true,
|
| 2432 |
+
"should_training_stop": false
|
| 2433 |
+
},
|
| 2434 |
+
"attributes": {}
|
| 2435 |
+
}
|
| 2436 |
+
},
|
| 2437 |
+
"total_flos": 5.0643079170298675e+17,
|
| 2438 |
+
"train_batch_size": 2,
|
| 2439 |
+
"trial_name": null,
|
| 2440 |
+
"trial_params": null
|
| 2441 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:02cecf4f42ec778ff1f7e0a8532fccfddf01c4de908690f2c716c868f69c5412
|
| 3 |
+
size 4987
|