Upload folder using huggingface_hub
Browse files- adapter_config.json +2 -2
- adapter_model.bin +1 -1
- checkpoint-1500/README.md +202 -0
- checkpoint-1500/adapter_config.json +30 -0
- checkpoint-1500/adapter_model.safetensors +3 -0
- checkpoint-1500/optimizer.pt +3 -0
- checkpoint-1500/rng_state.pth +3 -0
- checkpoint-1500/scheduler.pt +3 -0
- checkpoint-1500/special_tokens_map.json +23 -0
- checkpoint-1500/tokenizer.model +3 -0
- checkpoint-1500/tokenizer_config.json +43 -0
- checkpoint-1500/trainer_state.json +2658 -0
- checkpoint-1500/training_args.bin +3 -0
- trainer_state.json +0 -0
adapter_config.json
CHANGED
|
@@ -20,9 +20,9 @@
|
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
| 23 |
-
"
|
| 24 |
"v_proj",
|
| 25 |
-
"
|
| 26 |
],
|
| 27 |
"task_type": "CAUSAL_LM",
|
| 28 |
"use_dora": false,
|
|
|
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
| 23 |
+
"q_proj",
|
| 24 |
"v_proj",
|
| 25 |
+
"k_proj"
|
| 26 |
],
|
| 27 |
"task_type": "CAUSAL_LM",
|
| 28 |
"use_dora": false,
|
adapter_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 100733002
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e1efd888f4565a0c6f252f53fb2d520cdae353f3ac6f7b318cf5a66dac8c4c86
|
| 3 |
size 100733002
|
checkpoint-1500/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: FlagAlpha/Llama2-Chinese-7b-Chat
|
| 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 0.11.1
|
checkpoint-1500/adapter_config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "FlagAlpha/Llama2-Chinese-7b-Chat",
|
| 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": 128,
|
| 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": 64,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"q_proj",
|
| 24 |
+
"v_proj",
|
| 25 |
+
"k_proj"
|
| 26 |
+
],
|
| 27 |
+
"task_type": "CAUSAL_LM",
|
| 28 |
+
"use_dora": false,
|
| 29 |
+
"use_rslora": false
|
| 30 |
+
}
|
checkpoint-1500/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8607b9b56bcdfaeb6b3c76736547e896aba4ac5151c781e13e3fd6b4549e38ab
|
| 3 |
+
size 100689344
|
checkpoint-1500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f450b6a41305430d5bbd8d6d61835cc8651a7979b67aa7200bfdbbb2ea6c642b
|
| 3 |
+
size 201488570
|
checkpoint-1500/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8d03a096db7ee5a1191528b365ea5b44b41de47ef2fcd633a48ead136d5f3f4f
|
| 3 |
+
size 14244
|
checkpoint-1500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:16bb6eb3e071ae677d4ff02f958ab690aa9cdb0fd86a22d9cdf4c9c04c998c00
|
| 3 |
+
size 1064
|
checkpoint-1500/special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"unk_token": {
|
| 17 |
+
"content": "<unk>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
checkpoint-1500/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
checkpoint-1500/tokenizer_config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": true,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<unk>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"2": {
|
| 23 |
+
"content": "</s>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
}
|
| 30 |
+
},
|
| 31 |
+
"bos_token": "<s>",
|
| 32 |
+
"clean_up_tokenization_spaces": false,
|
| 33 |
+
"eos_token": "</s>",
|
| 34 |
+
"legacy": false,
|
| 35 |
+
"model_max_length": 512,
|
| 36 |
+
"pad_token": null,
|
| 37 |
+
"sp_model_kwargs": {},
|
| 38 |
+
"spaces_between_special_tokens": false,
|
| 39 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 40 |
+
"unk_token": "<unk>",
|
| 41 |
+
"use_default_system_prompt": false,
|
| 42 |
+
"use_fast": false
|
| 43 |
+
}
|
checkpoint-1500/trainer_state.json
ADDED
|
@@ -0,0 +1,2658 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.5353121801432958,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1500,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0040941658137154556,
|
| 13 |
+
"grad_norm": 0.59375,
|
| 14 |
+
"learning_rate": 5.9999999999999995e-05,
|
| 15 |
+
"loss": 0.6558,
|
| 16 |
+
"step": 4
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.008188331627430911,
|
| 20 |
+
"grad_norm": 0.46875,
|
| 21 |
+
"learning_rate": 0.00011999999999999999,
|
| 22 |
+
"loss": 0.6895,
|
| 23 |
+
"step": 8
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.012282497441146366,
|
| 27 |
+
"grad_norm": 0.4296875,
|
| 28 |
+
"learning_rate": 0.00017999999999999998,
|
| 29 |
+
"loss": 0.641,
|
| 30 |
+
"step": 12
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.016376663254861822,
|
| 34 |
+
"grad_norm": 0.357421875,
|
| 35 |
+
"learning_rate": 0.00023999999999999998,
|
| 36 |
+
"loss": 0.6635,
|
| 37 |
+
"step": 16
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.02047082906857728,
|
| 41 |
+
"grad_norm": 0.4296875,
|
| 42 |
+
"learning_rate": 0.0003,
|
| 43 |
+
"loss": 0.6486,
|
| 44 |
+
"step": 20
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.02456499488229273,
|
| 48 |
+
"grad_norm": 0.408203125,
|
| 49 |
+
"learning_rate": 0.0002999968335945527,
|
| 50 |
+
"loss": 0.6335,
|
| 51 |
+
"step": 24
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.028659160696008188,
|
| 55 |
+
"grad_norm": 0.404296875,
|
| 56 |
+
"learning_rate": 0.00029998733451189267,
|
| 57 |
+
"loss": 0.6513,
|
| 58 |
+
"step": 28
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.032753326509723645,
|
| 62 |
+
"grad_norm": 0.388671875,
|
| 63 |
+
"learning_rate": 0.0002999715031530591,
|
| 64 |
+
"loss": 0.6439,
|
| 65 |
+
"step": 32
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.0368474923234391,
|
| 69 |
+
"grad_norm": 0.4296875,
|
| 70 |
+
"learning_rate": 0.000299949340186432,
|
| 71 |
+
"loss": 0.6304,
|
| 72 |
+
"step": 36
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.04094165813715456,
|
| 76 |
+
"grad_norm": 0.423828125,
|
| 77 |
+
"learning_rate": 0.0002999208465477039,
|
| 78 |
+
"loss": 0.6772,
|
| 79 |
+
"step": 40
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.04503582395087001,
|
| 83 |
+
"grad_norm": 0.404296875,
|
| 84 |
+
"learning_rate": 0.0002998860234398403,
|
| 85 |
+
"loss": 0.6294,
|
| 86 |
+
"step": 44
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.04912998976458546,
|
| 90 |
+
"grad_norm": 0.396484375,
|
| 91 |
+
"learning_rate": 0.0002998448723330289,
|
| 92 |
+
"loss": 0.6093,
|
| 93 |
+
"step": 48
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.05322415557830092,
|
| 97 |
+
"grad_norm": 0.408203125,
|
| 98 |
+
"learning_rate": 0.0002997973949646176,
|
| 99 |
+
"loss": 0.6516,
|
| 100 |
+
"step": 52
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.057318321392016376,
|
| 104 |
+
"grad_norm": 0.443359375,
|
| 105 |
+
"learning_rate": 0.0002997435933390409,
|
| 106 |
+
"loss": 0.6261,
|
| 107 |
+
"step": 56
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.06141248720573183,
|
| 111 |
+
"grad_norm": 0.390625,
|
| 112 |
+
"learning_rate": 0.0002996834697277358,
|
| 113 |
+
"loss": 0.6294,
|
| 114 |
+
"step": 60
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.06550665301944729,
|
| 118 |
+
"grad_norm": 0.38671875,
|
| 119 |
+
"learning_rate": 0.00029961702666904524,
|
| 120 |
+
"loss": 0.615,
|
| 121 |
+
"step": 64
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.06960081883316274,
|
| 125 |
+
"grad_norm": 0.40234375,
|
| 126 |
+
"learning_rate": 0.00029954426696811147,
|
| 127 |
+
"loss": 0.6036,
|
| 128 |
+
"step": 68
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.0736949846468782,
|
| 132 |
+
"grad_norm": 0.3984375,
|
| 133 |
+
"learning_rate": 0.00029946519369675726,
|
| 134 |
+
"loss": 0.5834,
|
| 135 |
+
"step": 72
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.07778915046059365,
|
| 139 |
+
"grad_norm": 0.37109375,
|
| 140 |
+
"learning_rate": 0.0002993798101933565,
|
| 141 |
+
"loss": 0.628,
|
| 142 |
+
"step": 76
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.08188331627430911,
|
| 146 |
+
"grad_norm": 0.39453125,
|
| 147 |
+
"learning_rate": 0.000299288120062693,
|
| 148 |
+
"loss": 0.6307,
|
| 149 |
+
"step": 80
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.08597748208802457,
|
| 153 |
+
"grad_norm": 0.3984375,
|
| 154 |
+
"learning_rate": 0.0002991901271758085,
|
| 155 |
+
"loss": 0.6392,
|
| 156 |
+
"step": 84
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.09007164790174002,
|
| 160 |
+
"grad_norm": 0.419921875,
|
| 161 |
+
"learning_rate": 0.0002990858356698392,
|
| 162 |
+
"loss": 0.6184,
|
| 163 |
+
"step": 88
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.09416581371545547,
|
| 167 |
+
"grad_norm": 0.390625,
|
| 168 |
+
"learning_rate": 0.00029897524994784095,
|
| 169 |
+
"loss": 0.6669,
|
| 170 |
+
"step": 92
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.09825997952917093,
|
| 174 |
+
"grad_norm": 0.353515625,
|
| 175 |
+
"learning_rate": 0.0002988583746786035,
|
| 176 |
+
"loss": 0.6474,
|
| 177 |
+
"step": 96
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.1023541453428864,
|
| 181 |
+
"grad_norm": 0.41015625,
|
| 182 |
+
"learning_rate": 0.0002987352147964534,
|
| 183 |
+
"loss": 0.6427,
|
| 184 |
+
"step": 100
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.10644831115660185,
|
| 188 |
+
"grad_norm": 0.369140625,
|
| 189 |
+
"learning_rate": 0.00029860577550104567,
|
| 190 |
+
"loss": 0.6331,
|
| 191 |
+
"step": 104
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.1105424769703173,
|
| 195 |
+
"grad_norm": 0.35546875,
|
| 196 |
+
"learning_rate": 0.0002984700622571441,
|
| 197 |
+
"loss": 0.6274,
|
| 198 |
+
"step": 108
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.11463664278403275,
|
| 202 |
+
"grad_norm": 0.40234375,
|
| 203 |
+
"learning_rate": 0.00029832808079439076,
|
| 204 |
+
"loss": 0.6363,
|
| 205 |
+
"step": 112
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.1187308085977482,
|
| 209 |
+
"grad_norm": 0.57421875,
|
| 210 |
+
"learning_rate": 0.000298179837107064,
|
| 211 |
+
"loss": 0.6413,
|
| 212 |
+
"step": 116
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.12282497441146366,
|
| 216 |
+
"grad_norm": 0.390625,
|
| 217 |
+
"learning_rate": 0.00029802533745382546,
|
| 218 |
+
"loss": 0.6439,
|
| 219 |
+
"step": 120
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.1269191402251791,
|
| 223 |
+
"grad_norm": 0.3984375,
|
| 224 |
+
"learning_rate": 0.00029786458835745564,
|
| 225 |
+
"loss": 0.6274,
|
| 226 |
+
"step": 124
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.13101330603889458,
|
| 230 |
+
"grad_norm": 0.37890625,
|
| 231 |
+
"learning_rate": 0.0002976975966045788,
|
| 232 |
+
"loss": 0.605,
|
| 233 |
+
"step": 128
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.13510747185261002,
|
| 237 |
+
"grad_norm": 0.384765625,
|
| 238 |
+
"learning_rate": 0.00029752436924537616,
|
| 239 |
+
"loss": 0.6316,
|
| 240 |
+
"step": 132
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.13920163766632548,
|
| 244 |
+
"grad_norm": 0.376953125,
|
| 245 |
+
"learning_rate": 0.00029734491359328854,
|
| 246 |
+
"loss": 0.6802,
|
| 247 |
+
"step": 136
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.14329580348004095,
|
| 251 |
+
"grad_norm": 0.373046875,
|
| 252 |
+
"learning_rate": 0.00029715923722470724,
|
| 253 |
+
"loss": 0.6841,
|
| 254 |
+
"step": 140
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.1473899692937564,
|
| 258 |
+
"grad_norm": 0.396484375,
|
| 259 |
+
"learning_rate": 0.0002969673479786545,
|
| 260 |
+
"loss": 0.6004,
|
| 261 |
+
"step": 144
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.15148413510747186,
|
| 265 |
+
"grad_norm": 0.380859375,
|
| 266 |
+
"learning_rate": 0.00029676925395645233,
|
| 267 |
+
"loss": 0.671,
|
| 268 |
+
"step": 148
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.1555783009211873,
|
| 272 |
+
"grad_norm": 0.37890625,
|
| 273 |
+
"learning_rate": 0.00029656496352138066,
|
| 274 |
+
"loss": 0.6257,
|
| 275 |
+
"step": 152
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.15967246673490276,
|
| 279 |
+
"grad_norm": 0.384765625,
|
| 280 |
+
"learning_rate": 0.00029635448529832407,
|
| 281 |
+
"loss": 0.6141,
|
| 282 |
+
"step": 156
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.16376663254861823,
|
| 286 |
+
"grad_norm": 0.390625,
|
| 287 |
+
"learning_rate": 0.0002961378281734078,
|
| 288 |
+
"loss": 0.6391,
|
| 289 |
+
"step": 160
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.16786079836233367,
|
| 293 |
+
"grad_norm": 0.396484375,
|
| 294 |
+
"learning_rate": 0.00029591500129362255,
|
| 295 |
+
"loss": 0.6211,
|
| 296 |
+
"step": 164
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.17195496417604914,
|
| 300 |
+
"grad_norm": 0.369140625,
|
| 301 |
+
"learning_rate": 0.00029568601406643826,
|
| 302 |
+
"loss": 0.6644,
|
| 303 |
+
"step": 168
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.17604912998976457,
|
| 307 |
+
"grad_norm": 0.388671875,
|
| 308 |
+
"learning_rate": 0.0002954508761594069,
|
| 309 |
+
"loss": 0.6667,
|
| 310 |
+
"step": 172
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.18014329580348004,
|
| 314 |
+
"grad_norm": 0.412109375,
|
| 315 |
+
"learning_rate": 0.0002952095974997546,
|
| 316 |
+
"loss": 0.6351,
|
| 317 |
+
"step": 176
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.1842374616171955,
|
| 321 |
+
"grad_norm": 0.390625,
|
| 322 |
+
"learning_rate": 0.0002949621882739621,
|
| 323 |
+
"loss": 0.6142,
|
| 324 |
+
"step": 180
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.18833162743091095,
|
| 328 |
+
"grad_norm": 0.412109375,
|
| 329 |
+
"learning_rate": 0.000294708658927335,
|
| 330 |
+
"loss": 0.6569,
|
| 331 |
+
"step": 184
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.19242579324462641,
|
| 335 |
+
"grad_norm": 0.353515625,
|
| 336 |
+
"learning_rate": 0.00029444902016356267,
|
| 337 |
+
"loss": 0.6272,
|
| 338 |
+
"step": 188
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.19651995905834185,
|
| 342 |
+
"grad_norm": 0.37109375,
|
| 343 |
+
"learning_rate": 0.00029418328294426643,
|
| 344 |
+
"loss": 0.6742,
|
| 345 |
+
"step": 192
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.20061412487205732,
|
| 349 |
+
"grad_norm": 0.404296875,
|
| 350 |
+
"learning_rate": 0.00029391145848853674,
|
| 351 |
+
"loss": 0.6513,
|
| 352 |
+
"step": 196
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.2047082906857728,
|
| 356 |
+
"grad_norm": 0.37109375,
|
| 357 |
+
"learning_rate": 0.00029363355827245925,
|
| 358 |
+
"loss": 0.6369,
|
| 359 |
+
"step": 200
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.20880245649948823,
|
| 363 |
+
"grad_norm": 0.376953125,
|
| 364 |
+
"learning_rate": 0.0002933495940286309,
|
| 365 |
+
"loss": 0.6371,
|
| 366 |
+
"step": 204
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.2128966223132037,
|
| 370 |
+
"grad_norm": 0.376953125,
|
| 371 |
+
"learning_rate": 0.000293059577745664,
|
| 372 |
+
"loss": 0.6745,
|
| 373 |
+
"step": 208
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.21699078812691913,
|
| 377 |
+
"grad_norm": 0.376953125,
|
| 378 |
+
"learning_rate": 0.00029276352166768033,
|
| 379 |
+
"loss": 0.6577,
|
| 380 |
+
"step": 212
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.2210849539406346,
|
| 384 |
+
"grad_norm": 0.392578125,
|
| 385 |
+
"learning_rate": 0.0002924614382937944,
|
| 386 |
+
"loss": 0.6224,
|
| 387 |
+
"step": 216
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.22517911975435004,
|
| 391 |
+
"grad_norm": 0.37109375,
|
| 392 |
+
"learning_rate": 0.0002921533403775853,
|
| 393 |
+
"loss": 0.6471,
|
| 394 |
+
"step": 220
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.2292732855680655,
|
| 398 |
+
"grad_norm": 0.3828125,
|
| 399 |
+
"learning_rate": 0.0002918392409265587,
|
| 400 |
+
"loss": 0.6583,
|
| 401 |
+
"step": 224
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.23336745138178097,
|
| 405 |
+
"grad_norm": 0.390625,
|
| 406 |
+
"learning_rate": 0.00029151915320159747,
|
| 407 |
+
"loss": 0.6408,
|
| 408 |
+
"step": 228
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.2374616171954964,
|
| 412 |
+
"grad_norm": 0.396484375,
|
| 413 |
+
"learning_rate": 0.0002911930907164017,
|
| 414 |
+
"loss": 0.6275,
|
| 415 |
+
"step": 232
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.24155578300921188,
|
| 419 |
+
"grad_norm": 0.359375,
|
| 420 |
+
"learning_rate": 0.00029086106723691857,
|
| 421 |
+
"loss": 0.6083,
|
| 422 |
+
"step": 236
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.24564994882292732,
|
| 426 |
+
"grad_norm": 0.37890625,
|
| 427 |
+
"learning_rate": 0.00029052309678076065,
|
| 428 |
+
"loss": 0.5966,
|
| 429 |
+
"step": 240
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.24974411463664278,
|
| 433 |
+
"grad_norm": 0.3671875,
|
| 434 |
+
"learning_rate": 0.0002901791936166147,
|
| 435 |
+
"loss": 0.6294,
|
| 436 |
+
"step": 244
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.2538382804503582,
|
| 440 |
+
"grad_norm": 0.390625,
|
| 441 |
+
"learning_rate": 0.0002898293722636386,
|
| 442 |
+
"loss": 0.647,
|
| 443 |
+
"step": 248
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.2579324462640737,
|
| 447 |
+
"grad_norm": 0.421875,
|
| 448 |
+
"learning_rate": 0.00028947364749084897,
|
| 449 |
+
"loss": 0.6532,
|
| 450 |
+
"step": 252
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.26202661207778916,
|
| 454 |
+
"grad_norm": 0.38671875,
|
| 455 |
+
"learning_rate": 0.0002891120343164972,
|
| 456 |
+
"loss": 0.6059,
|
| 457 |
+
"step": 256
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.2661207778915046,
|
| 461 |
+
"grad_norm": 0.39453125,
|
| 462 |
+
"learning_rate": 0.00028874454800743556,
|
| 463 |
+
"loss": 0.6545,
|
| 464 |
+
"step": 260
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.27021494370522003,
|
| 468 |
+
"grad_norm": 0.365234375,
|
| 469 |
+
"learning_rate": 0.00028837120407847286,
|
| 470 |
+
"loss": 0.6462,
|
| 471 |
+
"step": 264
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.2743091095189355,
|
| 475 |
+
"grad_norm": 0.373046875,
|
| 476 |
+
"learning_rate": 0.000287992018291719,
|
| 477 |
+
"loss": 0.6337,
|
| 478 |
+
"step": 268
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.27840327533265097,
|
| 482 |
+
"grad_norm": 0.365234375,
|
| 483 |
+
"learning_rate": 0.00028760700665591985,
|
| 484 |
+
"loss": 0.6431,
|
| 485 |
+
"step": 272
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.28249744114636643,
|
| 489 |
+
"grad_norm": 0.353515625,
|
| 490 |
+
"learning_rate": 0.0002872161854257814,
|
| 491 |
+
"loss": 0.6797,
|
| 492 |
+
"step": 276
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.2865916069600819,
|
| 496 |
+
"grad_norm": 0.369140625,
|
| 497 |
+
"learning_rate": 0.00028681957110128313,
|
| 498 |
+
"loss": 0.6191,
|
| 499 |
+
"step": 280
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.2906857727737973,
|
| 503 |
+
"grad_norm": 0.384765625,
|
| 504 |
+
"learning_rate": 0.000286417180426982,
|
| 505 |
+
"loss": 0.6064,
|
| 506 |
+
"step": 284
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.2947799385875128,
|
| 510 |
+
"grad_norm": 0.369140625,
|
| 511 |
+
"learning_rate": 0.0002860090303913048,
|
| 512 |
+
"loss": 0.6451,
|
| 513 |
+
"step": 288
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.29887410440122825,
|
| 517 |
+
"grad_norm": 0.380859375,
|
| 518 |
+
"learning_rate": 0.00028559513822583153,
|
| 519 |
+
"loss": 0.6402,
|
| 520 |
+
"step": 292
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.3029682702149437,
|
| 524 |
+
"grad_norm": 0.408203125,
|
| 525 |
+
"learning_rate": 0.0002851755214045676,
|
| 526 |
+
"loss": 0.655,
|
| 527 |
+
"step": 296
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.3070624360286592,
|
| 531 |
+
"grad_norm": 0.349609375,
|
| 532 |
+
"learning_rate": 0.00028475019764320634,
|
| 533 |
+
"loss": 0.6627,
|
| 534 |
+
"step": 300
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.3111566018423746,
|
| 538 |
+
"grad_norm": 0.390625,
|
| 539 |
+
"learning_rate": 0.00028431918489838057,
|
| 540 |
+
"loss": 0.6654,
|
| 541 |
+
"step": 304
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.31525076765609006,
|
| 545 |
+
"grad_norm": 0.365234375,
|
| 546 |
+
"learning_rate": 0.0002838825013669051,
|
| 547 |
+
"loss": 0.6193,
|
| 548 |
+
"step": 308
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.3193449334698055,
|
| 552 |
+
"grad_norm": 0.396484375,
|
| 553 |
+
"learning_rate": 0.000283440165485008,
|
| 554 |
+
"loss": 0.6411,
|
| 555 |
+
"step": 312
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.323439099283521,
|
| 559 |
+
"grad_norm": 0.35546875,
|
| 560 |
+
"learning_rate": 0.00028299219592755264,
|
| 561 |
+
"loss": 0.5887,
|
| 562 |
+
"step": 316
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.32753326509723646,
|
| 566 |
+
"grad_norm": 0.373046875,
|
| 567 |
+
"learning_rate": 0.000282538611607249,
|
| 568 |
+
"loss": 0.5907,
|
| 569 |
+
"step": 320
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.33162743091095187,
|
| 573 |
+
"grad_norm": 0.369140625,
|
| 574 |
+
"learning_rate": 0.00028207943167385516,
|
| 575 |
+
"loss": 0.6408,
|
| 576 |
+
"step": 324
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.33572159672466734,
|
| 580 |
+
"grad_norm": 0.4140625,
|
| 581 |
+
"learning_rate": 0.000281614675513369,
|
| 582 |
+
"loss": 0.5642,
|
| 583 |
+
"step": 328
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.3398157625383828,
|
| 587 |
+
"grad_norm": 0.392578125,
|
| 588 |
+
"learning_rate": 0.0002811443627472098,
|
| 589 |
+
"loss": 0.6303,
|
| 590 |
+
"step": 332
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.34390992835209827,
|
| 594 |
+
"grad_norm": 0.369140625,
|
| 595 |
+
"learning_rate": 0.0002806685132313896,
|
| 596 |
+
"loss": 0.6267,
|
| 597 |
+
"step": 336
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.34800409416581374,
|
| 601 |
+
"grad_norm": 0.35546875,
|
| 602 |
+
"learning_rate": 0.00028018714705567503,
|
| 603 |
+
"loss": 0.6681,
|
| 604 |
+
"step": 340
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.35209825997952915,
|
| 608 |
+
"grad_norm": 0.3671875,
|
| 609 |
+
"learning_rate": 0.00027970028454273917,
|
| 610 |
+
"loss": 0.6606,
|
| 611 |
+
"step": 344
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.3561924257932446,
|
| 615 |
+
"grad_norm": 0.373046875,
|
| 616 |
+
"learning_rate": 0.0002792079462473035,
|
| 617 |
+
"loss": 0.6027,
|
| 618 |
+
"step": 348
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.3602865916069601,
|
| 622 |
+
"grad_norm": 0.400390625,
|
| 623 |
+
"learning_rate": 0.0002787101529552702,
|
| 624 |
+
"loss": 0.6485,
|
| 625 |
+
"step": 352
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.36438075742067555,
|
| 629 |
+
"grad_norm": 0.33984375,
|
| 630 |
+
"learning_rate": 0.0002782069256828445,
|
| 631 |
+
"loss": 0.6345,
|
| 632 |
+
"step": 356
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.368474923234391,
|
| 636 |
+
"grad_norm": 0.38671875,
|
| 637 |
+
"learning_rate": 0.0002776982856756473,
|
| 638 |
+
"loss": 0.6211,
|
| 639 |
+
"step": 360
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.3725690890481064,
|
| 643 |
+
"grad_norm": 0.384765625,
|
| 644 |
+
"learning_rate": 0.0002771842544078187,
|
| 645 |
+
"loss": 0.598,
|
| 646 |
+
"step": 364
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.3766632548618219,
|
| 650 |
+
"grad_norm": 0.369140625,
|
| 651 |
+
"learning_rate": 0.0002766648535811105,
|
| 652 |
+
"loss": 0.6719,
|
| 653 |
+
"step": 368
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.38075742067553736,
|
| 657 |
+
"grad_norm": 0.341796875,
|
| 658 |
+
"learning_rate": 0.000276140105123971,
|
| 659 |
+
"loss": 0.6142,
|
| 660 |
+
"step": 372
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.38485158648925283,
|
| 664 |
+
"grad_norm": 0.365234375,
|
| 665 |
+
"learning_rate": 0.0002756100311906185,
|
| 666 |
+
"loss": 0.6187,
|
| 667 |
+
"step": 376
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.3889457523029683,
|
| 671 |
+
"grad_norm": 0.365234375,
|
| 672 |
+
"learning_rate": 0.000275074654160106,
|
| 673 |
+
"loss": 0.6373,
|
| 674 |
+
"step": 380
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.3930399181166837,
|
| 678 |
+
"grad_norm": 0.361328125,
|
| 679 |
+
"learning_rate": 0.00027453399663537707,
|
| 680 |
+
"loss": 0.6376,
|
| 681 |
+
"step": 384
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.3971340839303992,
|
| 685 |
+
"grad_norm": 0.365234375,
|
| 686 |
+
"learning_rate": 0.0002739880814423106,
|
| 687 |
+
"loss": 0.6187,
|
| 688 |
+
"step": 388
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.40122824974411464,
|
| 692 |
+
"grad_norm": 0.357421875,
|
| 693 |
+
"learning_rate": 0.0002734369316287578,
|
| 694 |
+
"loss": 0.648,
|
| 695 |
+
"step": 392
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.4053224155578301,
|
| 699 |
+
"grad_norm": 0.365234375,
|
| 700 |
+
"learning_rate": 0.0002728805704635691,
|
| 701 |
+
"loss": 0.6342,
|
| 702 |
+
"step": 396
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.4094165813715456,
|
| 706 |
+
"grad_norm": 0.3671875,
|
| 707 |
+
"learning_rate": 0.0002723190214356113,
|
| 708 |
+
"loss": 0.584,
|
| 709 |
+
"step": 400
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.413510747185261,
|
| 713 |
+
"grad_norm": 0.416015625,
|
| 714 |
+
"learning_rate": 0.0002717523082527766,
|
| 715 |
+
"loss": 0.6497,
|
| 716 |
+
"step": 404
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.41760491299897645,
|
| 720 |
+
"grad_norm": 0.365234375,
|
| 721 |
+
"learning_rate": 0.00027118045484098095,
|
| 722 |
+
"loss": 0.6038,
|
| 723 |
+
"step": 408
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.4216990788126919,
|
| 727 |
+
"grad_norm": 0.37109375,
|
| 728 |
+
"learning_rate": 0.0002706034853431546,
|
| 729 |
+
"loss": 0.6665,
|
| 730 |
+
"step": 412
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.4257932446264074,
|
| 734 |
+
"grad_norm": 0.341796875,
|
| 735 |
+
"learning_rate": 0.0002700214241182223,
|
| 736 |
+
"loss": 0.6422,
|
| 737 |
+
"step": 416
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.42988741044012285,
|
| 741 |
+
"grad_norm": 0.36328125,
|
| 742 |
+
"learning_rate": 0.00026943429574007515,
|
| 743 |
+
"loss": 0.5954,
|
| 744 |
+
"step": 420
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.43398157625383826,
|
| 748 |
+
"grad_norm": 0.388671875,
|
| 749 |
+
"learning_rate": 0.0002688421249965331,
|
| 750 |
+
"loss": 0.5899,
|
| 751 |
+
"step": 424
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.43807574206755373,
|
| 755 |
+
"grad_norm": 0.388671875,
|
| 756 |
+
"learning_rate": 0.0002682449368882984,
|
| 757 |
+
"loss": 0.5858,
|
| 758 |
+
"step": 428
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.4421699078812692,
|
| 762 |
+
"grad_norm": 0.376953125,
|
| 763 |
+
"learning_rate": 0.00026764275662790005,
|
| 764 |
+
"loss": 0.6247,
|
| 765 |
+
"step": 432
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.44626407369498466,
|
| 769 |
+
"grad_norm": 0.357421875,
|
| 770 |
+
"learning_rate": 0.00026703560963862956,
|
| 771 |
+
"loss": 0.5961,
|
| 772 |
+
"step": 436
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 0.4503582395087001,
|
| 776 |
+
"grad_norm": 0.390625,
|
| 777 |
+
"learning_rate": 0.0002664235215534673,
|
| 778 |
+
"loss": 0.6428,
|
| 779 |
+
"step": 440
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.45445240532241554,
|
| 783 |
+
"grad_norm": 0.376953125,
|
| 784 |
+
"learning_rate": 0.00026580651821400057,
|
| 785 |
+
"loss": 0.6387,
|
| 786 |
+
"step": 444
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.458546571136131,
|
| 790 |
+
"grad_norm": 0.3828125,
|
| 791 |
+
"learning_rate": 0.0002651846256693326,
|
| 792 |
+
"loss": 0.6024,
|
| 793 |
+
"step": 448
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.4626407369498465,
|
| 797 |
+
"grad_norm": 0.369140625,
|
| 798 |
+
"learning_rate": 0.00026455787017498253,
|
| 799 |
+
"loss": 0.6385,
|
| 800 |
+
"step": 452
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.46673490276356194,
|
| 804 |
+
"grad_norm": 0.365234375,
|
| 805 |
+
"learning_rate": 0.0002639262781917771,
|
| 806 |
+
"loss": 0.6228,
|
| 807 |
+
"step": 456
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.47082906857727735,
|
| 811 |
+
"grad_norm": 0.373046875,
|
| 812 |
+
"learning_rate": 0.0002632898763847338,
|
| 813 |
+
"loss": 0.6307,
|
| 814 |
+
"step": 460
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 0.4749232343909928,
|
| 818 |
+
"grad_norm": 0.392578125,
|
| 819 |
+
"learning_rate": 0.0002626486916219344,
|
| 820 |
+
"loss": 0.6465,
|
| 821 |
+
"step": 464
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.4790174002047083,
|
| 825 |
+
"grad_norm": 0.384765625,
|
| 826 |
+
"learning_rate": 0.0002620027509733914,
|
| 827 |
+
"loss": 0.6349,
|
| 828 |
+
"step": 468
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.48311156601842375,
|
| 832 |
+
"grad_norm": 0.3671875,
|
| 833 |
+
"learning_rate": 0.0002613520817099045,
|
| 834 |
+
"loss": 0.6223,
|
| 835 |
+
"step": 472
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.4872057318321392,
|
| 839 |
+
"grad_norm": 0.373046875,
|
| 840 |
+
"learning_rate": 0.0002606967113019098,
|
| 841 |
+
"loss": 0.605,
|
| 842 |
+
"step": 476
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.49129989764585463,
|
| 846 |
+
"grad_norm": 0.40234375,
|
| 847 |
+
"learning_rate": 0.0002600366674183196,
|
| 848 |
+
"loss": 0.6169,
|
| 849 |
+
"step": 480
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.4953940634595701,
|
| 853 |
+
"grad_norm": 0.3515625,
|
| 854 |
+
"learning_rate": 0.0002593719779253548,
|
| 855 |
+
"loss": 0.6289,
|
| 856 |
+
"step": 484
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.49948822927328557,
|
| 860 |
+
"grad_norm": 0.380859375,
|
| 861 |
+
"learning_rate": 0.0002587026708853674,
|
| 862 |
+
"loss": 0.6718,
|
| 863 |
+
"step": 488
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.503582395087001,
|
| 867 |
+
"grad_norm": 0.396484375,
|
| 868 |
+
"learning_rate": 0.0002580287745556572,
|
| 869 |
+
"loss": 0.5592,
|
| 870 |
+
"step": 492
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 0.5076765609007164,
|
| 874 |
+
"grad_norm": 0.392578125,
|
| 875 |
+
"learning_rate": 0.00025735031738727753,
|
| 876 |
+
"loss": 0.6118,
|
| 877 |
+
"step": 496
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.5117707267144319,
|
| 881 |
+
"grad_norm": 0.380859375,
|
| 882 |
+
"learning_rate": 0.00025666732802383463,
|
| 883 |
+
"loss": 0.5798,
|
| 884 |
+
"step": 500
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.5158648925281474,
|
| 888 |
+
"grad_norm": 0.341796875,
|
| 889 |
+
"learning_rate": 0.0002559798353002785,
|
| 890 |
+
"loss": 0.6488,
|
| 891 |
+
"step": 504
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.5199590583418628,
|
| 895 |
+
"grad_norm": 0.359375,
|
| 896 |
+
"learning_rate": 0.0002552878682416851,
|
| 897 |
+
"loss": 0.6363,
|
| 898 |
+
"step": 508
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.5240532241555783,
|
| 902 |
+
"grad_norm": 0.34375,
|
| 903 |
+
"learning_rate": 0.0002545914560620313,
|
| 904 |
+
"loss": 0.6246,
|
| 905 |
+
"step": 512
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.5281473899692938,
|
| 909 |
+
"grad_norm": 0.37109375,
|
| 910 |
+
"learning_rate": 0.00025389062816296153,
|
| 911 |
+
"loss": 0.6277,
|
| 912 |
+
"step": 516
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.5322415557830092,
|
| 916 |
+
"grad_norm": 0.357421875,
|
| 917 |
+
"learning_rate": 0.00025318541413254587,
|
| 918 |
+
"loss": 0.5822,
|
| 919 |
+
"step": 520
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.5363357215967247,
|
| 923 |
+
"grad_norm": 0.36328125,
|
| 924 |
+
"learning_rate": 0.0002524758437440318,
|
| 925 |
+
"loss": 0.581,
|
| 926 |
+
"step": 524
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.5404298874104401,
|
| 930 |
+
"grad_norm": 0.345703125,
|
| 931 |
+
"learning_rate": 0.00025176194695458644,
|
| 932 |
+
"loss": 0.6365,
|
| 933 |
+
"step": 528
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.5445240532241555,
|
| 937 |
+
"grad_norm": 0.357421875,
|
| 938 |
+
"learning_rate": 0.0002510437539040324,
|
| 939 |
+
"loss": 0.5974,
|
| 940 |
+
"step": 532
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.548618219037871,
|
| 944 |
+
"grad_norm": 0.3671875,
|
| 945 |
+
"learning_rate": 0.0002503212949135747,
|
| 946 |
+
"loss": 0.646,
|
| 947 |
+
"step": 536
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.5527123848515865,
|
| 951 |
+
"grad_norm": 0.373046875,
|
| 952 |
+
"learning_rate": 0.00024959460048452117,
|
| 953 |
+
"loss": 0.6508,
|
| 954 |
+
"step": 540
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.5568065506653019,
|
| 958 |
+
"grad_norm": 0.357421875,
|
| 959 |
+
"learning_rate": 0.0002488637012969945,
|
| 960 |
+
"loss": 0.5838,
|
| 961 |
+
"step": 544
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.5609007164790174,
|
| 965 |
+
"grad_norm": 0.337890625,
|
| 966 |
+
"learning_rate": 0.0002481286282086368,
|
| 967 |
+
"loss": 0.597,
|
| 968 |
+
"step": 548
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.5649948822927329,
|
| 972 |
+
"grad_norm": 0.380859375,
|
| 973 |
+
"learning_rate": 0.00024738941225330727,
|
| 974 |
+
"loss": 0.6617,
|
| 975 |
+
"step": 552
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.5690890481064483,
|
| 979 |
+
"grad_norm": 0.3671875,
|
| 980 |
+
"learning_rate": 0.00024664608463977164,
|
| 981 |
+
"loss": 0.5968,
|
| 982 |
+
"step": 556
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 0.5731832139201638,
|
| 986 |
+
"grad_norm": 0.3359375,
|
| 987 |
+
"learning_rate": 0.0002458986767503845,
|
| 988 |
+
"loss": 0.5837,
|
| 989 |
+
"step": 560
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.5772773797338793,
|
| 993 |
+
"grad_norm": 0.3828125,
|
| 994 |
+
"learning_rate": 0.00024514722013976485,
|
| 995 |
+
"loss": 0.6175,
|
| 996 |
+
"step": 564
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 0.5813715455475946,
|
| 1000 |
+
"grad_norm": 0.4140625,
|
| 1001 |
+
"learning_rate": 0.00024439174653346325,
|
| 1002 |
+
"loss": 0.592,
|
| 1003 |
+
"step": 568
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.5854657113613101,
|
| 1007 |
+
"grad_norm": 0.3515625,
|
| 1008 |
+
"learning_rate": 0.00024363228782662308,
|
| 1009 |
+
"loss": 0.6434,
|
| 1010 |
+
"step": 572
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.5895598771750256,
|
| 1014 |
+
"grad_norm": 0.3671875,
|
| 1015 |
+
"learning_rate": 0.0002428688760826334,
|
| 1016 |
+
"loss": 0.6441,
|
| 1017 |
+
"step": 576
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.593654042988741,
|
| 1021 |
+
"grad_norm": 0.3671875,
|
| 1022 |
+
"learning_rate": 0.00024210154353177562,
|
| 1023 |
+
"loss": 0.5881,
|
| 1024 |
+
"step": 580
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.5977482088024565,
|
| 1028 |
+
"grad_norm": 0.349609375,
|
| 1029 |
+
"learning_rate": 0.00024133032256986274,
|
| 1030 |
+
"loss": 0.6454,
|
| 1031 |
+
"step": 584
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.601842374616172,
|
| 1035 |
+
"grad_norm": 0.3203125,
|
| 1036 |
+
"learning_rate": 0.00024055524575687136,
|
| 1037 |
+
"loss": 0.5999,
|
| 1038 |
+
"step": 588
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 0.6059365404298874,
|
| 1042 |
+
"grad_norm": 0.345703125,
|
| 1043 |
+
"learning_rate": 0.00023977634581556743,
|
| 1044 |
+
"loss": 0.6028,
|
| 1045 |
+
"step": 592
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.6100307062436029,
|
| 1049 |
+
"grad_norm": 0.376953125,
|
| 1050 |
+
"learning_rate": 0.00023899365563012455,
|
| 1051 |
+
"loss": 0.5945,
|
| 1052 |
+
"step": 596
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.6141248720573184,
|
| 1056 |
+
"grad_norm": 0.38671875,
|
| 1057 |
+
"learning_rate": 0.00023820720824473555,
|
| 1058 |
+
"loss": 0.6106,
|
| 1059 |
+
"step": 600
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.6182190378710338,
|
| 1063 |
+
"grad_norm": 0.34765625,
|
| 1064 |
+
"learning_rate": 0.00023741703686221767,
|
| 1065 |
+
"loss": 0.6626,
|
| 1066 |
+
"step": 604
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.6223132036847492,
|
| 1070 |
+
"grad_norm": 0.361328125,
|
| 1071 |
+
"learning_rate": 0.00023662317484261038,
|
| 1072 |
+
"loss": 0.6107,
|
| 1073 |
+
"step": 608
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.6264073694984647,
|
| 1077 |
+
"grad_norm": 0.34765625,
|
| 1078 |
+
"learning_rate": 0.00023582565570176738,
|
| 1079 |
+
"loss": 0.5691,
|
| 1080 |
+
"step": 612
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 0.6305015353121801,
|
| 1084 |
+
"grad_norm": 0.330078125,
|
| 1085 |
+
"learning_rate": 0.00023502451310994138,
|
| 1086 |
+
"loss": 0.648,
|
| 1087 |
+
"step": 616
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.6345957011258956,
|
| 1091 |
+
"grad_norm": 0.359375,
|
| 1092 |
+
"learning_rate": 0.0002342197808903626,
|
| 1093 |
+
"loss": 0.6255,
|
| 1094 |
+
"step": 620
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 0.638689866939611,
|
| 1098 |
+
"grad_norm": 0.33984375,
|
| 1099 |
+
"learning_rate": 0.00023341149301781076,
|
| 1100 |
+
"loss": 0.6423,
|
| 1101 |
+
"step": 624
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.6427840327533265,
|
| 1105 |
+
"grad_norm": 0.353515625,
|
| 1106 |
+
"learning_rate": 0.00023259968361718093,
|
| 1107 |
+
"loss": 0.6358,
|
| 1108 |
+
"step": 628
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 0.646878198567042,
|
| 1112 |
+
"grad_norm": 0.328125,
|
| 1113 |
+
"learning_rate": 0.00023178438696204248,
|
| 1114 |
+
"loss": 0.6217,
|
| 1115 |
+
"step": 632
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.6509723643807575,
|
| 1119 |
+
"grad_norm": 0.380859375,
|
| 1120 |
+
"learning_rate": 0.0002309656374731923,
|
| 1121 |
+
"loss": 0.6543,
|
| 1122 |
+
"step": 636
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.6550665301944729,
|
| 1126 |
+
"grad_norm": 0.326171875,
|
| 1127 |
+
"learning_rate": 0.00023014346971720172,
|
| 1128 |
+
"loss": 0.6438,
|
| 1129 |
+
"step": 640
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.6591606960081884,
|
| 1133 |
+
"grad_norm": 0.337890625,
|
| 1134 |
+
"learning_rate": 0.00022931791840495683,
|
| 1135 |
+
"loss": 0.6364,
|
| 1136 |
+
"step": 644
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 0.6632548618219037,
|
| 1140 |
+
"grad_norm": 0.375,
|
| 1141 |
+
"learning_rate": 0.00022848901839019325,
|
| 1142 |
+
"loss": 0.5709,
|
| 1143 |
+
"step": 648
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.6673490276356192,
|
| 1147 |
+
"grad_norm": 0.3671875,
|
| 1148 |
+
"learning_rate": 0.00022765680466802467,
|
| 1149 |
+
"loss": 0.6298,
|
| 1150 |
+
"step": 652
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 0.6714431934493347,
|
| 1154 |
+
"grad_norm": 0.380859375,
|
| 1155 |
+
"learning_rate": 0.00022682131237346514,
|
| 1156 |
+
"loss": 0.6143,
|
| 1157 |
+
"step": 656
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.6755373592630501,
|
| 1161 |
+
"grad_norm": 0.326171875,
|
| 1162 |
+
"learning_rate": 0.00022598257677994616,
|
| 1163 |
+
"loss": 0.64,
|
| 1164 |
+
"step": 660
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 0.6796315250767656,
|
| 1168 |
+
"grad_norm": 0.365234375,
|
| 1169 |
+
"learning_rate": 0.00022514063329782702,
|
| 1170 |
+
"loss": 0.6509,
|
| 1171 |
+
"step": 664
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.6837256908904811,
|
| 1175 |
+
"grad_norm": 0.384765625,
|
| 1176 |
+
"learning_rate": 0.0002242955174729001,
|
| 1177 |
+
"loss": 0.6393,
|
| 1178 |
+
"step": 668
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.6878198567041965,
|
| 1182 |
+
"grad_norm": 0.357421875,
|
| 1183 |
+
"learning_rate": 0.00022344726498489009,
|
| 1184 |
+
"loss": 0.6492,
|
| 1185 |
+
"step": 672
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.691914022517912,
|
| 1189 |
+
"grad_norm": 0.384765625,
|
| 1190 |
+
"learning_rate": 0.0002225959116459477,
|
| 1191 |
+
"loss": 0.6519,
|
| 1192 |
+
"step": 676
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 0.6960081883316275,
|
| 1196 |
+
"grad_norm": 0.373046875,
|
| 1197 |
+
"learning_rate": 0.00022174149339913745,
|
| 1198 |
+
"loss": 0.5808,
|
| 1199 |
+
"step": 680
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.7001023541453428,
|
| 1203 |
+
"grad_norm": 0.341796875,
|
| 1204 |
+
"learning_rate": 0.0002208840463169207,
|
| 1205 |
+
"loss": 0.6531,
|
| 1206 |
+
"step": 684
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 0.7041965199590583,
|
| 1210 |
+
"grad_norm": 0.37109375,
|
| 1211 |
+
"learning_rate": 0.0002200236065996322,
|
| 1212 |
+
"loss": 0.677,
|
| 1213 |
+
"step": 688
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.7082906857727738,
|
| 1217 |
+
"grad_norm": 0.34765625,
|
| 1218 |
+
"learning_rate": 0.0002191602105739521,
|
| 1219 |
+
"loss": 0.5903,
|
| 1220 |
+
"step": 692
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 0.7123848515864892,
|
| 1224 |
+
"grad_norm": 0.40625,
|
| 1225 |
+
"learning_rate": 0.00021829389469137206,
|
| 1226 |
+
"loss": 0.6429,
|
| 1227 |
+
"step": 696
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.7164790174002047,
|
| 1231 |
+
"grad_norm": 0.34375,
|
| 1232 |
+
"learning_rate": 0.0002174246955266565,
|
| 1233 |
+
"loss": 0.6316,
|
| 1234 |
+
"step": 700
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 0.7205731832139202,
|
| 1238 |
+
"grad_norm": 0.3671875,
|
| 1239 |
+
"learning_rate": 0.00021655264977629842,
|
| 1240 |
+
"loss": 0.6191,
|
| 1241 |
+
"step": 704
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.7246673490276356,
|
| 1245 |
+
"grad_norm": 0.3828125,
|
| 1246 |
+
"learning_rate": 0.00021567779425696993,
|
| 1247 |
+
"loss": 0.5909,
|
| 1248 |
+
"step": 708
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 0.7287615148413511,
|
| 1252 |
+
"grad_norm": 0.353515625,
|
| 1253 |
+
"learning_rate": 0.00021480016590396807,
|
| 1254 |
+
"loss": 0.5745,
|
| 1255 |
+
"step": 712
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.7328556806550666,
|
| 1259 |
+
"grad_norm": 0.359375,
|
| 1260 |
+
"learning_rate": 0.0002139198017696556,
|
| 1261 |
+
"loss": 0.627,
|
| 1262 |
+
"step": 716
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 0.736949846468782,
|
| 1266 |
+
"grad_norm": 0.375,
|
| 1267 |
+
"learning_rate": 0.00021303673902189636,
|
| 1268 |
+
"loss": 0.5907,
|
| 1269 |
+
"step": 720
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.7410440122824974,
|
| 1273 |
+
"grad_norm": 0.34375,
|
| 1274 |
+
"learning_rate": 0.00021215101494248618,
|
| 1275 |
+
"loss": 0.6565,
|
| 1276 |
+
"step": 724
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 0.7451381780962129,
|
| 1280 |
+
"grad_norm": 0.37890625,
|
| 1281 |
+
"learning_rate": 0.00021126266692557917,
|
| 1282 |
+
"loss": 0.6313,
|
| 1283 |
+
"step": 728
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.7492323439099283,
|
| 1287 |
+
"grad_norm": 0.337890625,
|
| 1288 |
+
"learning_rate": 0.00021037173247610863,
|
| 1289 |
+
"loss": 0.6126,
|
| 1290 |
+
"step": 732
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 0.7533265097236438,
|
| 1294 |
+
"grad_norm": 0.34765625,
|
| 1295 |
+
"learning_rate": 0.00020947824920820383,
|
| 1296 |
+
"loss": 0.6302,
|
| 1297 |
+
"step": 736
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.7574206755373593,
|
| 1301 |
+
"grad_norm": 0.3828125,
|
| 1302 |
+
"learning_rate": 0.00020858225484360186,
|
| 1303 |
+
"loss": 0.6709,
|
| 1304 |
+
"step": 740
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 0.7615148413510747,
|
| 1308 |
+
"grad_norm": 0.36328125,
|
| 1309 |
+
"learning_rate": 0.00020768378721005526,
|
| 1310 |
+
"loss": 0.6173,
|
| 1311 |
+
"step": 744
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.7656090071647902,
|
| 1315 |
+
"grad_norm": 0.357421875,
|
| 1316 |
+
"learning_rate": 0.00020678288423973476,
|
| 1317 |
+
"loss": 0.5911,
|
| 1318 |
+
"step": 748
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 0.7697031729785057,
|
| 1322 |
+
"grad_norm": 0.396484375,
|
| 1323 |
+
"learning_rate": 0.00020587958396762815,
|
| 1324 |
+
"loss": 0.6153,
|
| 1325 |
+
"step": 752
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 0.7737973387922211,
|
| 1329 |
+
"grad_norm": 0.375,
|
| 1330 |
+
"learning_rate": 0.00020497392452993395,
|
| 1331 |
+
"loss": 0.5763,
|
| 1332 |
+
"step": 756
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 0.7778915046059366,
|
| 1336 |
+
"grad_norm": 0.34375,
|
| 1337 |
+
"learning_rate": 0.0002040659441624519,
|
| 1338 |
+
"loss": 0.5981,
|
| 1339 |
+
"step": 760
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 0.781985670419652,
|
| 1343 |
+
"grad_norm": 0.35546875,
|
| 1344 |
+
"learning_rate": 0.00020315568119896846,
|
| 1345 |
+
"loss": 0.6124,
|
| 1346 |
+
"step": 764
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 0.7860798362333674,
|
| 1350 |
+
"grad_norm": 0.35546875,
|
| 1351 |
+
"learning_rate": 0.00020224317406963835,
|
| 1352 |
+
"loss": 0.6245,
|
| 1353 |
+
"step": 768
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 0.7901740020470829,
|
| 1357 |
+
"grad_norm": 0.361328125,
|
| 1358 |
+
"learning_rate": 0.00020132846129936223,
|
| 1359 |
+
"loss": 0.6093,
|
| 1360 |
+
"step": 772
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 0.7942681678607983,
|
| 1364 |
+
"grad_norm": 0.359375,
|
| 1365 |
+
"learning_rate": 0.00020041158150615996,
|
| 1366 |
+
"loss": 0.6212,
|
| 1367 |
+
"step": 776
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 0.7983623336745138,
|
| 1371 |
+
"grad_norm": 0.376953125,
|
| 1372 |
+
"learning_rate": 0.00019949257339954056,
|
| 1373 |
+
"loss": 0.6338,
|
| 1374 |
+
"step": 780
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 0.8024564994882293,
|
| 1378 |
+
"grad_norm": 0.33203125,
|
| 1379 |
+
"learning_rate": 0.0001985714757788677,
|
| 1380 |
+
"loss": 0.6196,
|
| 1381 |
+
"step": 784
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 0.8065506653019447,
|
| 1385 |
+
"grad_norm": 0.337890625,
|
| 1386 |
+
"learning_rate": 0.00019764832753172172,
|
| 1387 |
+
"loss": 0.5654,
|
| 1388 |
+
"step": 788
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 0.8106448311156602,
|
| 1392 |
+
"grad_norm": 0.47265625,
|
| 1393 |
+
"learning_rate": 0.00019672316763225773,
|
| 1394 |
+
"loss": 0.5876,
|
| 1395 |
+
"step": 792
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 0.8147389969293757,
|
| 1399 |
+
"grad_norm": 0.369140625,
|
| 1400 |
+
"learning_rate": 0.0001957960351395604,
|
| 1401 |
+
"loss": 0.5951,
|
| 1402 |
+
"step": 796
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 0.8188331627430911,
|
| 1406 |
+
"grad_norm": 0.361328125,
|
| 1407 |
+
"learning_rate": 0.0001948669691959947,
|
| 1408 |
+
"loss": 0.5991,
|
| 1409 |
+
"step": 800
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 0.8229273285568065,
|
| 1413 |
+
"grad_norm": 0.353515625,
|
| 1414 |
+
"learning_rate": 0.0001939360090255535,
|
| 1415 |
+
"loss": 0.6002,
|
| 1416 |
+
"step": 804
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 0.827021494370522,
|
| 1420 |
+
"grad_norm": 0.357421875,
|
| 1421 |
+
"learning_rate": 0.00019300319393220146,
|
| 1422 |
+
"loss": 0.5882,
|
| 1423 |
+
"step": 808
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 0.8311156601842374,
|
| 1427 |
+
"grad_norm": 0.365234375,
|
| 1428 |
+
"learning_rate": 0.00019206856329821595,
|
| 1429 |
+
"loss": 0.6324,
|
| 1430 |
+
"step": 812
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 0.8352098259979529,
|
| 1434 |
+
"grad_norm": 0.353515625,
|
| 1435 |
+
"learning_rate": 0.00019113215658252394,
|
| 1436 |
+
"loss": 0.608,
|
| 1437 |
+
"step": 816
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 0.8393039918116684,
|
| 1441 |
+
"grad_norm": 0.37890625,
|
| 1442 |
+
"learning_rate": 0.0001901940133190365,
|
| 1443 |
+
"loss": 0.659,
|
| 1444 |
+
"step": 820
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 0.8433981576253838,
|
| 1448 |
+
"grad_norm": 0.34765625,
|
| 1449 |
+
"learning_rate": 0.00018925417311497944,
|
| 1450 |
+
"loss": 0.641,
|
| 1451 |
+
"step": 824
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 0.8474923234390993,
|
| 1455 |
+
"grad_norm": 0.33984375,
|
| 1456 |
+
"learning_rate": 0.00018831267564922135,
|
| 1457 |
+
"loss": 0.6171,
|
| 1458 |
+
"step": 828
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 0.8515864892528148,
|
| 1462 |
+
"grad_norm": 0.326171875,
|
| 1463 |
+
"learning_rate": 0.00018736956067059827,
|
| 1464 |
+
"loss": 0.6022,
|
| 1465 |
+
"step": 832
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 0.8556806550665302,
|
| 1469 |
+
"grad_norm": 0.34765625,
|
| 1470 |
+
"learning_rate": 0.00018642486799623563,
|
| 1471 |
+
"loss": 0.6303,
|
| 1472 |
+
"step": 836
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 0.8597748208802457,
|
| 1476 |
+
"grad_norm": 0.3515625,
|
| 1477 |
+
"learning_rate": 0.00018547863750986715,
|
| 1478 |
+
"loss": 0.6694,
|
| 1479 |
+
"step": 840
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 0.8638689866939611,
|
| 1483 |
+
"grad_norm": 0.3125,
|
| 1484 |
+
"learning_rate": 0.000184530909160151,
|
| 1485 |
+
"loss": 0.5785,
|
| 1486 |
+
"step": 844
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 0.8679631525076765,
|
| 1490 |
+
"grad_norm": 0.373046875,
|
| 1491 |
+
"learning_rate": 0.0001835817229589834,
|
| 1492 |
+
"loss": 0.6293,
|
| 1493 |
+
"step": 848
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 0.872057318321392,
|
| 1497 |
+
"grad_norm": 0.349609375,
|
| 1498 |
+
"learning_rate": 0.00018263111897980907,
|
| 1499 |
+
"loss": 0.6031,
|
| 1500 |
+
"step": 852
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 0.8761514841351075,
|
| 1504 |
+
"grad_norm": 0.326171875,
|
| 1505 |
+
"learning_rate": 0.00018167913735592955,
|
| 1506 |
+
"loss": 0.5936,
|
| 1507 |
+
"step": 856
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 0.8802456499488229,
|
| 1511 |
+
"grad_norm": 0.375,
|
| 1512 |
+
"learning_rate": 0.00018072581827880885,
|
| 1513 |
+
"loss": 0.6135,
|
| 1514 |
+
"step": 860
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 0.8843398157625384,
|
| 1518 |
+
"grad_norm": 0.349609375,
|
| 1519 |
+
"learning_rate": 0.0001797712019963766,
|
| 1520 |
+
"loss": 0.5845,
|
| 1521 |
+
"step": 864
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 0.8884339815762539,
|
| 1525 |
+
"grad_norm": 0.349609375,
|
| 1526 |
+
"learning_rate": 0.00017881532881132878,
|
| 1527 |
+
"loss": 0.5956,
|
| 1528 |
+
"step": 868
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 0.8925281473899693,
|
| 1532 |
+
"grad_norm": 0.373046875,
|
| 1533 |
+
"learning_rate": 0.00017785823907942602,
|
| 1534 |
+
"loss": 0.6384,
|
| 1535 |
+
"step": 872
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 0.8966223132036848,
|
| 1539 |
+
"grad_norm": 0.3671875,
|
| 1540 |
+
"learning_rate": 0.00017689997320779037,
|
| 1541 |
+
"loss": 0.6084,
|
| 1542 |
+
"step": 876
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 0.9007164790174002,
|
| 1546 |
+
"grad_norm": 0.390625,
|
| 1547 |
+
"learning_rate": 0.00017594057165319876,
|
| 1548 |
+
"loss": 0.6023,
|
| 1549 |
+
"step": 880
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 0.9048106448311156,
|
| 1553 |
+
"grad_norm": 0.365234375,
|
| 1554 |
+
"learning_rate": 0.00017498007492037536,
|
| 1555 |
+
"loss": 0.6271,
|
| 1556 |
+
"step": 884
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 0.9089048106448311,
|
| 1560 |
+
"grad_norm": 0.3515625,
|
| 1561 |
+
"learning_rate": 0.00017401852356028124,
|
| 1562 |
+
"loss": 0.6071,
|
| 1563 |
+
"step": 888
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 0.9129989764585466,
|
| 1567 |
+
"grad_norm": 0.341796875,
|
| 1568 |
+
"learning_rate": 0.00017305595816840267,
|
| 1569 |
+
"loss": 0.5881,
|
| 1570 |
+
"step": 892
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 0.917093142272262,
|
| 1574 |
+
"grad_norm": 0.359375,
|
| 1575 |
+
"learning_rate": 0.00017209241938303697,
|
| 1576 |
+
"loss": 0.6022,
|
| 1577 |
+
"step": 896
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 0.9211873080859775,
|
| 1581 |
+
"grad_norm": 0.3671875,
|
| 1582 |
+
"learning_rate": 0.00017112794788357686,
|
| 1583 |
+
"loss": 0.5948,
|
| 1584 |
+
"step": 900
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 0.925281473899693,
|
| 1588 |
+
"grad_norm": 0.345703125,
|
| 1589 |
+
"learning_rate": 0.00017016258438879323,
|
| 1590 |
+
"loss": 0.5529,
|
| 1591 |
+
"step": 904
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 0.9293756397134084,
|
| 1595 |
+
"grad_norm": 0.33984375,
|
| 1596 |
+
"learning_rate": 0.00016919636965511572,
|
| 1597 |
+
"loss": 0.61,
|
| 1598 |
+
"step": 908
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 0.9334698055271239,
|
| 1602 |
+
"grad_norm": 0.345703125,
|
| 1603 |
+
"learning_rate": 0.00016822934447491232,
|
| 1604 |
+
"loss": 0.6209,
|
| 1605 |
+
"step": 912
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 0.9375639713408394,
|
| 1609 |
+
"grad_norm": 0.396484375,
|
| 1610 |
+
"learning_rate": 0.000167261549674767,
|
| 1611 |
+
"loss": 0.5949,
|
| 1612 |
+
"step": 916
|
| 1613 |
+
},
|
| 1614 |
+
{
|
| 1615 |
+
"epoch": 0.9416581371545547,
|
| 1616 |
+
"grad_norm": 0.3359375,
|
| 1617 |
+
"learning_rate": 0.0001662930261137561,
|
| 1618 |
+
"loss": 0.5936,
|
| 1619 |
+
"step": 920
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 0.9457523029682702,
|
| 1623 |
+
"grad_norm": 0.365234375,
|
| 1624 |
+
"learning_rate": 0.0001653238146817233,
|
| 1625 |
+
"loss": 0.6019,
|
| 1626 |
+
"step": 924
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 0.9498464687819856,
|
| 1630 |
+
"grad_norm": 0.326171875,
|
| 1631 |
+
"learning_rate": 0.00016435395629755346,
|
| 1632 |
+
"loss": 0.5651,
|
| 1633 |
+
"step": 928
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 0.9539406345957011,
|
| 1637 |
+
"grad_norm": 0.34765625,
|
| 1638 |
+
"learning_rate": 0.00016338349190744486,
|
| 1639 |
+
"loss": 0.6279,
|
| 1640 |
+
"step": 932
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 0.9580348004094166,
|
| 1644 |
+
"grad_norm": 0.365234375,
|
| 1645 |
+
"learning_rate": 0.0001624124624831805,
|
| 1646 |
+
"loss": 0.599,
|
| 1647 |
+
"step": 936
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 0.962128966223132,
|
| 1651 |
+
"grad_norm": 0.3671875,
|
| 1652 |
+
"learning_rate": 0.00016144090902039856,
|
| 1653 |
+
"loss": 0.593,
|
| 1654 |
+
"step": 940
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"epoch": 0.9662231320368475,
|
| 1658 |
+
"grad_norm": 0.32421875,
|
| 1659 |
+
"learning_rate": 0.00016046887253686135,
|
| 1660 |
+
"loss": 0.5827,
|
| 1661 |
+
"step": 944
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 0.970317297850563,
|
| 1665 |
+
"grad_norm": 0.333984375,
|
| 1666 |
+
"learning_rate": 0.00015949639407072383,
|
| 1667 |
+
"loss": 0.6371,
|
| 1668 |
+
"step": 948
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 0.9744114636642784,
|
| 1672 |
+
"grad_norm": 0.37109375,
|
| 1673 |
+
"learning_rate": 0.00015852351467880076,
|
| 1674 |
+
"loss": 0.5856,
|
| 1675 |
+
"step": 952
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 0.9785056294779939,
|
| 1679 |
+
"grad_norm": 0.359375,
|
| 1680 |
+
"learning_rate": 0.00015755027543483353,
|
| 1681 |
+
"loss": 0.6166,
|
| 1682 |
+
"step": 956
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 0.9825997952917093,
|
| 1686 |
+
"grad_norm": 0.349609375,
|
| 1687 |
+
"learning_rate": 0.00015657671742775613,
|
| 1688 |
+
"loss": 0.5667,
|
| 1689 |
+
"step": 960
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 0.9866939611054247,
|
| 1693 |
+
"grad_norm": 0.345703125,
|
| 1694 |
+
"learning_rate": 0.00015560288175996023,
|
| 1695 |
+
"loss": 0.5446,
|
| 1696 |
+
"step": 964
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 0.9907881269191402,
|
| 1700 |
+
"grad_norm": 0.380859375,
|
| 1701 |
+
"learning_rate": 0.00015462880954555998,
|
| 1702 |
+
"loss": 0.6376,
|
| 1703 |
+
"step": 968
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 0.9948822927328557,
|
| 1707 |
+
"grad_norm": 0.3515625,
|
| 1708 |
+
"learning_rate": 0.0001536545419086563,
|
| 1709 |
+
"loss": 0.6071,
|
| 1710 |
+
"step": 972
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"epoch": 0.9989764585465711,
|
| 1714 |
+
"grad_norm": 0.376953125,
|
| 1715 |
+
"learning_rate": 0.00015268011998160048,
|
| 1716 |
+
"loss": 0.6143,
|
| 1717 |
+
"step": 976
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 1.0030706243602865,
|
| 1721 |
+
"grad_norm": 0.302734375,
|
| 1722 |
+
"learning_rate": 0.00015170558490325793,
|
| 1723 |
+
"loss": 0.5123,
|
| 1724 |
+
"step": 980
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 1.007164790174002,
|
| 1728 |
+
"grad_norm": 0.337890625,
|
| 1729 |
+
"learning_rate": 0.000150730977817271,
|
| 1730 |
+
"loss": 0.5264,
|
| 1731 |
+
"step": 984
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 1.0112589559877174,
|
| 1735 |
+
"grad_norm": 0.34375,
|
| 1736 |
+
"learning_rate": 0.00014975633987032212,
|
| 1737 |
+
"loss": 0.4917,
|
| 1738 |
+
"step": 988
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 1.015353121801433,
|
| 1742 |
+
"grad_norm": 0.34375,
|
| 1743 |
+
"learning_rate": 0.00014878171221039676,
|
| 1744 |
+
"loss": 0.5258,
|
| 1745 |
+
"step": 992
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 1.0194472876151484,
|
| 1749 |
+
"grad_norm": 0.353515625,
|
| 1750 |
+
"learning_rate": 0.000147807135985046,
|
| 1751 |
+
"loss": 0.4466,
|
| 1752 |
+
"step": 996
|
| 1753 |
+
},
|
| 1754 |
+
{
|
| 1755 |
+
"epoch": 1.0235414534288638,
|
| 1756 |
+
"grad_norm": 0.3671875,
|
| 1757 |
+
"learning_rate": 0.00014683265233964937,
|
| 1758 |
+
"loss": 0.5049,
|
| 1759 |
+
"step": 1000
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 1.0276356192425793,
|
| 1763 |
+
"grad_norm": 0.345703125,
|
| 1764 |
+
"learning_rate": 0.00014585830241567785,
|
| 1765 |
+
"loss": 0.469,
|
| 1766 |
+
"step": 1004
|
| 1767 |
+
},
|
| 1768 |
+
{
|
| 1769 |
+
"epoch": 1.0317297850562948,
|
| 1770 |
+
"grad_norm": 0.337890625,
|
| 1771 |
+
"learning_rate": 0.00014488412734895692,
|
| 1772 |
+
"loss": 0.4901,
|
| 1773 |
+
"step": 1008
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 1.0358239508700102,
|
| 1777 |
+
"grad_norm": 0.34375,
|
| 1778 |
+
"learning_rate": 0.00014391016826792972,
|
| 1779 |
+
"loss": 0.5008,
|
| 1780 |
+
"step": 1012
|
| 1781 |
+
},
|
| 1782 |
+
{
|
| 1783 |
+
"epoch": 1.0399181166837257,
|
| 1784 |
+
"grad_norm": 0.35546875,
|
| 1785 |
+
"learning_rate": 0.0001429364662919208,
|
| 1786 |
+
"loss": 0.5037,
|
| 1787 |
+
"step": 1016
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 1.0440122824974412,
|
| 1791 |
+
"grad_norm": 0.32421875,
|
| 1792 |
+
"learning_rate": 0.00014196306252939998,
|
| 1793 |
+
"loss": 0.5418,
|
| 1794 |
+
"step": 1020
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 1.0481064483111566,
|
| 1798 |
+
"grad_norm": 0.373046875,
|
| 1799 |
+
"learning_rate": 0.00014098999807624695,
|
| 1800 |
+
"loss": 0.5068,
|
| 1801 |
+
"step": 1024
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 1.052200614124872,
|
| 1805 |
+
"grad_norm": 0.369140625,
|
| 1806 |
+
"learning_rate": 0.00014001731401401622,
|
| 1807 |
+
"loss": 0.523,
|
| 1808 |
+
"step": 1028
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 1.0562947799385876,
|
| 1812 |
+
"grad_norm": 0.34765625,
|
| 1813 |
+
"learning_rate": 0.00013904505140820264,
|
| 1814 |
+
"loss": 0.486,
|
| 1815 |
+
"step": 1032
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 1.060388945752303,
|
| 1819 |
+
"grad_norm": 0.322265625,
|
| 1820 |
+
"learning_rate": 0.00013807325130650764,
|
| 1821 |
+
"loss": 0.4964,
|
| 1822 |
+
"step": 1036
|
| 1823 |
+
},
|
| 1824 |
+
{
|
| 1825 |
+
"epoch": 1.0644831115660185,
|
| 1826 |
+
"grad_norm": 0.349609375,
|
| 1827 |
+
"learning_rate": 0.00013710195473710636,
|
| 1828 |
+
"loss": 0.4921,
|
| 1829 |
+
"step": 1040
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 1.068577277379734,
|
| 1833 |
+
"grad_norm": 0.36328125,
|
| 1834 |
+
"learning_rate": 0.00013613120270691552,
|
| 1835 |
+
"loss": 0.5132,
|
| 1836 |
+
"step": 1044
|
| 1837 |
+
},
|
| 1838 |
+
{
|
| 1839 |
+
"epoch": 1.0726714431934494,
|
| 1840 |
+
"grad_norm": 0.349609375,
|
| 1841 |
+
"learning_rate": 0.00013516103619986192,
|
| 1842 |
+
"loss": 0.5205,
|
| 1843 |
+
"step": 1048
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 1.076765609007165,
|
| 1847 |
+
"grad_norm": 0.341796875,
|
| 1848 |
+
"learning_rate": 0.00013419149617515243,
|
| 1849 |
+
"loss": 0.5278,
|
| 1850 |
+
"step": 1052
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 1.0808597748208801,
|
| 1854 |
+
"grad_norm": 0.3515625,
|
| 1855 |
+
"learning_rate": 0.00013322262356554456,
|
| 1856 |
+
"loss": 0.4682,
|
| 1857 |
+
"step": 1056
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 1.0849539406345956,
|
| 1861 |
+
"grad_norm": 0.35546875,
|
| 1862 |
+
"learning_rate": 0.0001322544592756185,
|
| 1863 |
+
"loss": 0.5016,
|
| 1864 |
+
"step": 1060
|
| 1865 |
+
},
|
| 1866 |
+
{
|
| 1867 |
+
"epoch": 1.089048106448311,
|
| 1868 |
+
"grad_norm": 0.333984375,
|
| 1869 |
+
"learning_rate": 0.00013128704418004995,
|
| 1870 |
+
"loss": 0.5081,
|
| 1871 |
+
"step": 1064
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 1.0931422722620265,
|
| 1875 |
+
"grad_norm": 0.33203125,
|
| 1876 |
+
"learning_rate": 0.00013032041912188467,
|
| 1877 |
+
"loss": 0.5117,
|
| 1878 |
+
"step": 1068
|
| 1879 |
+
},
|
| 1880 |
+
{
|
| 1881 |
+
"epoch": 1.097236438075742,
|
| 1882 |
+
"grad_norm": 0.3359375,
|
| 1883 |
+
"learning_rate": 0.00012935462491081391,
|
| 1884 |
+
"loss": 0.4805,
|
| 1885 |
+
"step": 1072
|
| 1886 |
+
},
|
| 1887 |
+
{
|
| 1888 |
+
"epoch": 1.1013306038894575,
|
| 1889 |
+
"grad_norm": 0.369140625,
|
| 1890 |
+
"learning_rate": 0.00012838970232145172,
|
| 1891 |
+
"loss": 0.5378,
|
| 1892 |
+
"step": 1076
|
| 1893 |
+
},
|
| 1894 |
+
{
|
| 1895 |
+
"epoch": 1.105424769703173,
|
| 1896 |
+
"grad_norm": 0.349609375,
|
| 1897 |
+
"learning_rate": 0.00012742569209161334,
|
| 1898 |
+
"loss": 0.494,
|
| 1899 |
+
"step": 1080
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 1.1095189355168884,
|
| 1903 |
+
"grad_norm": 0.34375,
|
| 1904 |
+
"learning_rate": 0.00012646263492059528,
|
| 1905 |
+
"loss": 0.4742,
|
| 1906 |
+
"step": 1084
|
| 1907 |
+
},
|
| 1908 |
+
{
|
| 1909 |
+
"epoch": 1.1136131013306039,
|
| 1910 |
+
"grad_norm": 0.357421875,
|
| 1911 |
+
"learning_rate": 0.0001255005714674573,
|
| 1912 |
+
"loss": 0.5341,
|
| 1913 |
+
"step": 1088
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 1.1177072671443193,
|
| 1917 |
+
"grad_norm": 0.3515625,
|
| 1918 |
+
"learning_rate": 0.00012453954234930542,
|
| 1919 |
+
"loss": 0.5028,
|
| 1920 |
+
"step": 1092
|
| 1921 |
+
},
|
| 1922 |
+
{
|
| 1923 |
+
"epoch": 1.1218014329580348,
|
| 1924 |
+
"grad_norm": 0.353515625,
|
| 1925 |
+
"learning_rate": 0.00012357958813957748,
|
| 1926 |
+
"loss": 0.4893,
|
| 1927 |
+
"step": 1096
|
| 1928 |
+
},
|
| 1929 |
+
{
|
| 1930 |
+
"epoch": 1.1258955987717503,
|
| 1931 |
+
"grad_norm": 0.33984375,
|
| 1932 |
+
"learning_rate": 0.00012262074936632994,
|
| 1933 |
+
"loss": 0.548,
|
| 1934 |
+
"step": 1100
|
| 1935 |
+
},
|
| 1936 |
+
{
|
| 1937 |
+
"epoch": 1.1299897645854657,
|
| 1938 |
+
"grad_norm": 0.36328125,
|
| 1939 |
+
"learning_rate": 0.00012166306651052708,
|
| 1940 |
+
"loss": 0.4871,
|
| 1941 |
+
"step": 1104
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 1.1340839303991812,
|
| 1945 |
+
"grad_norm": 0.349609375,
|
| 1946 |
+
"learning_rate": 0.00012070658000433166,
|
| 1947 |
+
"loss": 0.4393,
|
| 1948 |
+
"step": 1108
|
| 1949 |
+
},
|
| 1950 |
+
{
|
| 1951 |
+
"epoch": 1.1381780962128967,
|
| 1952 |
+
"grad_norm": 0.353515625,
|
| 1953 |
+
"learning_rate": 0.00011975133022939816,
|
| 1954 |
+
"loss": 0.5077,
|
| 1955 |
+
"step": 1112
|
| 1956 |
+
},
|
| 1957 |
+
{
|
| 1958 |
+
"epoch": 1.1422722620266121,
|
| 1959 |
+
"grad_norm": 0.369140625,
|
| 1960 |
+
"learning_rate": 0.0001187973575151677,
|
| 1961 |
+
"loss": 0.5037,
|
| 1962 |
+
"step": 1116
|
| 1963 |
+
},
|
| 1964 |
+
{
|
| 1965 |
+
"epoch": 1.1463664278403276,
|
| 1966 |
+
"grad_norm": 0.341796875,
|
| 1967 |
+
"learning_rate": 0.00011784470213716574,
|
| 1968 |
+
"loss": 0.4682,
|
| 1969 |
+
"step": 1120
|
| 1970 |
+
},
|
| 1971 |
+
{
|
| 1972 |
+
"epoch": 1.150460593654043,
|
| 1973 |
+
"grad_norm": 0.373046875,
|
| 1974 |
+
"learning_rate": 0.00011689340431530123,
|
| 1975 |
+
"loss": 0.5539,
|
| 1976 |
+
"step": 1124
|
| 1977 |
+
},
|
| 1978 |
+
{
|
| 1979 |
+
"epoch": 1.1545547594677585,
|
| 1980 |
+
"grad_norm": 0.33984375,
|
| 1981 |
+
"learning_rate": 0.00011594350421216891,
|
| 1982 |
+
"loss": 0.4853,
|
| 1983 |
+
"step": 1128
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 1.158648925281474,
|
| 1987 |
+
"grad_norm": 0.36328125,
|
| 1988 |
+
"learning_rate": 0.00011499504193135363,
|
| 1989 |
+
"loss": 0.5045,
|
| 1990 |
+
"step": 1132
|
| 1991 |
+
},
|
| 1992 |
+
{
|
| 1993 |
+
"epoch": 1.1627430910951895,
|
| 1994 |
+
"grad_norm": 0.388671875,
|
| 1995 |
+
"learning_rate": 0.00011404805751573712,
|
| 1996 |
+
"loss": 0.4964,
|
| 1997 |
+
"step": 1136
|
| 1998 |
+
},
|
| 1999 |
+
{
|
| 2000 |
+
"epoch": 1.1668372569089047,
|
| 2001 |
+
"grad_norm": 0.37109375,
|
| 2002 |
+
"learning_rate": 0.00011310259094580754,
|
| 2003 |
+
"loss": 0.4819,
|
| 2004 |
+
"step": 1140
|
| 2005 |
+
},
|
| 2006 |
+
{
|
| 2007 |
+
"epoch": 1.1709314227226202,
|
| 2008 |
+
"grad_norm": 0.3359375,
|
| 2009 |
+
"learning_rate": 0.00011215868213797156,
|
| 2010 |
+
"loss": 0.4805,
|
| 2011 |
+
"step": 1144
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 1.1750255885363357,
|
| 2015 |
+
"grad_norm": 0.361328125,
|
| 2016 |
+
"learning_rate": 0.00011121637094286903,
|
| 2017 |
+
"loss": 0.4872,
|
| 2018 |
+
"step": 1148
|
| 2019 |
+
},
|
| 2020 |
+
{
|
| 2021 |
+
"epoch": 1.1791197543500511,
|
| 2022 |
+
"grad_norm": 0.359375,
|
| 2023 |
+
"learning_rate": 0.00011027569714369059,
|
| 2024 |
+
"loss": 0.4955,
|
| 2025 |
+
"step": 1152
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 1.1832139201637666,
|
| 2029 |
+
"grad_norm": 0.384765625,
|
| 2030 |
+
"learning_rate": 0.00010933670045449822,
|
| 2031 |
+
"loss": 0.4939,
|
| 2032 |
+
"step": 1156
|
| 2033 |
+
},
|
| 2034 |
+
{
|
| 2035 |
+
"epoch": 1.187308085977482,
|
| 2036 |
+
"grad_norm": 0.345703125,
|
| 2037 |
+
"learning_rate": 0.00010839942051854829,
|
| 2038 |
+
"loss": 0.5074,
|
| 2039 |
+
"step": 1160
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 1.1914022517911975,
|
| 2043 |
+
"grad_norm": 0.384765625,
|
| 2044 |
+
"learning_rate": 0.00010746389690661808,
|
| 2045 |
+
"loss": 0.5396,
|
| 2046 |
+
"step": 1164
|
| 2047 |
+
},
|
| 2048 |
+
{
|
| 2049 |
+
"epoch": 1.195496417604913,
|
| 2050 |
+
"grad_norm": 0.369140625,
|
| 2051 |
+
"learning_rate": 0.000106530169115335,
|
| 2052 |
+
"loss": 0.5302,
|
| 2053 |
+
"step": 1168
|
| 2054 |
+
},
|
| 2055 |
+
{
|
| 2056 |
+
"epoch": 1.1995905834186285,
|
| 2057 |
+
"grad_norm": 0.376953125,
|
| 2058 |
+
"learning_rate": 0.00010559827656550933,
|
| 2059 |
+
"loss": 0.5012,
|
| 2060 |
+
"step": 1172
|
| 2061 |
+
},
|
| 2062 |
+
{
|
| 2063 |
+
"epoch": 1.203684749232344,
|
| 2064 |
+
"grad_norm": 0.357421875,
|
| 2065 |
+
"learning_rate": 0.00010466825860046967,
|
| 2066 |
+
"loss": 0.5324,
|
| 2067 |
+
"step": 1176
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 1.2077789150460594,
|
| 2071 |
+
"grad_norm": 0.32421875,
|
| 2072 |
+
"learning_rate": 0.00010374015448440203,
|
| 2073 |
+
"loss": 0.498,
|
| 2074 |
+
"step": 1180
|
| 2075 |
+
},
|
| 2076 |
+
{
|
| 2077 |
+
"epoch": 1.2118730808597749,
|
| 2078 |
+
"grad_norm": 0.365234375,
|
| 2079 |
+
"learning_rate": 0.00010281400340069205,
|
| 2080 |
+
"loss": 0.4906,
|
| 2081 |
+
"step": 1184
|
| 2082 |
+
},
|
| 2083 |
+
{
|
| 2084 |
+
"epoch": 1.2159672466734903,
|
| 2085 |
+
"grad_norm": 0.357421875,
|
| 2086 |
+
"learning_rate": 0.00010188984445027097,
|
| 2087 |
+
"loss": 0.4885,
|
| 2088 |
+
"step": 1188
|
| 2089 |
+
},
|
| 2090 |
+
{
|
| 2091 |
+
"epoch": 1.2200614124872058,
|
| 2092 |
+
"grad_norm": 0.376953125,
|
| 2093 |
+
"learning_rate": 0.00010096771664996456,
|
| 2094 |
+
"loss": 0.5133,
|
| 2095 |
+
"step": 1192
|
| 2096 |
+
},
|
| 2097 |
+
{
|
| 2098 |
+
"epoch": 1.2241555783009213,
|
| 2099 |
+
"grad_norm": 0.349609375,
|
| 2100 |
+
"learning_rate": 0.00010004765893084603,
|
| 2101 |
+
"loss": 0.4521,
|
| 2102 |
+
"step": 1196
|
| 2103 |
+
},
|
| 2104 |
+
{
|
| 2105 |
+
"epoch": 1.2282497441146367,
|
| 2106 |
+
"grad_norm": 0.37109375,
|
| 2107 |
+
"learning_rate": 9.912971013659232e-05,
|
| 2108 |
+
"loss": 0.5168,
|
| 2109 |
+
"step": 1200
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 1.2323439099283522,
|
| 2113 |
+
"grad_norm": 0.498046875,
|
| 2114 |
+
"learning_rate": 9.821390902184426e-05,
|
| 2115 |
+
"loss": 0.4759,
|
| 2116 |
+
"step": 1204
|
| 2117 |
+
},
|
| 2118 |
+
{
|
| 2119 |
+
"epoch": 1.2364380757420674,
|
| 2120 |
+
"grad_norm": 0.36328125,
|
| 2121 |
+
"learning_rate": 9.730029425057045e-05,
|
| 2122 |
+
"loss": 0.5194,
|
| 2123 |
+
"step": 1208
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 1.240532241555783,
|
| 2127 |
+
"grad_norm": 0.376953125,
|
| 2128 |
+
"learning_rate": 9.638890439443464e-05,
|
| 2129 |
+
"loss": 0.4903,
|
| 2130 |
+
"step": 1212
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 1.2446264073694984,
|
| 2134 |
+
"grad_norm": 0.33984375,
|
| 2135 |
+
"learning_rate": 9.547977793116762e-05,
|
| 2136 |
+
"loss": 0.5149,
|
| 2137 |
+
"step": 1216
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 1.2487205731832138,
|
| 2141 |
+
"grad_norm": 0.3359375,
|
| 2142 |
+
"learning_rate": 9.457295324294247e-05,
|
| 2143 |
+
"loss": 0.4665,
|
| 2144 |
+
"step": 1220
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 1.2528147389969293,
|
| 2148 |
+
"grad_norm": 0.408203125,
|
| 2149 |
+
"learning_rate": 9.366846861475435e-05,
|
| 2150 |
+
"loss": 0.4834,
|
| 2151 |
+
"step": 1224
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 1.2569089048106448,
|
| 2155 |
+
"grad_norm": 0.34375,
|
| 2156 |
+
"learning_rate": 9.276636223280396e-05,
|
| 2157 |
+
"loss": 0.5027,
|
| 2158 |
+
"step": 1228
|
| 2159 |
+
},
|
| 2160 |
+
{
|
| 2161 |
+
"epoch": 1.2610030706243602,
|
| 2162 |
+
"grad_norm": 0.36328125,
|
| 2163 |
+
"learning_rate": 9.186667218288549e-05,
|
| 2164 |
+
"loss": 0.5093,
|
| 2165 |
+
"step": 1232
|
| 2166 |
+
},
|
| 2167 |
+
{
|
| 2168 |
+
"epoch": 1.2650972364380757,
|
| 2169 |
+
"grad_norm": 0.35546875,
|
| 2170 |
+
"learning_rate": 9.096943644877854e-05,
|
| 2171 |
+
"loss": 0.5105,
|
| 2172 |
+
"step": 1236
|
| 2173 |
+
},
|
| 2174 |
+
{
|
| 2175 |
+
"epoch": 1.2691914022517912,
|
| 2176 |
+
"grad_norm": 0.380859375,
|
| 2177 |
+
"learning_rate": 9.007469291064467e-05,
|
| 2178 |
+
"loss": 0.5212,
|
| 2179 |
+
"step": 1240
|
| 2180 |
+
},
|
| 2181 |
+
{
|
| 2182 |
+
"epoch": 1.2732855680655066,
|
| 2183 |
+
"grad_norm": 0.353515625,
|
| 2184 |
+
"learning_rate": 8.918247934342806e-05,
|
| 2185 |
+
"loss": 0.5191,
|
| 2186 |
+
"step": 1244
|
| 2187 |
+
},
|
| 2188 |
+
{
|
| 2189 |
+
"epoch": 1.277379733879222,
|
| 2190 |
+
"grad_norm": 0.365234375,
|
| 2191 |
+
"learning_rate": 8.829283341526067e-05,
|
| 2192 |
+
"loss": 0.5019,
|
| 2193 |
+
"step": 1248
|
| 2194 |
+
},
|
| 2195 |
+
{
|
| 2196 |
+
"epoch": 1.2814738996929376,
|
| 2197 |
+
"grad_norm": 0.384765625,
|
| 2198 |
+
"learning_rate": 8.74057926858721e-05,
|
| 2199 |
+
"loss": 0.5162,
|
| 2200 |
+
"step": 1252
|
| 2201 |
+
},
|
| 2202 |
+
{
|
| 2203 |
+
"epoch": 1.285568065506653,
|
| 2204 |
+
"grad_norm": 0.3828125,
|
| 2205 |
+
"learning_rate": 8.652139460500359e-05,
|
| 2206 |
+
"loss": 0.5061,
|
| 2207 |
+
"step": 1256
|
| 2208 |
+
},
|
| 2209 |
+
{
|
| 2210 |
+
"epoch": 1.2896622313203685,
|
| 2211 |
+
"grad_norm": 0.376953125,
|
| 2212 |
+
"learning_rate": 8.563967651082713e-05,
|
| 2213 |
+
"loss": 0.5003,
|
| 2214 |
+
"step": 1260
|
| 2215 |
+
},
|
| 2216 |
+
{
|
| 2217 |
+
"epoch": 1.293756397134084,
|
| 2218 |
+
"grad_norm": 0.3671875,
|
| 2219 |
+
"learning_rate": 8.47606756283691e-05,
|
| 2220 |
+
"loss": 0.5196,
|
| 2221 |
+
"step": 1264
|
| 2222 |
+
},
|
| 2223 |
+
{
|
| 2224 |
+
"epoch": 1.2978505629477994,
|
| 2225 |
+
"grad_norm": 0.34765625,
|
| 2226 |
+
"learning_rate": 8.388442906793862e-05,
|
| 2227 |
+
"loss": 0.4932,
|
| 2228 |
+
"step": 1268
|
| 2229 |
+
},
|
| 2230 |
+
{
|
| 2231 |
+
"epoch": 1.301944728761515,
|
| 2232 |
+
"grad_norm": 0.369140625,
|
| 2233 |
+
"learning_rate": 8.301097382356067e-05,
|
| 2234 |
+
"loss": 0.4871,
|
| 2235 |
+
"step": 1272
|
| 2236 |
+
},
|
| 2237 |
+
{
|
| 2238 |
+
"epoch": 1.3060388945752304,
|
| 2239 |
+
"grad_norm": 0.384765625,
|
| 2240 |
+
"learning_rate": 8.214034677141465e-05,
|
| 2241 |
+
"loss": 0.494,
|
| 2242 |
+
"step": 1276
|
| 2243 |
+
},
|
| 2244 |
+
{
|
| 2245 |
+
"epoch": 1.3101330603889458,
|
| 2246 |
+
"grad_norm": 0.357421875,
|
| 2247 |
+
"learning_rate": 8.127258466827704e-05,
|
| 2248 |
+
"loss": 0.5034,
|
| 2249 |
+
"step": 1280
|
| 2250 |
+
},
|
| 2251 |
+
{
|
| 2252 |
+
"epoch": 1.3142272262026613,
|
| 2253 |
+
"grad_norm": 0.365234375,
|
| 2254 |
+
"learning_rate": 8.040772414996984e-05,
|
| 2255 |
+
"loss": 0.5111,
|
| 2256 |
+
"step": 1284
|
| 2257 |
+
},
|
| 2258 |
+
{
|
| 2259 |
+
"epoch": 1.3183213920163768,
|
| 2260 |
+
"grad_norm": 0.32421875,
|
| 2261 |
+
"learning_rate": 7.95458017298138e-05,
|
| 2262 |
+
"loss": 0.5169,
|
| 2263 |
+
"step": 1288
|
| 2264 |
+
},
|
| 2265 |
+
{
|
| 2266 |
+
"epoch": 1.3224155578300922,
|
| 2267 |
+
"grad_norm": 0.37109375,
|
| 2268 |
+
"learning_rate": 7.868685379708686e-05,
|
| 2269 |
+
"loss": 0.4631,
|
| 2270 |
+
"step": 1292
|
| 2271 |
+
},
|
| 2272 |
+
{
|
| 2273 |
+
"epoch": 1.3265097236438077,
|
| 2274 |
+
"grad_norm": 0.341796875,
|
| 2275 |
+
"learning_rate": 7.783091661548789e-05,
|
| 2276 |
+
"loss": 0.4756,
|
| 2277 |
+
"step": 1296
|
| 2278 |
+
},
|
| 2279 |
+
{
|
| 2280 |
+
"epoch": 1.330603889457523,
|
| 2281 |
+
"grad_norm": 0.34765625,
|
| 2282 |
+
"learning_rate": 7.697802632160557e-05,
|
| 2283 |
+
"loss": 0.4705,
|
| 2284 |
+
"step": 1300
|
| 2285 |
+
},
|
| 2286 |
+
{
|
| 2287 |
+
"epoch": 1.3346980552712384,
|
| 2288 |
+
"grad_norm": 0.357421875,
|
| 2289 |
+
"learning_rate": 7.612821892339284e-05,
|
| 2290 |
+
"loss": 0.522,
|
| 2291 |
+
"step": 1304
|
| 2292 |
+
},
|
| 2293 |
+
{
|
| 2294 |
+
"epoch": 1.3387922210849539,
|
| 2295 |
+
"grad_norm": 0.375,
|
| 2296 |
+
"learning_rate": 7.528153029864682e-05,
|
| 2297 |
+
"loss": 0.5192,
|
| 2298 |
+
"step": 1308
|
| 2299 |
+
},
|
| 2300 |
+
{
|
| 2301 |
+
"epoch": 1.3428863868986693,
|
| 2302 |
+
"grad_norm": 0.341796875,
|
| 2303 |
+
"learning_rate": 7.443799619349374e-05,
|
| 2304 |
+
"loss": 0.5183,
|
| 2305 |
+
"step": 1312
|
| 2306 |
+
},
|
| 2307 |
+
{
|
| 2308 |
+
"epoch": 1.3469805527123848,
|
| 2309 |
+
"grad_norm": 0.35546875,
|
| 2310 |
+
"learning_rate": 7.359765222088008e-05,
|
| 2311 |
+
"loss": 0.506,
|
| 2312 |
+
"step": 1316
|
| 2313 |
+
},
|
| 2314 |
+
{
|
| 2315 |
+
"epoch": 1.3510747185261003,
|
| 2316 |
+
"grad_norm": 0.3828125,
|
| 2317 |
+
"learning_rate": 7.276053385906896e-05,
|
| 2318 |
+
"loss": 0.5021,
|
| 2319 |
+
"step": 1320
|
| 2320 |
+
},
|
| 2321 |
+
{
|
| 2322 |
+
"epoch": 1.3551688843398157,
|
| 2323 |
+
"grad_norm": 0.3515625,
|
| 2324 |
+
"learning_rate": 7.192667645014223e-05,
|
| 2325 |
+
"loss": 0.4803,
|
| 2326 |
+
"step": 1324
|
| 2327 |
+
},
|
| 2328 |
+
{
|
| 2329 |
+
"epoch": 1.3592630501535312,
|
| 2330 |
+
"grad_norm": 0.365234375,
|
| 2331 |
+
"learning_rate": 7.109611519850845e-05,
|
| 2332 |
+
"loss": 0.4941,
|
| 2333 |
+
"step": 1328
|
| 2334 |
+
},
|
| 2335 |
+
{
|
| 2336 |
+
"epoch": 1.3633572159672467,
|
| 2337 |
+
"grad_norm": 0.37890625,
|
| 2338 |
+
"learning_rate": 7.026888516941658e-05,
|
| 2339 |
+
"loss": 0.508,
|
| 2340 |
+
"step": 1332
|
| 2341 |
+
},
|
| 2342 |
+
{
|
| 2343 |
+
"epoch": 1.3674513817809621,
|
| 2344 |
+
"grad_norm": 0.36328125,
|
| 2345 |
+
"learning_rate": 6.944502128747558e-05,
|
| 2346 |
+
"loss": 0.5139,
|
| 2347 |
+
"step": 1336
|
| 2348 |
+
},
|
| 2349 |
+
{
|
| 2350 |
+
"epoch": 1.3715455475946776,
|
| 2351 |
+
"grad_norm": 0.36328125,
|
| 2352 |
+
"learning_rate": 6.862455833517979e-05,
|
| 2353 |
+
"loss": 0.4899,
|
| 2354 |
+
"step": 1340
|
| 2355 |
+
},
|
| 2356 |
+
{
|
| 2357 |
+
"epoch": 1.375639713408393,
|
| 2358 |
+
"grad_norm": 0.38671875,
|
| 2359 |
+
"learning_rate": 6.780753095144086e-05,
|
| 2360 |
+
"loss": 0.526,
|
| 2361 |
+
"step": 1344
|
| 2362 |
+
},
|
| 2363 |
+
{
|
| 2364 |
+
"epoch": 1.3797338792221086,
|
| 2365 |
+
"grad_norm": 0.373046875,
|
| 2366 |
+
"learning_rate": 6.699397363012482e-05,
|
| 2367 |
+
"loss": 0.499,
|
| 2368 |
+
"step": 1348
|
| 2369 |
+
},
|
| 2370 |
+
{
|
| 2371 |
+
"epoch": 1.383828045035824,
|
| 2372 |
+
"grad_norm": 0.39453125,
|
| 2373 |
+
"learning_rate": 6.618392071859612e-05,
|
| 2374 |
+
"loss": 0.5155,
|
| 2375 |
+
"step": 1352
|
| 2376 |
+
},
|
| 2377 |
+
{
|
| 2378 |
+
"epoch": 1.3879222108495395,
|
| 2379 |
+
"grad_norm": 0.384765625,
|
| 2380 |
+
"learning_rate": 6.537740641626746e-05,
|
| 2381 |
+
"loss": 0.5165,
|
| 2382 |
+
"step": 1356
|
| 2383 |
+
},
|
| 2384 |
+
{
|
| 2385 |
+
"epoch": 1.3920163766632547,
|
| 2386 |
+
"grad_norm": 0.357421875,
|
| 2387 |
+
"learning_rate": 6.457446477315588e-05,
|
| 2388 |
+
"loss": 0.4815,
|
| 2389 |
+
"step": 1360
|
| 2390 |
+
},
|
| 2391 |
+
{
|
| 2392 |
+
"epoch": 1.3961105424769702,
|
| 2393 |
+
"grad_norm": 0.3671875,
|
| 2394 |
+
"learning_rate": 6.377512968844533e-05,
|
| 2395 |
+
"loss": 0.5091,
|
| 2396 |
+
"step": 1364
|
| 2397 |
+
},
|
| 2398 |
+
{
|
| 2399 |
+
"epoch": 1.4002047082906857,
|
| 2400 |
+
"grad_norm": 0.3515625,
|
| 2401 |
+
"learning_rate": 6.297943490905531e-05,
|
| 2402 |
+
"loss": 0.4868,
|
| 2403 |
+
"step": 1368
|
| 2404 |
+
},
|
| 2405 |
+
{
|
| 2406 |
+
"epoch": 1.4042988741044011,
|
| 2407 |
+
"grad_norm": 0.373046875,
|
| 2408 |
+
"learning_rate": 6.218741402821624e-05,
|
| 2409 |
+
"loss": 0.4928,
|
| 2410 |
+
"step": 1372
|
| 2411 |
+
},
|
| 2412 |
+
{
|
| 2413 |
+
"epoch": 1.4083930399181166,
|
| 2414 |
+
"grad_norm": 0.369140625,
|
| 2415 |
+
"learning_rate": 6.139910048405134e-05,
|
| 2416 |
+
"loss": 0.5173,
|
| 2417 |
+
"step": 1376
|
| 2418 |
+
},
|
| 2419 |
+
{
|
| 2420 |
+
"epoch": 1.412487205731832,
|
| 2421 |
+
"grad_norm": 0.3515625,
|
| 2422 |
+
"learning_rate": 6.061452755816451e-05,
|
| 2423 |
+
"loss": 0.492,
|
| 2424 |
+
"step": 1380
|
| 2425 |
+
},
|
| 2426 |
+
{
|
| 2427 |
+
"epoch": 1.4165813715455475,
|
| 2428 |
+
"grad_norm": 0.357421875,
|
| 2429 |
+
"learning_rate": 5.9833728374235615e-05,
|
| 2430 |
+
"loss": 0.5033,
|
| 2431 |
+
"step": 1384
|
| 2432 |
+
},
|
| 2433 |
+
{
|
| 2434 |
+
"epoch": 1.420675537359263,
|
| 2435 |
+
"grad_norm": 0.33984375,
|
| 2436 |
+
"learning_rate": 5.9056735896621796e-05,
|
| 2437 |
+
"loss": 0.5119,
|
| 2438 |
+
"step": 1388
|
| 2439 |
+
},
|
| 2440 |
+
{
|
| 2441 |
+
"epoch": 1.4247697031729785,
|
| 2442 |
+
"grad_norm": 0.34375,
|
| 2443 |
+
"learning_rate": 5.8283582928965986e-05,
|
| 2444 |
+
"loss": 0.4938,
|
| 2445 |
+
"step": 1392
|
| 2446 |
+
},
|
| 2447 |
+
{
|
| 2448 |
+
"epoch": 1.428863868986694,
|
| 2449 |
+
"grad_norm": 0.36328125,
|
| 2450 |
+
"learning_rate": 5.751430211281165e-05,
|
| 2451 |
+
"loss": 0.4877,
|
| 2452 |
+
"step": 1396
|
| 2453 |
+
},
|
| 2454 |
+
{
|
| 2455 |
+
"epoch": 1.4329580348004094,
|
| 2456 |
+
"grad_norm": 0.359375,
|
| 2457 |
+
"learning_rate": 5.674892592622502e-05,
|
| 2458 |
+
"loss": 0.4866,
|
| 2459 |
+
"step": 1400
|
| 2460 |
+
},
|
| 2461 |
+
{
|
| 2462 |
+
"epoch": 1.4370522006141249,
|
| 2463 |
+
"grad_norm": 0.369140625,
|
| 2464 |
+
"learning_rate": 5.5987486682423865e-05,
|
| 2465 |
+
"loss": 0.4863,
|
| 2466 |
+
"step": 1404
|
| 2467 |
+
},
|
| 2468 |
+
{
|
| 2469 |
+
"epoch": 1.4411463664278403,
|
| 2470 |
+
"grad_norm": 0.361328125,
|
| 2471 |
+
"learning_rate": 5.5230016528413076e-05,
|
| 2472 |
+
"loss": 0.5,
|
| 2473 |
+
"step": 1408
|
| 2474 |
+
},
|
| 2475 |
+
{
|
| 2476 |
+
"epoch": 1.4452405322415558,
|
| 2477 |
+
"grad_norm": 0.357421875,
|
| 2478 |
+
"learning_rate": 5.447654744362761e-05,
|
| 2479 |
+
"loss": 0.4917,
|
| 2480 |
+
"step": 1412
|
| 2481 |
+
},
|
| 2482 |
+
{
|
| 2483 |
+
"epoch": 1.4493346980552713,
|
| 2484 |
+
"grad_norm": 0.34765625,
|
| 2485 |
+
"learning_rate": 5.37271112385823e-05,
|
| 2486 |
+
"loss": 0.4828,
|
| 2487 |
+
"step": 1416
|
| 2488 |
+
},
|
| 2489 |
+
{
|
| 2490 |
+
"epoch": 1.4534288638689867,
|
| 2491 |
+
"grad_norm": 0.3515625,
|
| 2492 |
+
"learning_rate": 5.2981739553528944e-05,
|
| 2493 |
+
"loss": 0.5278,
|
| 2494 |
+
"step": 1420
|
| 2495 |
+
},
|
| 2496 |
+
{
|
| 2497 |
+
"epoch": 1.4575230296827022,
|
| 2498 |
+
"grad_norm": 0.365234375,
|
| 2499 |
+
"learning_rate": 5.2240463857120365e-05,
|
| 2500 |
+
"loss": 0.4959,
|
| 2501 |
+
"step": 1424
|
| 2502 |
+
},
|
| 2503 |
+
{
|
| 2504 |
+
"epoch": 1.4616171954964177,
|
| 2505 |
+
"grad_norm": 0.384765625,
|
| 2506 |
+
"learning_rate": 5.1503315445081946e-05,
|
| 2507 |
+
"loss": 0.4767,
|
| 2508 |
+
"step": 1428
|
| 2509 |
+
},
|
| 2510 |
+
{
|
| 2511 |
+
"epoch": 1.4657113613101331,
|
| 2512 |
+
"grad_norm": 0.357421875,
|
| 2513 |
+
"learning_rate": 5.0770325438890304e-05,
|
| 2514 |
+
"loss": 0.5052,
|
| 2515 |
+
"step": 1432
|
| 2516 |
+
},
|
| 2517 |
+
{
|
| 2518 |
+
"epoch": 1.4698055271238486,
|
| 2519 |
+
"grad_norm": 0.365234375,
|
| 2520 |
+
"learning_rate": 5.004152478445939e-05,
|
| 2521 |
+
"loss": 0.4988,
|
| 2522 |
+
"step": 1436
|
| 2523 |
+
},
|
| 2524 |
+
{
|
| 2525 |
+
"epoch": 1.473899692937564,
|
| 2526 |
+
"grad_norm": 0.36328125,
|
| 2527 |
+
"learning_rate": 4.9316944250834126e-05,
|
| 2528 |
+
"loss": 0.486,
|
| 2529 |
+
"step": 1440
|
| 2530 |
+
},
|
| 2531 |
+
{
|
| 2532 |
+
"epoch": 1.4779938587512795,
|
| 2533 |
+
"grad_norm": 0.384765625,
|
| 2534 |
+
"learning_rate": 4.8596614428891094e-05,
|
| 2535 |
+
"loss": 0.5126,
|
| 2536 |
+
"step": 1444
|
| 2537 |
+
},
|
| 2538 |
+
{
|
| 2539 |
+
"epoch": 1.482088024564995,
|
| 2540 |
+
"grad_norm": 0.35546875,
|
| 2541 |
+
"learning_rate": 4.788056573004726e-05,
|
| 2542 |
+
"loss": 0.5124,
|
| 2543 |
+
"step": 1448
|
| 2544 |
+
},
|
| 2545 |
+
{
|
| 2546 |
+
"epoch": 1.4861821903787105,
|
| 2547 |
+
"grad_norm": 0.365234375,
|
| 2548 |
+
"learning_rate": 4.7168828384975985e-05,
|
| 2549 |
+
"loss": 0.5304,
|
| 2550 |
+
"step": 1452
|
| 2551 |
+
},
|
| 2552 |
+
{
|
| 2553 |
+
"epoch": 1.4902763561924257,
|
| 2554 |
+
"grad_norm": 0.376953125,
|
| 2555 |
+
"learning_rate": 4.646143244233068e-05,
|
| 2556 |
+
"loss": 0.5023,
|
| 2557 |
+
"step": 1456
|
| 2558 |
+
},
|
| 2559 |
+
{
|
| 2560 |
+
"epoch": 1.4943705220061412,
|
| 2561 |
+
"grad_norm": 0.33203125,
|
| 2562 |
+
"learning_rate": 4.575840776747621e-05,
|
| 2563 |
+
"loss": 0.453,
|
| 2564 |
+
"step": 1460
|
| 2565 |
+
},
|
| 2566 |
+
{
|
| 2567 |
+
"epoch": 1.4984646878198566,
|
| 2568 |
+
"grad_norm": 0.365234375,
|
| 2569 |
+
"learning_rate": 4.505978404122805e-05,
|
| 2570 |
+
"loss": 0.4769,
|
| 2571 |
+
"step": 1464
|
| 2572 |
+
},
|
| 2573 |
+
{
|
| 2574 |
+
"epoch": 1.5025588536335721,
|
| 2575 |
+
"grad_norm": 0.36328125,
|
| 2576 |
+
"learning_rate": 4.436559075859911e-05,
|
| 2577 |
+
"loss": 0.54,
|
| 2578 |
+
"step": 1468
|
| 2579 |
+
},
|
| 2580 |
+
{
|
| 2581 |
+
"epoch": 1.5066530194472876,
|
| 2582 |
+
"grad_norm": 0.365234375,
|
| 2583 |
+
"learning_rate": 4.367585722755474e-05,
|
| 2584 |
+
"loss": 0.5083,
|
| 2585 |
+
"step": 1472
|
| 2586 |
+
},
|
| 2587 |
+
{
|
| 2588 |
+
"epoch": 1.510747185261003,
|
| 2589 |
+
"grad_norm": 0.341796875,
|
| 2590 |
+
"learning_rate": 4.299061256777498e-05,
|
| 2591 |
+
"loss": 0.4746,
|
| 2592 |
+
"step": 1476
|
| 2593 |
+
},
|
| 2594 |
+
{
|
| 2595 |
+
"epoch": 1.5148413510747185,
|
| 2596 |
+
"grad_norm": 0.3671875,
|
| 2597 |
+
"learning_rate": 4.23098857094255e-05,
|
| 2598 |
+
"loss": 0.511,
|
| 2599 |
+
"step": 1480
|
| 2600 |
+
},
|
| 2601 |
+
{
|
| 2602 |
+
"epoch": 1.518935516888434,
|
| 2603 |
+
"grad_norm": 0.380859375,
|
| 2604 |
+
"learning_rate": 4.163370539193606e-05,
|
| 2605 |
+
"loss": 0.4853,
|
| 2606 |
+
"step": 1484
|
| 2607 |
+
},
|
| 2608 |
+
{
|
| 2609 |
+
"epoch": 1.5230296827021494,
|
| 2610 |
+
"grad_norm": 0.35546875,
|
| 2611 |
+
"learning_rate": 4.0962100162787195e-05,
|
| 2612 |
+
"loss": 0.4949,
|
| 2613 |
+
"step": 1488
|
| 2614 |
+
},
|
| 2615 |
+
{
|
| 2616 |
+
"epoch": 1.527123848515865,
|
| 2617 |
+
"grad_norm": 0.37109375,
|
| 2618 |
+
"learning_rate": 4.029509837630499e-05,
|
| 2619 |
+
"loss": 0.4859,
|
| 2620 |
+
"step": 1492
|
| 2621 |
+
},
|
| 2622 |
+
{
|
| 2623 |
+
"epoch": 1.5312180143295804,
|
| 2624 |
+
"grad_norm": 0.353515625,
|
| 2625 |
+
"learning_rate": 3.9632728192463986e-05,
|
| 2626 |
+
"loss": 0.5075,
|
| 2627 |
+
"step": 1496
|
| 2628 |
+
},
|
| 2629 |
+
{
|
| 2630 |
+
"epoch": 1.5353121801432958,
|
| 2631 |
+
"grad_norm": 0.380859375,
|
| 2632 |
+
"learning_rate": 3.897501757569827e-05,
|
| 2633 |
+
"loss": 0.5268,
|
| 2634 |
+
"step": 1500
|
| 2635 |
+
}
|
| 2636 |
+
],
|
| 2637 |
+
"logging_steps": 4,
|
| 2638 |
+
"max_steps": 1954,
|
| 2639 |
+
"num_input_tokens_seen": 0,
|
| 2640 |
+
"num_train_epochs": 2,
|
| 2641 |
+
"save_steps": 500,
|
| 2642 |
+
"stateful_callbacks": {
|
| 2643 |
+
"TrainerControl": {
|
| 2644 |
+
"args": {
|
| 2645 |
+
"should_epoch_stop": false,
|
| 2646 |
+
"should_evaluate": false,
|
| 2647 |
+
"should_log": false,
|
| 2648 |
+
"should_save": true,
|
| 2649 |
+
"should_training_stop": false
|
| 2650 |
+
},
|
| 2651 |
+
"attributes": {}
|
| 2652 |
+
}
|
| 2653 |
+
},
|
| 2654 |
+
"total_flos": 9.81652806593151e+17,
|
| 2655 |
+
"train_batch_size": 32,
|
| 2656 |
+
"trial_name": null,
|
| 2657 |
+
"trial_params": null
|
| 2658 |
+
}
|
checkpoint-1500/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f9c03ab85612736ff806f80c0760cb10efb622262d7cd71babdea03fc557f761
|
| 3 |
+
size 5368
|
trainer_state.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|