Upload folder using huggingface_hub
Browse files- adapter/README.md +206 -0
- adapter/adapter_config.json +39 -0
- adapter/adapter_model.safetensors +3 -0
- optimizer.pt +2 -2
- pytorch_model.bin +2 -2
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +7 -1
- trainer_meta.json +6 -6
- trainer_state.json +3254 -0
adapter/README.md
ADDED
|
@@ -0,0 +1,206 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: Qwen/Qwen2-0.5B-Instruct
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- base_model:adapter:Qwen/Qwen2-0.5B-Instruct
|
| 6 |
+
- lora
|
| 7 |
+
- transformers
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
# Model Card for Model ID
|
| 11 |
+
|
| 12 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 13 |
+
|
| 14 |
+
|
| 15 |
+
|
| 16 |
+
## Model Details
|
| 17 |
+
|
| 18 |
+
### Model Description
|
| 19 |
+
|
| 20 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 21 |
+
|
| 22 |
+
|
| 23 |
+
|
| 24 |
+
- **Developed by:** [More Information Needed]
|
| 25 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 26 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 27 |
+
- **Model type:** [More Information Needed]
|
| 28 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 29 |
+
- **License:** [More Information Needed]
|
| 30 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 31 |
+
|
| 32 |
+
### Model Sources [optional]
|
| 33 |
+
|
| 34 |
+
<!-- Provide the basic links for the model. -->
|
| 35 |
+
|
| 36 |
+
- **Repository:** [More Information Needed]
|
| 37 |
+
- **Paper [optional]:** [More Information Needed]
|
| 38 |
+
- **Demo [optional]:** [More Information Needed]
|
| 39 |
+
|
| 40 |
+
## Uses
|
| 41 |
+
|
| 42 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 43 |
+
|
| 44 |
+
### Direct Use
|
| 45 |
+
|
| 46 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 47 |
+
|
| 48 |
+
[More Information Needed]
|
| 49 |
+
|
| 50 |
+
### Downstream Use [optional]
|
| 51 |
+
|
| 52 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 53 |
+
|
| 54 |
+
[More Information Needed]
|
| 55 |
+
|
| 56 |
+
### Out-of-Scope Use
|
| 57 |
+
|
| 58 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 59 |
+
|
| 60 |
+
[More Information Needed]
|
| 61 |
+
|
| 62 |
+
## Bias, Risks, and Limitations
|
| 63 |
+
|
| 64 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 65 |
+
|
| 66 |
+
[More Information Needed]
|
| 67 |
+
|
| 68 |
+
### Recommendations
|
| 69 |
+
|
| 70 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 71 |
+
|
| 72 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 73 |
+
|
| 74 |
+
## How to Get Started with the Model
|
| 75 |
+
|
| 76 |
+
Use the code below to get started with the model.
|
| 77 |
+
|
| 78 |
+
[More Information Needed]
|
| 79 |
+
|
| 80 |
+
## Training Details
|
| 81 |
+
|
| 82 |
+
### Training Data
|
| 83 |
+
|
| 84 |
+
<!-- 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. -->
|
| 85 |
+
|
| 86 |
+
[More Information Needed]
|
| 87 |
+
|
| 88 |
+
### Training Procedure
|
| 89 |
+
|
| 90 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 91 |
+
|
| 92 |
+
#### Preprocessing [optional]
|
| 93 |
+
|
| 94 |
+
[More Information Needed]
|
| 95 |
+
|
| 96 |
+
|
| 97 |
+
#### Training Hyperparameters
|
| 98 |
+
|
| 99 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 100 |
+
|
| 101 |
+
#### Speeds, Sizes, Times [optional]
|
| 102 |
+
|
| 103 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 104 |
+
|
| 105 |
+
[More Information Needed]
|
| 106 |
+
|
| 107 |
+
## Evaluation
|
| 108 |
+
|
| 109 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 110 |
+
|
| 111 |
+
### Testing Data, Factors & Metrics
|
| 112 |
+
|
| 113 |
+
#### Testing Data
|
| 114 |
+
|
| 115 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 116 |
+
|
| 117 |
+
[More Information Needed]
|
| 118 |
+
|
| 119 |
+
#### Factors
|
| 120 |
+
|
| 121 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 122 |
+
|
| 123 |
+
[More Information Needed]
|
| 124 |
+
|
| 125 |
+
#### Metrics
|
| 126 |
+
|
| 127 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
### Results
|
| 132 |
+
|
| 133 |
+
[More Information Needed]
|
| 134 |
+
|
| 135 |
+
#### Summary
|
| 136 |
+
|
| 137 |
+
|
| 138 |
+
|
| 139 |
+
## Model Examination [optional]
|
| 140 |
+
|
| 141 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 142 |
+
|
| 143 |
+
[More Information Needed]
|
| 144 |
+
|
| 145 |
+
## Environmental Impact
|
| 146 |
+
|
| 147 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 148 |
+
|
| 149 |
+
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).
|
| 150 |
+
|
| 151 |
+
- **Hardware Type:** [More Information Needed]
|
| 152 |
+
- **Hours used:** [More Information Needed]
|
| 153 |
+
- **Cloud Provider:** [More Information Needed]
|
| 154 |
+
- **Compute Region:** [More Information Needed]
|
| 155 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 156 |
+
|
| 157 |
+
## Technical Specifications [optional]
|
| 158 |
+
|
| 159 |
+
### Model Architecture and Objective
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
### Compute Infrastructure
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Hardware
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
#### Software
|
| 172 |
+
|
| 173 |
+
[More Information Needed]
|
| 174 |
+
|
| 175 |
+
## Citation [optional]
|
| 176 |
+
|
| 177 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 178 |
+
|
| 179 |
+
**BibTeX:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
**APA:**
|
| 184 |
+
|
| 185 |
+
[More Information Needed]
|
| 186 |
+
|
| 187 |
+
## Glossary [optional]
|
| 188 |
+
|
| 189 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## More Information [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Authors [optional]
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
|
| 201 |
+
## Model Card Contact
|
| 202 |
+
|
| 203 |
+
[More Information Needed]
|
| 204 |
+
### Framework versions
|
| 205 |
+
|
| 206 |
+
- PEFT 0.17.1
|
adapter/adapter_config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "Qwen/Qwen2-0.5B-Instruct",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": true,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 64,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.1,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"qalora_group_size": 16,
|
| 24 |
+
"r": 32,
|
| 25 |
+
"rank_pattern": {},
|
| 26 |
+
"revision": null,
|
| 27 |
+
"target_modules": [
|
| 28 |
+
"k_proj",
|
| 29 |
+
"v_proj",
|
| 30 |
+
"o_proj",
|
| 31 |
+
"q_proj"
|
| 32 |
+
],
|
| 33 |
+
"target_parameters": null,
|
| 34 |
+
"task_type": "FEATURE_EXTRACTION",
|
| 35 |
+
"trainable_token_indices": null,
|
| 36 |
+
"use_dora": false,
|
| 37 |
+
"use_qalora": false,
|
| 38 |
+
"use_rslora": false
|
| 39 |
+
}
|
adapter/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:95cbb8d7f2c0ecedae3d94c2a038e931bd3bd1cfe39e2b9b313df91f60868da2
|
| 3 |
+
size 560829384
|
optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:585c8aaaf9ea9e69d33337bc3ff60570af531c73962dfc046b81cad37c3337cd
|
| 3 |
+
size 4050202507
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fb97af5870650475a5e17d447ff6b657159e600820722baddaff8e118c1ec0a1
|
| 3 |
+
size 4543897811
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1d3e23a36255eddcd3a277c6724dd30af498796e96ab4a4fbac7d4ec2d11b949
|
| 3 |
+
size 14645
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cbca958e6af0e425ee1c5ea42f2f40a5f70c7afee7a38c7e4dce964c49c183f9
|
| 3 |
+
size 1593
|
special_tokens_map.json
CHANGED
|
@@ -1,6 +1,12 @@
|
|
| 1 |
{
|
| 2 |
"additional_special_tokens": [
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
],
|
| 5 |
"eos_token": {
|
| 6 |
"content": "<|im_end|>",
|
|
|
|
| 1 |
{
|
| 2 |
"additional_special_tokens": [
|
| 3 |
+
{
|
| 4 |
+
"content": "<|eoj|>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false
|
| 9 |
+
}
|
| 10 |
],
|
| 11 |
"eos_token": {
|
| 12 |
"content": "<|im_end|>",
|
trainer_meta.json
CHANGED
|
@@ -1,20 +1,20 @@
|
|
| 1 |
{
|
| 2 |
-
"timestamp": "
|
| 3 |
"model_class": "SequentialMultiTokenLM",
|
| 4 |
"n_future": 3,
|
| 5 |
"vocab_size": 151647,
|
| 6 |
-
"save_steps":
|
| 7 |
"learning_rate": 1e-05,
|
| 8 |
"weight_decay": 0.0,
|
| 9 |
"base_model_name_or_path": "Qwen/Qwen2-0.5B-Instruct",
|
| 10 |
-
"tokenizer_name_or_path": "/
|
| 11 |
"tokenizer_len_at_save": 151647,
|
| 12 |
"tokenizer_pad_token_id": 151643,
|
| 13 |
"dtype_hint": "float32",
|
| 14 |
"head_grad_scales": [
|
| 15 |
-
|
| 16 |
-
|
| 17 |
-
1.
|
| 18 |
],
|
| 19 |
"norm_grad_scales": true
|
| 20 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"timestamp": "20250908_212622",
|
| 3 |
"model_class": "SequentialMultiTokenLM",
|
| 4 |
"n_future": 3,
|
| 5 |
"vocab_size": 151647,
|
| 6 |
+
"save_steps": 1000,
|
| 7 |
"learning_rate": 1e-05,
|
| 8 |
"weight_decay": 0.0,
|
| 9 |
"base_model_name_or_path": "Qwen/Qwen2-0.5B-Instruct",
|
| 10 |
+
"tokenizer_name_or_path": "Qwen/Qwen2-0.5B-Instruct",
|
| 11 |
"tokenizer_len_at_save": 151647,
|
| 12 |
"tokenizer_pad_token_id": 151643,
|
| 13 |
"dtype_hint": "float32",
|
| 14 |
"head_grad_scales": [
|
| 15 |
+
0.5454545454545455,
|
| 16 |
+
0.9090909090909092,
|
| 17 |
+
1.5454545454545456
|
| 18 |
],
|
| 19 |
"norm_grad_scales": true
|
| 20 |
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,3254 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.7863785557986871,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 23000,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.0017095185995623632,
|
| 14 |
+
"grad_norm": 34.20619201660156,
|
| 15 |
+
"learning_rate": 8.376068376068377e-08,
|
| 16 |
+
"loss": 6.8966,
|
| 17 |
+
"step": 50
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.0034190371991247265,
|
| 21 |
+
"grad_norm": 32.02785110473633,
|
| 22 |
+
"learning_rate": 1.6923076923076923e-07,
|
| 23 |
+
"loss": 6.6568,
|
| 24 |
+
"step": 100
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.0051285557986870895,
|
| 28 |
+
"grad_norm": 35.386775970458984,
|
| 29 |
+
"learning_rate": 2.547008547008547e-07,
|
| 30 |
+
"loss": 6.2124,
|
| 31 |
+
"step": 150
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.006838074398249453,
|
| 35 |
+
"grad_norm": 23.91164207458496,
|
| 36 |
+
"learning_rate": 3.401709401709402e-07,
|
| 37 |
+
"loss": 5.8207,
|
| 38 |
+
"step": 200
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.008547592997811816,
|
| 42 |
+
"grad_norm": 30.31170654296875,
|
| 43 |
+
"learning_rate": 4.2564102564102564e-07,
|
| 44 |
+
"loss": 5.5524,
|
| 45 |
+
"step": 250
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.010257111597374179,
|
| 49 |
+
"grad_norm": 24.82166862487793,
|
| 50 |
+
"learning_rate": 5.111111111111112e-07,
|
| 51 |
+
"loss": 5.1772,
|
| 52 |
+
"step": 300
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.011966630196936542,
|
| 56 |
+
"grad_norm": 17.603418350219727,
|
| 57 |
+
"learning_rate": 5.965811965811966e-07,
|
| 58 |
+
"loss": 5.0611,
|
| 59 |
+
"step": 350
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.013676148796498906,
|
| 63 |
+
"grad_norm": 13.119149208068848,
|
| 64 |
+
"learning_rate": 6.820512820512821e-07,
|
| 65 |
+
"loss": 5.0102,
|
| 66 |
+
"step": 400
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.01538566739606127,
|
| 70 |
+
"grad_norm": 23.832378387451172,
|
| 71 |
+
"learning_rate": 7.675213675213676e-07,
|
| 72 |
+
"loss": 4.6759,
|
| 73 |
+
"step": 450
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.01709518599562363,
|
| 77 |
+
"grad_norm": 19.699283599853516,
|
| 78 |
+
"learning_rate": 8.529914529914531e-07,
|
| 79 |
+
"loss": 4.5444,
|
| 80 |
+
"step": 500
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.018804704595185996,
|
| 84 |
+
"grad_norm": 19.384296417236328,
|
| 85 |
+
"learning_rate": 9.384615384615385e-07,
|
| 86 |
+
"loss": 4.5259,
|
| 87 |
+
"step": 550
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.020514223194748358,
|
| 91 |
+
"grad_norm": 19.501312255859375,
|
| 92 |
+
"learning_rate": 1.023931623931624e-06,
|
| 93 |
+
"loss": 4.3041,
|
| 94 |
+
"step": 600
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.022223741794310723,
|
| 98 |
+
"grad_norm": 13.48172378540039,
|
| 99 |
+
"learning_rate": 1.1094017094017095e-06,
|
| 100 |
+
"loss": 4.215,
|
| 101 |
+
"step": 650
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.023933260393873085,
|
| 105 |
+
"grad_norm": 22.756120681762695,
|
| 106 |
+
"learning_rate": 1.194871794871795e-06,
|
| 107 |
+
"loss": 4.1054,
|
| 108 |
+
"step": 700
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.02564277899343545,
|
| 112 |
+
"grad_norm": 14.500043869018555,
|
| 113 |
+
"learning_rate": 1.2803418803418804e-06,
|
| 114 |
+
"loss": 4.1573,
|
| 115 |
+
"step": 750
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.02735229759299781,
|
| 119 |
+
"grad_norm": 21.77857208251953,
|
| 120 |
+
"learning_rate": 1.365811965811966e-06,
|
| 121 |
+
"loss": 4.0071,
|
| 122 |
+
"step": 800
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.029061816192560173,
|
| 126 |
+
"grad_norm": 19.40562629699707,
|
| 127 |
+
"learning_rate": 1.4512820512820514e-06,
|
| 128 |
+
"loss": 3.8912,
|
| 129 |
+
"step": 850
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.03077133479212254,
|
| 133 |
+
"grad_norm": 18.101581573486328,
|
| 134 |
+
"learning_rate": 1.5367521367521367e-06,
|
| 135 |
+
"loss": 3.8709,
|
| 136 |
+
"step": 900
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.032480853391684904,
|
| 140 |
+
"grad_norm": 17.86353874206543,
|
| 141 |
+
"learning_rate": 1.6222222222222223e-06,
|
| 142 |
+
"loss": 3.8385,
|
| 143 |
+
"step": 950
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.03419037199124726,
|
| 147 |
+
"grad_norm": 16.365238189697266,
|
| 148 |
+
"learning_rate": 1.7076923076923077e-06,
|
| 149 |
+
"loss": 3.7701,
|
| 150 |
+
"step": 1000
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.03589989059080963,
|
| 154 |
+
"grad_norm": 15.656188011169434,
|
| 155 |
+
"learning_rate": 1.7931623931623935e-06,
|
| 156 |
+
"loss": 3.7244,
|
| 157 |
+
"step": 1050
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.03760940919037199,
|
| 161 |
+
"grad_norm": 19.4959716796875,
|
| 162 |
+
"learning_rate": 1.8786324786324788e-06,
|
| 163 |
+
"loss": 3.5903,
|
| 164 |
+
"step": 1100
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.03931892778993436,
|
| 168 |
+
"grad_norm": 17.789569854736328,
|
| 169 |
+
"learning_rate": 1.964102564102564e-06,
|
| 170 |
+
"loss": 3.5679,
|
| 171 |
+
"step": 1150
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.041028446389496716,
|
| 175 |
+
"grad_norm": 14.917860984802246,
|
| 176 |
+
"learning_rate": 2.0495726495726498e-06,
|
| 177 |
+
"loss": 3.6257,
|
| 178 |
+
"step": 1200
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.04273796498905908,
|
| 182 |
+
"grad_norm": 15.332232475280762,
|
| 183 |
+
"learning_rate": 2.1350427350427354e-06,
|
| 184 |
+
"loss": 3.4988,
|
| 185 |
+
"step": 1250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.044447483588621446,
|
| 189 |
+
"grad_norm": 14.154925346374512,
|
| 190 |
+
"learning_rate": 2.2205128205128205e-06,
|
| 191 |
+
"loss": 3.5376,
|
| 192 |
+
"step": 1300
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.046157002188183804,
|
| 196 |
+
"grad_norm": 18.201717376708984,
|
| 197 |
+
"learning_rate": 2.305982905982906e-06,
|
| 198 |
+
"loss": 3.4419,
|
| 199 |
+
"step": 1350
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.04786652078774617,
|
| 203 |
+
"grad_norm": 18.137598037719727,
|
| 204 |
+
"learning_rate": 2.3914529914529917e-06,
|
| 205 |
+
"loss": 3.3533,
|
| 206 |
+
"step": 1400
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.049576039387308535,
|
| 210 |
+
"grad_norm": 18.30217170715332,
|
| 211 |
+
"learning_rate": 2.4769230769230773e-06,
|
| 212 |
+
"loss": 3.3475,
|
| 213 |
+
"step": 1450
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.0512855579868709,
|
| 217 |
+
"grad_norm": 21.307165145874023,
|
| 218 |
+
"learning_rate": 2.5623931623931624e-06,
|
| 219 |
+
"loss": 3.3188,
|
| 220 |
+
"step": 1500
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.05299507658643326,
|
| 224 |
+
"grad_norm": 23.544694900512695,
|
| 225 |
+
"learning_rate": 2.6478632478632484e-06,
|
| 226 |
+
"loss": 3.2971,
|
| 227 |
+
"step": 1550
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.05470459518599562,
|
| 231 |
+
"grad_norm": 20.15461540222168,
|
| 232 |
+
"learning_rate": 2.7333333333333336e-06,
|
| 233 |
+
"loss": 3.2786,
|
| 234 |
+
"step": 1600
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.05641411378555799,
|
| 238 |
+
"grad_norm": 15.73994255065918,
|
| 239 |
+
"learning_rate": 2.818803418803419e-06,
|
| 240 |
+
"loss": 3.1461,
|
| 241 |
+
"step": 1650
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.05812363238512035,
|
| 245 |
+
"grad_norm": 19.65288734436035,
|
| 246 |
+
"learning_rate": 2.9042735042735043e-06,
|
| 247 |
+
"loss": 3.0896,
|
| 248 |
+
"step": 1700
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.05983315098468271,
|
| 252 |
+
"grad_norm": 22.848451614379883,
|
| 253 |
+
"learning_rate": 2.98974358974359e-06,
|
| 254 |
+
"loss": 3.2667,
|
| 255 |
+
"step": 1750
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.06154266958424508,
|
| 259 |
+
"grad_norm": 19.8078556060791,
|
| 260 |
+
"learning_rate": 3.075213675213675e-06,
|
| 261 |
+
"loss": 3.1488,
|
| 262 |
+
"step": 1800
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.06325218818380744,
|
| 266 |
+
"grad_norm": 18.983543395996094,
|
| 267 |
+
"learning_rate": 3.160683760683761e-06,
|
| 268 |
+
"loss": 3.0173,
|
| 269 |
+
"step": 1850
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.06496170678336981,
|
| 273 |
+
"grad_norm": 21.267881393432617,
|
| 274 |
+
"learning_rate": 3.2461538461538466e-06,
|
| 275 |
+
"loss": 3.0424,
|
| 276 |
+
"step": 1900
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.06667122538293217,
|
| 280 |
+
"grad_norm": 18.275516510009766,
|
| 281 |
+
"learning_rate": 3.3316239316239318e-06,
|
| 282 |
+
"loss": 2.972,
|
| 283 |
+
"step": 1950
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.06838074398249452,
|
| 287 |
+
"grad_norm": 21.104080200195312,
|
| 288 |
+
"learning_rate": 3.4170940170940178e-06,
|
| 289 |
+
"loss": 3.0653,
|
| 290 |
+
"step": 2000
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.07009026258205689,
|
| 294 |
+
"grad_norm": 15.254624366760254,
|
| 295 |
+
"learning_rate": 3.502564102564103e-06,
|
| 296 |
+
"loss": 2.7883,
|
| 297 |
+
"step": 2050
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.07179978118161925,
|
| 301 |
+
"grad_norm": 18.156373977661133,
|
| 302 |
+
"learning_rate": 3.5880341880341885e-06,
|
| 303 |
+
"loss": 2.8612,
|
| 304 |
+
"step": 2100
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.07350929978118162,
|
| 308 |
+
"grad_norm": 24.07493782043457,
|
| 309 |
+
"learning_rate": 3.6735042735042737e-06,
|
| 310 |
+
"loss": 2.8092,
|
| 311 |
+
"step": 2150
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.07521881838074398,
|
| 315 |
+
"grad_norm": 13.714811325073242,
|
| 316 |
+
"learning_rate": 3.7589743589743592e-06,
|
| 317 |
+
"loss": 2.8359,
|
| 318 |
+
"step": 2200
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.07692833698030635,
|
| 322 |
+
"grad_norm": 17.753250122070312,
|
| 323 |
+
"learning_rate": 3.844444444444445e-06,
|
| 324 |
+
"loss": 2.964,
|
| 325 |
+
"step": 2250
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.07863785557986872,
|
| 329 |
+
"grad_norm": 18.18113899230957,
|
| 330 |
+
"learning_rate": 3.92991452991453e-06,
|
| 331 |
+
"loss": 2.9071,
|
| 332 |
+
"step": 2300
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.08034737417943107,
|
| 336 |
+
"grad_norm": 21.560134887695312,
|
| 337 |
+
"learning_rate": 4.015384615384615e-06,
|
| 338 |
+
"loss": 2.9326,
|
| 339 |
+
"step": 2350
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.08205689277899343,
|
| 343 |
+
"grad_norm": 15.2616548538208,
|
| 344 |
+
"learning_rate": 4.1008547008547015e-06,
|
| 345 |
+
"loss": 2.7805,
|
| 346 |
+
"step": 2400
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.0837664113785558,
|
| 350 |
+
"grad_norm": 22.07532501220703,
|
| 351 |
+
"learning_rate": 4.186324786324787e-06,
|
| 352 |
+
"loss": 2.7264,
|
| 353 |
+
"step": 2450
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.08547592997811816,
|
| 357 |
+
"grad_norm": 17.394521713256836,
|
| 358 |
+
"learning_rate": 4.271794871794872e-06,
|
| 359 |
+
"loss": 2.741,
|
| 360 |
+
"step": 2500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.08718544857768053,
|
| 364 |
+
"grad_norm": 21.23651123046875,
|
| 365 |
+
"learning_rate": 4.3572649572649574e-06,
|
| 366 |
+
"loss": 2.7985,
|
| 367 |
+
"step": 2550
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.08889496717724289,
|
| 371 |
+
"grad_norm": 15.779874801635742,
|
| 372 |
+
"learning_rate": 4.442735042735043e-06,
|
| 373 |
+
"loss": 2.8208,
|
| 374 |
+
"step": 2600
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.09060448577680526,
|
| 378 |
+
"grad_norm": 20.37311553955078,
|
| 379 |
+
"learning_rate": 4.528205128205129e-06,
|
| 380 |
+
"loss": 2.8134,
|
| 381 |
+
"step": 2650
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.09231400437636761,
|
| 385 |
+
"grad_norm": 17.330570220947266,
|
| 386 |
+
"learning_rate": 4.613675213675214e-06,
|
| 387 |
+
"loss": 2.8116,
|
| 388 |
+
"step": 2700
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.09402352297592997,
|
| 392 |
+
"grad_norm": 20.631671905517578,
|
| 393 |
+
"learning_rate": 4.6991452991453e-06,
|
| 394 |
+
"loss": 2.6903,
|
| 395 |
+
"step": 2750
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.09573304157549234,
|
| 399 |
+
"grad_norm": 20.615148544311523,
|
| 400 |
+
"learning_rate": 4.7846153846153845e-06,
|
| 401 |
+
"loss": 2.732,
|
| 402 |
+
"step": 2800
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.0974425601750547,
|
| 406 |
+
"grad_norm": 15.630000114440918,
|
| 407 |
+
"learning_rate": 4.870085470085471e-06,
|
| 408 |
+
"loss": 2.7111,
|
| 409 |
+
"step": 2850
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.09915207877461707,
|
| 413 |
+
"grad_norm": 27.40517807006836,
|
| 414 |
+
"learning_rate": 4.9555555555555565e-06,
|
| 415 |
+
"loss": 2.7426,
|
| 416 |
+
"step": 2900
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.10086159737417943,
|
| 420 |
+
"grad_norm": 38.03644561767578,
|
| 421 |
+
"learning_rate": 5.041025641025642e-06,
|
| 422 |
+
"loss": 2.5283,
|
| 423 |
+
"step": 2950
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.1025711159737418,
|
| 427 |
+
"grad_norm": 21.690614700317383,
|
| 428 |
+
"learning_rate": 5.126495726495727e-06,
|
| 429 |
+
"loss": 2.766,
|
| 430 |
+
"step": 3000
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.10428063457330415,
|
| 434 |
+
"grad_norm": 17.027589797973633,
|
| 435 |
+
"learning_rate": 5.211965811965812e-06,
|
| 436 |
+
"loss": 2.5797,
|
| 437 |
+
"step": 3050
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.10599015317286652,
|
| 441 |
+
"grad_norm": 16.64606475830078,
|
| 442 |
+
"learning_rate": 5.297435897435897e-06,
|
| 443 |
+
"loss": 2.6813,
|
| 444 |
+
"step": 3100
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.10769967177242888,
|
| 448 |
+
"grad_norm": 18.256309509277344,
|
| 449 |
+
"learning_rate": 5.3829059829059835e-06,
|
| 450 |
+
"loss": 2.6299,
|
| 451 |
+
"step": 3150
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.10940919037199125,
|
| 455 |
+
"grad_norm": 13.979446411132812,
|
| 456 |
+
"learning_rate": 5.468376068376069e-06,
|
| 457 |
+
"loss": 2.62,
|
| 458 |
+
"step": 3200
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.11111870897155361,
|
| 462 |
+
"grad_norm": 17.654306411743164,
|
| 463 |
+
"learning_rate": 5.553846153846154e-06,
|
| 464 |
+
"loss": 2.6431,
|
| 465 |
+
"step": 3250
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.11282822757111598,
|
| 469 |
+
"grad_norm": 21.24514389038086,
|
| 470 |
+
"learning_rate": 5.639316239316239e-06,
|
| 471 |
+
"loss": 2.5366,
|
| 472 |
+
"step": 3300
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.11453774617067834,
|
| 476 |
+
"grad_norm": 13.810998916625977,
|
| 477 |
+
"learning_rate": 5.724786324786326e-06,
|
| 478 |
+
"loss": 2.6265,
|
| 479 |
+
"step": 3350
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.1162472647702407,
|
| 483 |
+
"grad_norm": 11.360595703125,
|
| 484 |
+
"learning_rate": 5.8102564102564106e-06,
|
| 485 |
+
"loss": 2.4986,
|
| 486 |
+
"step": 3400
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.11795678336980306,
|
| 490 |
+
"grad_norm": 13.805792808532715,
|
| 491 |
+
"learning_rate": 5.895726495726496e-06,
|
| 492 |
+
"loss": 2.5982,
|
| 493 |
+
"step": 3450
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.11966630196936542,
|
| 497 |
+
"grad_norm": 25.531564712524414,
|
| 498 |
+
"learning_rate": 5.981196581196583e-06,
|
| 499 |
+
"loss": 2.5479,
|
| 500 |
+
"step": 3500
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.12137582056892779,
|
| 504 |
+
"grad_norm": 19.329952239990234,
|
| 505 |
+
"learning_rate": 6.066666666666667e-06,
|
| 506 |
+
"loss": 2.5495,
|
| 507 |
+
"step": 3550
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.12308533916849015,
|
| 511 |
+
"grad_norm": 13.985466957092285,
|
| 512 |
+
"learning_rate": 6.152136752136753e-06,
|
| 513 |
+
"loss": 2.5121,
|
| 514 |
+
"step": 3600
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.12479485776805252,
|
| 518 |
+
"grad_norm": 16.979772567749023,
|
| 519 |
+
"learning_rate": 6.237606837606838e-06,
|
| 520 |
+
"loss": 2.6066,
|
| 521 |
+
"step": 3650
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.12650437636761488,
|
| 525 |
+
"grad_norm": 12.745477676391602,
|
| 526 |
+
"learning_rate": 6.323076923076924e-06,
|
| 527 |
+
"loss": 2.5563,
|
| 528 |
+
"step": 3700
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.12821389496717725,
|
| 532 |
+
"grad_norm": 17.420799255371094,
|
| 533 |
+
"learning_rate": 6.408547008547009e-06,
|
| 534 |
+
"loss": 2.4173,
|
| 535 |
+
"step": 3750
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.12992341356673962,
|
| 539 |
+
"grad_norm": 17.6093807220459,
|
| 540 |
+
"learning_rate": 6.494017094017094e-06,
|
| 541 |
+
"loss": 2.4656,
|
| 542 |
+
"step": 3800
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.13163293216630198,
|
| 546 |
+
"grad_norm": 16.195486068725586,
|
| 547 |
+
"learning_rate": 6.57948717948718e-06,
|
| 548 |
+
"loss": 2.4247,
|
| 549 |
+
"step": 3850
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.13334245076586435,
|
| 553 |
+
"grad_norm": 27.564342498779297,
|
| 554 |
+
"learning_rate": 6.6649572649572655e-06,
|
| 555 |
+
"loss": 2.5029,
|
| 556 |
+
"step": 3900
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.13505196936542668,
|
| 560 |
+
"grad_norm": 13.072511672973633,
|
| 561 |
+
"learning_rate": 6.750427350427351e-06,
|
| 562 |
+
"loss": 2.5668,
|
| 563 |
+
"step": 3950
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.13676148796498905,
|
| 567 |
+
"grad_norm": 14.926274299621582,
|
| 568 |
+
"learning_rate": 6.835897435897436e-06,
|
| 569 |
+
"loss": 2.4985,
|
| 570 |
+
"step": 4000
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.1384710065645514,
|
| 574 |
+
"grad_norm": 28.216571807861328,
|
| 575 |
+
"learning_rate": 6.921367521367522e-06,
|
| 576 |
+
"loss": 2.35,
|
| 577 |
+
"step": 4050
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.14018052516411378,
|
| 581 |
+
"grad_norm": 21.192350387573242,
|
| 582 |
+
"learning_rate": 7.006837606837608e-06,
|
| 583 |
+
"loss": 2.4142,
|
| 584 |
+
"step": 4100
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.14189004376367614,
|
| 588 |
+
"grad_norm": 16.471691131591797,
|
| 589 |
+
"learning_rate": 7.0923076923076926e-06,
|
| 590 |
+
"loss": 2.4576,
|
| 591 |
+
"step": 4150
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.1435995623632385,
|
| 595 |
+
"grad_norm": 19.943017959594727,
|
| 596 |
+
"learning_rate": 7.177777777777778e-06,
|
| 597 |
+
"loss": 2.4515,
|
| 598 |
+
"step": 4200
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.14530908096280087,
|
| 602 |
+
"grad_norm": 17.90447235107422,
|
| 603 |
+
"learning_rate": 7.2632478632478646e-06,
|
| 604 |
+
"loss": 2.4173,
|
| 605 |
+
"step": 4250
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.14701859956236324,
|
| 609 |
+
"grad_norm": 21.140586853027344,
|
| 610 |
+
"learning_rate": 7.348717948717949e-06,
|
| 611 |
+
"loss": 2.4123,
|
| 612 |
+
"step": 4300
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.1487281181619256,
|
| 616 |
+
"grad_norm": 22.993038177490234,
|
| 617 |
+
"learning_rate": 7.434188034188035e-06,
|
| 618 |
+
"loss": 2.3826,
|
| 619 |
+
"step": 4350
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.15043763676148797,
|
| 623 |
+
"grad_norm": 25.716772079467773,
|
| 624 |
+
"learning_rate": 7.51965811965812e-06,
|
| 625 |
+
"loss": 2.3281,
|
| 626 |
+
"step": 4400
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.15214715536105033,
|
| 630 |
+
"grad_norm": 18.103527069091797,
|
| 631 |
+
"learning_rate": 7.605128205128206e-06,
|
| 632 |
+
"loss": 2.3241,
|
| 633 |
+
"step": 4450
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.1538566739606127,
|
| 637 |
+
"grad_norm": 17.1453914642334,
|
| 638 |
+
"learning_rate": 7.690598290598292e-06,
|
| 639 |
+
"loss": 2.3254,
|
| 640 |
+
"step": 4500
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.15556619256017507,
|
| 644 |
+
"grad_norm": 14.331672668457031,
|
| 645 |
+
"learning_rate": 7.776068376068377e-06,
|
| 646 |
+
"loss": 2.3201,
|
| 647 |
+
"step": 4550
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.15727571115973743,
|
| 651 |
+
"grad_norm": 20.77884864807129,
|
| 652 |
+
"learning_rate": 7.861538461538463e-06,
|
| 653 |
+
"loss": 2.3531,
|
| 654 |
+
"step": 4600
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.15898522975929977,
|
| 658 |
+
"grad_norm": 18.025270462036133,
|
| 659 |
+
"learning_rate": 7.947008547008548e-06,
|
| 660 |
+
"loss": 2.3346,
|
| 661 |
+
"step": 4650
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.16069474835886213,
|
| 665 |
+
"grad_norm": 16.290367126464844,
|
| 666 |
+
"learning_rate": 8.032478632478632e-06,
|
| 667 |
+
"loss": 2.3535,
|
| 668 |
+
"step": 4700
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.1624042669584245,
|
| 672 |
+
"grad_norm": 24.518840789794922,
|
| 673 |
+
"learning_rate": 8.117948717948718e-06,
|
| 674 |
+
"loss": 2.2131,
|
| 675 |
+
"step": 4750
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.16411378555798686,
|
| 679 |
+
"grad_norm": 20.910388946533203,
|
| 680 |
+
"learning_rate": 8.203418803418805e-06,
|
| 681 |
+
"loss": 2.3607,
|
| 682 |
+
"step": 4800
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.16582330415754923,
|
| 686 |
+
"grad_norm": 13.96959400177002,
|
| 687 |
+
"learning_rate": 8.288888888888889e-06,
|
| 688 |
+
"loss": 2.2136,
|
| 689 |
+
"step": 4850
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.1675328227571116,
|
| 693 |
+
"grad_norm": 17.41702651977539,
|
| 694 |
+
"learning_rate": 8.374358974358975e-06,
|
| 695 |
+
"loss": 2.3835,
|
| 696 |
+
"step": 4900
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.16924234135667396,
|
| 700 |
+
"grad_norm": 17.133712768554688,
|
| 701 |
+
"learning_rate": 8.45982905982906e-06,
|
| 702 |
+
"loss": 2.1707,
|
| 703 |
+
"step": 4950
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.17095185995623632,
|
| 707 |
+
"grad_norm": 35.360572814941406,
|
| 708 |
+
"learning_rate": 8.545299145299146e-06,
|
| 709 |
+
"loss": 2.3687,
|
| 710 |
+
"step": 5000
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.1726613785557987,
|
| 714 |
+
"grad_norm": 15.467413902282715,
|
| 715 |
+
"learning_rate": 8.630769230769231e-06,
|
| 716 |
+
"loss": 2.3401,
|
| 717 |
+
"step": 5050
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.17437089715536105,
|
| 721 |
+
"grad_norm": 34.2485466003418,
|
| 722 |
+
"learning_rate": 8.716239316239317e-06,
|
| 723 |
+
"loss": 2.3111,
|
| 724 |
+
"step": 5100
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.17608041575492342,
|
| 728 |
+
"grad_norm": 21.256460189819336,
|
| 729 |
+
"learning_rate": 8.801709401709402e-06,
|
| 730 |
+
"loss": 2.3289,
|
| 731 |
+
"step": 5150
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 0.17778993435448578,
|
| 735 |
+
"grad_norm": 18.203758239746094,
|
| 736 |
+
"learning_rate": 8.887179487179488e-06,
|
| 737 |
+
"loss": 2.2043,
|
| 738 |
+
"step": 5200
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.17949945295404815,
|
| 742 |
+
"grad_norm": 13.081682205200195,
|
| 743 |
+
"learning_rate": 8.972649572649574e-06,
|
| 744 |
+
"loss": 2.1719,
|
| 745 |
+
"step": 5250
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.18120897155361052,
|
| 749 |
+
"grad_norm": 20.49002456665039,
|
| 750 |
+
"learning_rate": 9.05811965811966e-06,
|
| 751 |
+
"loss": 2.1455,
|
| 752 |
+
"step": 5300
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.18291849015317288,
|
| 756 |
+
"grad_norm": 14.190125465393066,
|
| 757 |
+
"learning_rate": 9.143589743589745e-06,
|
| 758 |
+
"loss": 2.205,
|
| 759 |
+
"step": 5350
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.18462800875273522,
|
| 763 |
+
"grad_norm": 16.424596786499023,
|
| 764 |
+
"learning_rate": 9.22905982905983e-06,
|
| 765 |
+
"loss": 2.248,
|
| 766 |
+
"step": 5400
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 0.18633752735229758,
|
| 770 |
+
"grad_norm": 21.05573081970215,
|
| 771 |
+
"learning_rate": 9.314529914529916e-06,
|
| 772 |
+
"loss": 2.2435,
|
| 773 |
+
"step": 5450
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.18804704595185995,
|
| 777 |
+
"grad_norm": 15.5685396194458,
|
| 778 |
+
"learning_rate": 9.4e-06,
|
| 779 |
+
"loss": 2.2207,
|
| 780 |
+
"step": 5500
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 0.1897565645514223,
|
| 784 |
+
"grad_norm": 16.1705322265625,
|
| 785 |
+
"learning_rate": 9.485470085470087e-06,
|
| 786 |
+
"loss": 2.1864,
|
| 787 |
+
"step": 5550
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 0.19146608315098468,
|
| 791 |
+
"grad_norm": 15.598201751708984,
|
| 792 |
+
"learning_rate": 9.570940170940171e-06,
|
| 793 |
+
"loss": 2.2094,
|
| 794 |
+
"step": 5600
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.19317560175054704,
|
| 798 |
+
"grad_norm": 15.844294548034668,
|
| 799 |
+
"learning_rate": 9.656410256410257e-06,
|
| 800 |
+
"loss": 2.2291,
|
| 801 |
+
"step": 5650
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.1948851203501094,
|
| 805 |
+
"grad_norm": 15.670059204101562,
|
| 806 |
+
"learning_rate": 9.741880341880344e-06,
|
| 807 |
+
"loss": 2.2147,
|
| 808 |
+
"step": 5700
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 0.19659463894967177,
|
| 812 |
+
"grad_norm": 12.44599437713623,
|
| 813 |
+
"learning_rate": 9.827350427350428e-06,
|
| 814 |
+
"loss": 2.2226,
|
| 815 |
+
"step": 5750
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 0.19830415754923414,
|
| 819 |
+
"grad_norm": 13.161368370056152,
|
| 820 |
+
"learning_rate": 9.912820512820513e-06,
|
| 821 |
+
"loss": 2.2692,
|
| 822 |
+
"step": 5800
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 0.2000136761487965,
|
| 826 |
+
"grad_norm": 19.317020416259766,
|
| 827 |
+
"learning_rate": 9.998290598290599e-06,
|
| 828 |
+
"loss": 2.1788,
|
| 829 |
+
"step": 5850
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 0.20172319474835887,
|
| 833 |
+
"grad_norm": 17.623424530029297,
|
| 834 |
+
"learning_rate": 9.99997862525975e-06,
|
| 835 |
+
"loss": 2.1676,
|
| 836 |
+
"step": 5900
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 0.20343271334792123,
|
| 840 |
+
"grad_norm": 15.066019058227539,
|
| 841 |
+
"learning_rate": 9.999912747451412e-06,
|
| 842 |
+
"loss": 2.3071,
|
| 843 |
+
"step": 5950
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.2051422319474836,
|
| 847 |
+
"grad_norm": 15.274186134338379,
|
| 848 |
+
"learning_rate": 9.99980235825902e-06,
|
| 849 |
+
"loss": 2.2751,
|
| 850 |
+
"step": 6000
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 0.20685175054704596,
|
| 854 |
+
"grad_norm": 12.797357559204102,
|
| 855 |
+
"learning_rate": 9.999647458665305e-06,
|
| 856 |
+
"loss": 2.1273,
|
| 857 |
+
"step": 6050
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.2085612691466083,
|
| 861 |
+
"grad_norm": 27.488948822021484,
|
| 862 |
+
"learning_rate": 9.999448050049255e-06,
|
| 863 |
+
"loss": 2.1535,
|
| 864 |
+
"step": 6100
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.21027078774617067,
|
| 868 |
+
"grad_norm": 37.757755279541016,
|
| 869 |
+
"learning_rate": 9.999204134186085e-06,
|
| 870 |
+
"loss": 2.2644,
|
| 871 |
+
"step": 6150
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 0.21198030634573303,
|
| 875 |
+
"grad_norm": 18.722148895263672,
|
| 876 |
+
"learning_rate": 9.998915713247245e-06,
|
| 877 |
+
"loss": 2.2478,
|
| 878 |
+
"step": 6200
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.2136898249452954,
|
| 882 |
+
"grad_norm": 22.181777954101562,
|
| 883 |
+
"learning_rate": 9.99858278980038e-06,
|
| 884 |
+
"loss": 2.1993,
|
| 885 |
+
"step": 6250
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.21539934354485776,
|
| 889 |
+
"grad_norm": 26.6999568939209,
|
| 890 |
+
"learning_rate": 9.998205366809318e-06,
|
| 891 |
+
"loss": 2.1414,
|
| 892 |
+
"step": 6300
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 0.21710886214442013,
|
| 896 |
+
"grad_norm": 20.9763240814209,
|
| 897 |
+
"learning_rate": 9.997783447634044e-06,
|
| 898 |
+
"loss": 2.0355,
|
| 899 |
+
"step": 6350
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 0.2188183807439825,
|
| 903 |
+
"grad_norm": 16.244672775268555,
|
| 904 |
+
"learning_rate": 9.997317036030662e-06,
|
| 905 |
+
"loss": 1.9715,
|
| 906 |
+
"step": 6400
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.22052789934354486,
|
| 910 |
+
"grad_norm": 44.34477615356445,
|
| 911 |
+
"learning_rate": 9.996806136151373e-06,
|
| 912 |
+
"loss": 2.2538,
|
| 913 |
+
"step": 6450
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 0.22223741794310722,
|
| 917 |
+
"grad_norm": 22.649791717529297,
|
| 918 |
+
"learning_rate": 9.996250752544426e-06,
|
| 919 |
+
"loss": 2.0468,
|
| 920 |
+
"step": 6500
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 0.2239469365426696,
|
| 924 |
+
"grad_norm": 15.583914756774902,
|
| 925 |
+
"learning_rate": 9.995650890154085e-06,
|
| 926 |
+
"loss": 2.1565,
|
| 927 |
+
"step": 6550
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.22565645514223195,
|
| 931 |
+
"grad_norm": 14.008044242858887,
|
| 932 |
+
"learning_rate": 9.995006554320588e-06,
|
| 933 |
+
"loss": 2.1831,
|
| 934 |
+
"step": 6600
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 0.22736597374179432,
|
| 938 |
+
"grad_norm": 16.54193687438965,
|
| 939 |
+
"learning_rate": 9.994317750780087e-06,
|
| 940 |
+
"loss": 2.0943,
|
| 941 |
+
"step": 6650
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 0.22907549234135668,
|
| 945 |
+
"grad_norm": 45.659122467041016,
|
| 946 |
+
"learning_rate": 9.99358448566461e-06,
|
| 947 |
+
"loss": 2.1277,
|
| 948 |
+
"step": 6700
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 0.23078501094091905,
|
| 952 |
+
"grad_norm": 16.820131301879883,
|
| 953 |
+
"learning_rate": 9.992806765502001e-06,
|
| 954 |
+
"loss": 2.0758,
|
| 955 |
+
"step": 6750
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 0.2324945295404814,
|
| 959 |
+
"grad_norm": 20.920974731445312,
|
| 960 |
+
"learning_rate": 9.991984597215863e-06,
|
| 961 |
+
"loss": 2.0924,
|
| 962 |
+
"step": 6800
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.23420404814004375,
|
| 966 |
+
"grad_norm": 22.39616584777832,
|
| 967 |
+
"learning_rate": 9.991117988125487e-06,
|
| 968 |
+
"loss": 2.0189,
|
| 969 |
+
"step": 6850
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.23591356673960612,
|
| 973 |
+
"grad_norm": 16.077375411987305,
|
| 974 |
+
"learning_rate": 9.990206945945809e-06,
|
| 975 |
+
"loss": 2.1269,
|
| 976 |
+
"step": 6900
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 0.23762308533916848,
|
| 980 |
+
"grad_norm": 16.124616622924805,
|
| 981 |
+
"learning_rate": 9.989251478787313e-06,
|
| 982 |
+
"loss": 2.075,
|
| 983 |
+
"step": 6950
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 0.23933260393873085,
|
| 987 |
+
"grad_norm": 14.3237886428833,
|
| 988 |
+
"learning_rate": 9.98825159515599e-06,
|
| 989 |
+
"loss": 2.1884,
|
| 990 |
+
"step": 7000
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 0.2410421225382932,
|
| 994 |
+
"grad_norm": 16.76456069946289,
|
| 995 |
+
"learning_rate": 9.987207303953225e-06,
|
| 996 |
+
"loss": 2.0235,
|
| 997 |
+
"step": 7050
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 0.24275164113785558,
|
| 1001 |
+
"grad_norm": 14.389822006225586,
|
| 1002 |
+
"learning_rate": 9.986118614475757e-06,
|
| 1003 |
+
"loss": 2.0543,
|
| 1004 |
+
"step": 7100
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 0.24446115973741794,
|
| 1008 |
+
"grad_norm": 16.218551635742188,
|
| 1009 |
+
"learning_rate": 9.984985536415568e-06,
|
| 1010 |
+
"loss": 1.9819,
|
| 1011 |
+
"step": 7150
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 0.2461706783369803,
|
| 1015 |
+
"grad_norm": 15.761117935180664,
|
| 1016 |
+
"learning_rate": 9.98380807985981e-06,
|
| 1017 |
+
"loss": 2.1784,
|
| 1018 |
+
"step": 7200
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 0.24788019693654267,
|
| 1022 |
+
"grad_norm": 20.7835636138916,
|
| 1023 |
+
"learning_rate": 9.982586255290709e-06,
|
| 1024 |
+
"loss": 2.0753,
|
| 1025 |
+
"step": 7250
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 0.24958971553610504,
|
| 1029 |
+
"grad_norm": 13.867836952209473,
|
| 1030 |
+
"learning_rate": 9.981320073585474e-06,
|
| 1031 |
+
"loss": 2.1647,
|
| 1032 |
+
"step": 7300
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 0.2512992341356674,
|
| 1036 |
+
"grad_norm": 19.391090393066406,
|
| 1037 |
+
"learning_rate": 9.980009546016204e-06,
|
| 1038 |
+
"loss": 2.1356,
|
| 1039 |
+
"step": 7350
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 0.25300875273522977,
|
| 1043 |
+
"grad_norm": 13.705766677856445,
|
| 1044 |
+
"learning_rate": 9.97865468424978e-06,
|
| 1045 |
+
"loss": 2.078,
|
| 1046 |
+
"step": 7400
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 0.25471827133479213,
|
| 1050 |
+
"grad_norm": 11.007736206054688,
|
| 1051 |
+
"learning_rate": 9.977255500347768e-06,
|
| 1052 |
+
"loss": 1.9398,
|
| 1053 |
+
"step": 7450
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 0.2564277899343545,
|
| 1057 |
+
"grad_norm": 19.959243774414062,
|
| 1058 |
+
"learning_rate": 9.975812006766307e-06,
|
| 1059 |
+
"loss": 2.1255,
|
| 1060 |
+
"step": 7500
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 0.25813730853391686,
|
| 1064 |
+
"grad_norm": 13.390128135681152,
|
| 1065 |
+
"learning_rate": 9.974324216356004e-06,
|
| 1066 |
+
"loss": 1.9932,
|
| 1067 |
+
"step": 7550
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 0.25984682713347923,
|
| 1071 |
+
"grad_norm": 16.48237419128418,
|
| 1072 |
+
"learning_rate": 9.972792142361807e-06,
|
| 1073 |
+
"loss": 1.9915,
|
| 1074 |
+
"step": 7600
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 0.2615563457330416,
|
| 1078 |
+
"grad_norm": 15.196588516235352,
|
| 1079 |
+
"learning_rate": 9.971215798422903e-06,
|
| 1080 |
+
"loss": 2.0923,
|
| 1081 |
+
"step": 7650
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 0.26326586433260396,
|
| 1085 |
+
"grad_norm": 11.075020790100098,
|
| 1086 |
+
"learning_rate": 9.96959519857259e-06,
|
| 1087 |
+
"loss": 2.0227,
|
| 1088 |
+
"step": 7700
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 0.2649753829321663,
|
| 1092 |
+
"grad_norm": 14.955096244812012,
|
| 1093 |
+
"learning_rate": 9.967930357238143e-06,
|
| 1094 |
+
"loss": 2.1203,
|
| 1095 |
+
"step": 7750
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 0.2666849015317287,
|
| 1099 |
+
"grad_norm": 14.905282020568848,
|
| 1100 |
+
"learning_rate": 9.966221289240701e-06,
|
| 1101 |
+
"loss": 1.9937,
|
| 1102 |
+
"step": 7800
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 0.26839442013129106,
|
| 1106 |
+
"grad_norm": 13.809823036193848,
|
| 1107 |
+
"learning_rate": 9.964468009795128e-06,
|
| 1108 |
+
"loss": 1.924,
|
| 1109 |
+
"step": 7850
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 0.27010393873085337,
|
| 1113 |
+
"grad_norm": 12.6084623336792,
|
| 1114 |
+
"learning_rate": 9.962670534509874e-06,
|
| 1115 |
+
"loss": 1.9593,
|
| 1116 |
+
"step": 7900
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 0.27181345733041573,
|
| 1120 |
+
"grad_norm": 14.69896411895752,
|
| 1121 |
+
"learning_rate": 9.960828879386839e-06,
|
| 1122 |
+
"loss": 1.9911,
|
| 1123 |
+
"step": 7950
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 0.2735229759299781,
|
| 1127 |
+
"grad_norm": 14.121038436889648,
|
| 1128 |
+
"learning_rate": 9.958943060821236e-06,
|
| 1129 |
+
"loss": 2.0002,
|
| 1130 |
+
"step": 8000
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 0.27523249452954046,
|
| 1134 |
+
"grad_norm": 23.24753761291504,
|
| 1135 |
+
"learning_rate": 9.957013095601433e-06,
|
| 1136 |
+
"loss": 2.0019,
|
| 1137 |
+
"step": 8050
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 0.2769420131291028,
|
| 1141 |
+
"grad_norm": 14.432645797729492,
|
| 1142 |
+
"learning_rate": 9.95503900090882e-06,
|
| 1143 |
+
"loss": 2.0793,
|
| 1144 |
+
"step": 8100
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 0.2786515317286652,
|
| 1148 |
+
"grad_norm": 17.42491340637207,
|
| 1149 |
+
"learning_rate": 9.953020794317636e-06,
|
| 1150 |
+
"loss": 1.9915,
|
| 1151 |
+
"step": 8150
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 0.28036105032822756,
|
| 1155 |
+
"grad_norm": 18.98630142211914,
|
| 1156 |
+
"learning_rate": 9.95095849379483e-06,
|
| 1157 |
+
"loss": 1.844,
|
| 1158 |
+
"step": 8200
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 0.2820705689277899,
|
| 1162 |
+
"grad_norm": 12.92850399017334,
|
| 1163 |
+
"learning_rate": 9.948852117699891e-06,
|
| 1164 |
+
"loss": 2.0165,
|
| 1165 |
+
"step": 8250
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 0.2837800875273523,
|
| 1169 |
+
"grad_norm": 20.14081573486328,
|
| 1170 |
+
"learning_rate": 9.946701684784693e-06,
|
| 1171 |
+
"loss": 1.9656,
|
| 1172 |
+
"step": 8300
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 0.28548960612691465,
|
| 1176 |
+
"grad_norm": 18.85413932800293,
|
| 1177 |
+
"learning_rate": 9.944507214193314e-06,
|
| 1178 |
+
"loss": 1.9689,
|
| 1179 |
+
"step": 8350
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 0.287199124726477,
|
| 1183 |
+
"grad_norm": 14.870792388916016,
|
| 1184 |
+
"learning_rate": 9.942268725461885e-06,
|
| 1185 |
+
"loss": 2.0667,
|
| 1186 |
+
"step": 8400
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 0.2889086433260394,
|
| 1190 |
+
"grad_norm": 19.028017044067383,
|
| 1191 |
+
"learning_rate": 9.939986238518398e-06,
|
| 1192 |
+
"loss": 2.0373,
|
| 1193 |
+
"step": 8450
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 0.29061816192560175,
|
| 1197 |
+
"grad_norm": 15.60130786895752,
|
| 1198 |
+
"learning_rate": 9.937659773682536e-06,
|
| 1199 |
+
"loss": 1.9824,
|
| 1200 |
+
"step": 8500
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 0.2923276805251641,
|
| 1204 |
+
"grad_norm": 20.719398498535156,
|
| 1205 |
+
"learning_rate": 9.935289351665497e-06,
|
| 1206 |
+
"loss": 1.9714,
|
| 1207 |
+
"step": 8550
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 0.2940371991247265,
|
| 1211 |
+
"grad_norm": 14.705081939697266,
|
| 1212 |
+
"learning_rate": 9.932874993569803e-06,
|
| 1213 |
+
"loss": 2.0971,
|
| 1214 |
+
"step": 8600
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 0.29574671772428884,
|
| 1218 |
+
"grad_norm": 11.282833099365234,
|
| 1219 |
+
"learning_rate": 9.930416720889109e-06,
|
| 1220 |
+
"loss": 2.0876,
|
| 1221 |
+
"step": 8650
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 0.2974562363238512,
|
| 1225 |
+
"grad_norm": 19.6205997467041,
|
| 1226 |
+
"learning_rate": 9.927914555508024e-06,
|
| 1227 |
+
"loss": 1.8808,
|
| 1228 |
+
"step": 8700
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 0.2991657549234136,
|
| 1232 |
+
"grad_norm": 25.020099639892578,
|
| 1233 |
+
"learning_rate": 9.925368519701905e-06,
|
| 1234 |
+
"loss": 1.8979,
|
| 1235 |
+
"step": 8750
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 0.30087527352297594,
|
| 1239 |
+
"grad_norm": 17.481502532958984,
|
| 1240 |
+
"learning_rate": 9.922778636136662e-06,
|
| 1241 |
+
"loss": 1.9658,
|
| 1242 |
+
"step": 8800
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 0.3025847921225383,
|
| 1246 |
+
"grad_norm": 21.219453811645508,
|
| 1247 |
+
"learning_rate": 9.92014492786856e-06,
|
| 1248 |
+
"loss": 2.0974,
|
| 1249 |
+
"step": 8850
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 0.30429431072210067,
|
| 1253 |
+
"grad_norm": 16.85060691833496,
|
| 1254 |
+
"learning_rate": 9.917467418344007e-06,
|
| 1255 |
+
"loss": 1.9175,
|
| 1256 |
+
"step": 8900
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 0.30600382932166303,
|
| 1260 |
+
"grad_norm": 15.724526405334473,
|
| 1261 |
+
"learning_rate": 9.91474613139935e-06,
|
| 1262 |
+
"loss": 1.9806,
|
| 1263 |
+
"step": 8950
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 0.3077133479212254,
|
| 1267 |
+
"grad_norm": 20.52348518371582,
|
| 1268 |
+
"learning_rate": 9.91198109126066e-06,
|
| 1269 |
+
"loss": 1.9061,
|
| 1270 |
+
"step": 9000
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 0.30942286652078776,
|
| 1274 |
+
"grad_norm": 20.329023361206055,
|
| 1275 |
+
"learning_rate": 9.90917232254352e-06,
|
| 1276 |
+
"loss": 1.9428,
|
| 1277 |
+
"step": 9050
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 0.31113238512035013,
|
| 1281 |
+
"grad_norm": 12.417845726013184,
|
| 1282 |
+
"learning_rate": 9.906319850252806e-06,
|
| 1283 |
+
"loss": 1.9322,
|
| 1284 |
+
"step": 9100
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 0.3128419037199125,
|
| 1288 |
+
"grad_norm": 18.483198165893555,
|
| 1289 |
+
"learning_rate": 9.903423699782455e-06,
|
| 1290 |
+
"loss": 1.9058,
|
| 1291 |
+
"step": 9150
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 0.31455142231947486,
|
| 1295 |
+
"grad_norm": 15.660554885864258,
|
| 1296 |
+
"learning_rate": 9.900483896915249e-06,
|
| 1297 |
+
"loss": 1.9042,
|
| 1298 |
+
"step": 9200
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 0.3162609409190372,
|
| 1302 |
+
"grad_norm": 14.889840126037598,
|
| 1303 |
+
"learning_rate": 9.89750046782259e-06,
|
| 1304 |
+
"loss": 1.8102,
|
| 1305 |
+
"step": 9250
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 0.31797045951859954,
|
| 1309 |
+
"grad_norm": 15.479453086853027,
|
| 1310 |
+
"learning_rate": 9.894473439064247e-06,
|
| 1311 |
+
"loss": 1.8487,
|
| 1312 |
+
"step": 9300
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 0.3196799781181619,
|
| 1316 |
+
"grad_norm": 15.109560012817383,
|
| 1317 |
+
"learning_rate": 9.891402837588142e-06,
|
| 1318 |
+
"loss": 1.9667,
|
| 1319 |
+
"step": 9350
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 0.32138949671772427,
|
| 1323 |
+
"grad_norm": 13.044564247131348,
|
| 1324 |
+
"learning_rate": 9.888288690730093e-06,
|
| 1325 |
+
"loss": 1.8555,
|
| 1326 |
+
"step": 9400
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 0.32309901531728663,
|
| 1330 |
+
"grad_norm": 26.768775939941406,
|
| 1331 |
+
"learning_rate": 9.885131026213585e-06,
|
| 1332 |
+
"loss": 1.9616,
|
| 1333 |
+
"step": 9450
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 0.324808533916849,
|
| 1337 |
+
"grad_norm": 16.932340621948242,
|
| 1338 |
+
"learning_rate": 9.881929872149509e-06,
|
| 1339 |
+
"loss": 1.8477,
|
| 1340 |
+
"step": 9500
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 0.32651805251641136,
|
| 1344 |
+
"grad_norm": 9.407527923583984,
|
| 1345 |
+
"learning_rate": 9.878685257035922e-06,
|
| 1346 |
+
"loss": 1.9094,
|
| 1347 |
+
"step": 9550
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 0.3282275711159737,
|
| 1351 |
+
"grad_norm": 14.848407745361328,
|
| 1352 |
+
"learning_rate": 9.875397209757793e-06,
|
| 1353 |
+
"loss": 1.9258,
|
| 1354 |
+
"step": 9600
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 0.3299370897155361,
|
| 1358 |
+
"grad_norm": 15.687681198120117,
|
| 1359 |
+
"learning_rate": 9.872065759586737e-06,
|
| 1360 |
+
"loss": 1.9935,
|
| 1361 |
+
"step": 9650
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 0.33164660831509846,
|
| 1365 |
+
"grad_norm": 18.635231018066406,
|
| 1366 |
+
"learning_rate": 9.868690936180763e-06,
|
| 1367 |
+
"loss": 1.9039,
|
| 1368 |
+
"step": 9700
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 0.3333561269146608,
|
| 1372 |
+
"grad_norm": 18.819971084594727,
|
| 1373 |
+
"learning_rate": 9.865272769584009e-06,
|
| 1374 |
+
"loss": 1.8751,
|
| 1375 |
+
"step": 9750
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 0.3350656455142232,
|
| 1379 |
+
"grad_norm": 13.116785049438477,
|
| 1380 |
+
"learning_rate": 9.86181129022647e-06,
|
| 1381 |
+
"loss": 1.8115,
|
| 1382 |
+
"step": 9800
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 0.33677516411378555,
|
| 1386 |
+
"grad_norm": 11.919672012329102,
|
| 1387 |
+
"learning_rate": 9.858306528923734e-06,
|
| 1388 |
+
"loss": 1.8357,
|
| 1389 |
+
"step": 9850
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 0.3384846827133479,
|
| 1393 |
+
"grad_norm": 20.79678726196289,
|
| 1394 |
+
"learning_rate": 9.854758516876695e-06,
|
| 1395 |
+
"loss": 1.806,
|
| 1396 |
+
"step": 9900
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 0.3401942013129103,
|
| 1400 |
+
"grad_norm": 14.870176315307617,
|
| 1401 |
+
"learning_rate": 9.851167285671295e-06,
|
| 1402 |
+
"loss": 1.919,
|
| 1403 |
+
"step": 9950
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 0.34190371991247265,
|
| 1407 |
+
"grad_norm": 16.700462341308594,
|
| 1408 |
+
"learning_rate": 9.847532867278225e-06,
|
| 1409 |
+
"loss": 1.828,
|
| 1410 |
+
"step": 10000
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 0.343613238512035,
|
| 1414 |
+
"grad_norm": 10.180593490600586,
|
| 1415 |
+
"learning_rate": 9.843855294052647e-06,
|
| 1416 |
+
"loss": 1.8198,
|
| 1417 |
+
"step": 10050
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 0.3453227571115974,
|
| 1421 |
+
"grad_norm": 11.027109146118164,
|
| 1422 |
+
"learning_rate": 9.840134598733906e-06,
|
| 1423 |
+
"loss": 1.9374,
|
| 1424 |
+
"step": 10100
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 0.34703227571115974,
|
| 1428 |
+
"grad_norm": 13.347614288330078,
|
| 1429 |
+
"learning_rate": 9.836370814445243e-06,
|
| 1430 |
+
"loss": 1.9592,
|
| 1431 |
+
"step": 10150
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 0.3487417943107221,
|
| 1435 |
+
"grad_norm": 17.22547149658203,
|
| 1436 |
+
"learning_rate": 9.83256397469349e-06,
|
| 1437 |
+
"loss": 1.8559,
|
| 1438 |
+
"step": 10200
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 0.3504513129102845,
|
| 1442 |
+
"grad_norm": 11.288195610046387,
|
| 1443 |
+
"learning_rate": 9.82871411336878e-06,
|
| 1444 |
+
"loss": 1.85,
|
| 1445 |
+
"step": 10250
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 0.35216083150984684,
|
| 1449 |
+
"grad_norm": 15.15438461303711,
|
| 1450 |
+
"learning_rate": 9.824821264744243e-06,
|
| 1451 |
+
"loss": 1.8604,
|
| 1452 |
+
"step": 10300
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 0.3538703501094092,
|
| 1456 |
+
"grad_norm": 15.401188850402832,
|
| 1457 |
+
"learning_rate": 9.8208854634757e-06,
|
| 1458 |
+
"loss": 2.0481,
|
| 1459 |
+
"step": 10350
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 0.35557986870897157,
|
| 1463 |
+
"grad_norm": 14.70609188079834,
|
| 1464 |
+
"learning_rate": 9.816906744601353e-06,
|
| 1465 |
+
"loss": 1.9255,
|
| 1466 |
+
"step": 10400
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 0.35728938730853393,
|
| 1470 |
+
"grad_norm": 16.757524490356445,
|
| 1471 |
+
"learning_rate": 9.812885143541477e-06,
|
| 1472 |
+
"loss": 1.8856,
|
| 1473 |
+
"step": 10450
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 0.3589989059080963,
|
| 1477 |
+
"grad_norm": 12.90262222290039,
|
| 1478 |
+
"learning_rate": 9.808820696098106e-06,
|
| 1479 |
+
"loss": 1.8734,
|
| 1480 |
+
"step": 10500
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 0.36070842450765866,
|
| 1484 |
+
"grad_norm": 18.712739944458008,
|
| 1485 |
+
"learning_rate": 9.804713438454704e-06,
|
| 1486 |
+
"loss": 1.9551,
|
| 1487 |
+
"step": 10550
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 0.36241794310722103,
|
| 1491 |
+
"grad_norm": 17.069164276123047,
|
| 1492 |
+
"learning_rate": 9.800563407175856e-06,
|
| 1493 |
+
"loss": 1.7486,
|
| 1494 |
+
"step": 10600
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 0.3641274617067834,
|
| 1498 |
+
"grad_norm": 22.363609313964844,
|
| 1499 |
+
"learning_rate": 9.796370639206932e-06,
|
| 1500 |
+
"loss": 1.9065,
|
| 1501 |
+
"step": 10650
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 0.36583698030634576,
|
| 1505 |
+
"grad_norm": 17.77787971496582,
|
| 1506 |
+
"learning_rate": 9.792135171873764e-06,
|
| 1507 |
+
"loss": 1.8192,
|
| 1508 |
+
"step": 10700
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 0.36754649890590807,
|
| 1512 |
+
"grad_norm": 16.25446891784668,
|
| 1513 |
+
"learning_rate": 9.787857042882314e-06,
|
| 1514 |
+
"loss": 1.7741,
|
| 1515 |
+
"step": 10750
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 0.36925601750547044,
|
| 1519 |
+
"grad_norm": 24.092191696166992,
|
| 1520 |
+
"learning_rate": 9.783536290318336e-06,
|
| 1521 |
+
"loss": 1.8663,
|
| 1522 |
+
"step": 10800
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 0.3709655361050328,
|
| 1526 |
+
"grad_norm": 11.511517524719238,
|
| 1527 |
+
"learning_rate": 9.779172952647035e-06,
|
| 1528 |
+
"loss": 1.9729,
|
| 1529 |
+
"step": 10850
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 0.37267505470459517,
|
| 1533 |
+
"grad_norm": 11.354775428771973,
|
| 1534 |
+
"learning_rate": 9.774767068712729e-06,
|
| 1535 |
+
"loss": 1.8034,
|
| 1536 |
+
"step": 10900
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 0.37438457330415753,
|
| 1540 |
+
"grad_norm": 16.31209945678711,
|
| 1541 |
+
"learning_rate": 9.770318677738501e-06,
|
| 1542 |
+
"loss": 1.8423,
|
| 1543 |
+
"step": 10950
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 0.3760940919037199,
|
| 1547 |
+
"grad_norm": 22.771448135375977,
|
| 1548 |
+
"learning_rate": 9.76582781932585e-06,
|
| 1549 |
+
"loss": 1.8439,
|
| 1550 |
+
"step": 11000
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 0.37780361050328226,
|
| 1554 |
+
"grad_norm": 13.11441421508789,
|
| 1555 |
+
"learning_rate": 9.761294533454338e-06,
|
| 1556 |
+
"loss": 1.6769,
|
| 1557 |
+
"step": 11050
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 0.3795131291028446,
|
| 1561 |
+
"grad_norm": 14.530037879943848,
|
| 1562 |
+
"learning_rate": 9.756718860481235e-06,
|
| 1563 |
+
"loss": 1.8893,
|
| 1564 |
+
"step": 11100
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 0.381222647702407,
|
| 1568 |
+
"grad_norm": 16.52512550354004,
|
| 1569 |
+
"learning_rate": 9.752100841141158e-06,
|
| 1570 |
+
"loss": 1.9421,
|
| 1571 |
+
"step": 11150
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 0.38293216630196936,
|
| 1575 |
+
"grad_norm": 13.35423469543457,
|
| 1576 |
+
"learning_rate": 9.747440516545715e-06,
|
| 1577 |
+
"loss": 1.8307,
|
| 1578 |
+
"step": 11200
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 0.3846416849015317,
|
| 1582 |
+
"grad_norm": 15.599985122680664,
|
| 1583 |
+
"learning_rate": 9.742737928183125e-06,
|
| 1584 |
+
"loss": 1.8177,
|
| 1585 |
+
"step": 11250
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 0.3863512035010941,
|
| 1589 |
+
"grad_norm": 17.42766571044922,
|
| 1590 |
+
"learning_rate": 9.737993117917865e-06,
|
| 1591 |
+
"loss": 1.799,
|
| 1592 |
+
"step": 11300
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 0.38806072210065645,
|
| 1596 |
+
"grad_norm": 24.196828842163086,
|
| 1597 |
+
"learning_rate": 9.733206127990285e-06,
|
| 1598 |
+
"loss": 1.9555,
|
| 1599 |
+
"step": 11350
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 0.3897702407002188,
|
| 1603 |
+
"grad_norm": 15.108709335327148,
|
| 1604 |
+
"learning_rate": 9.728377001016238e-06,
|
| 1605 |
+
"loss": 1.9783,
|
| 1606 |
+
"step": 11400
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 0.3914797592997812,
|
| 1610 |
+
"grad_norm": 10.54240608215332,
|
| 1611 |
+
"learning_rate": 9.7235057799867e-06,
|
| 1612 |
+
"loss": 1.7858,
|
| 1613 |
+
"step": 11450
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 0.39318927789934355,
|
| 1617 |
+
"grad_norm": 19.702739715576172,
|
| 1618 |
+
"learning_rate": 9.718592508267385e-06,
|
| 1619 |
+
"loss": 1.7884,
|
| 1620 |
+
"step": 11500
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 0.3948987964989059,
|
| 1624 |
+
"grad_norm": 13.241172790527344,
|
| 1625 |
+
"learning_rate": 9.713637229598363e-06,
|
| 1626 |
+
"loss": 1.9809,
|
| 1627 |
+
"step": 11550
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 0.3966083150984683,
|
| 1631 |
+
"grad_norm": 20.629985809326172,
|
| 1632 |
+
"learning_rate": 9.708639988093663e-06,
|
| 1633 |
+
"loss": 1.8333,
|
| 1634 |
+
"step": 11600
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 0.39831783369803064,
|
| 1638 |
+
"grad_norm": 20.3800048828125,
|
| 1639 |
+
"learning_rate": 9.703600828240891e-06,
|
| 1640 |
+
"loss": 1.7269,
|
| 1641 |
+
"step": 11650
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 0.400027352297593,
|
| 1645 |
+
"grad_norm": 14.835444450378418,
|
| 1646 |
+
"learning_rate": 9.698519794900825e-06,
|
| 1647 |
+
"loss": 1.767,
|
| 1648 |
+
"step": 11700
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 0.4017368708971554,
|
| 1652 |
+
"grad_norm": 15.657560348510742,
|
| 1653 |
+
"learning_rate": 9.693396933307019e-06,
|
| 1654 |
+
"loss": 1.8383,
|
| 1655 |
+
"step": 11750
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 0.40344638949671774,
|
| 1659 |
+
"grad_norm": 23.308496475219727,
|
| 1660 |
+
"learning_rate": 9.688232289065403e-06,
|
| 1661 |
+
"loss": 1.7441,
|
| 1662 |
+
"step": 11800
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 0.4051559080962801,
|
| 1666 |
+
"grad_norm": 14.822980880737305,
|
| 1667 |
+
"learning_rate": 9.683025908153868e-06,
|
| 1668 |
+
"loss": 1.7588,
|
| 1669 |
+
"step": 11850
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 0.40686542669584247,
|
| 1673 |
+
"grad_norm": 11.681976318359375,
|
| 1674 |
+
"learning_rate": 9.67777783692187e-06,
|
| 1675 |
+
"loss": 1.8072,
|
| 1676 |
+
"step": 11900
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 0.40857494529540483,
|
| 1680 |
+
"grad_norm": 12.76650619506836,
|
| 1681 |
+
"learning_rate": 9.672488122090007e-06,
|
| 1682 |
+
"loss": 1.9785,
|
| 1683 |
+
"step": 11950
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 0.4102844638949672,
|
| 1687 |
+
"grad_norm": 26.24738883972168,
|
| 1688 |
+
"learning_rate": 9.667156810749607e-06,
|
| 1689 |
+
"loss": 1.6886,
|
| 1690 |
+
"step": 12000
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 0.41199398249452956,
|
| 1694 |
+
"grad_norm": 25.363872528076172,
|
| 1695 |
+
"learning_rate": 9.661783950362306e-06,
|
| 1696 |
+
"loss": 1.837,
|
| 1697 |
+
"step": 12050
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 0.41370350109409193,
|
| 1701 |
+
"grad_norm": 16.34269142150879,
|
| 1702 |
+
"learning_rate": 9.656369588759628e-06,
|
| 1703 |
+
"loss": 1.7758,
|
| 1704 |
+
"step": 12100
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 0.41541301969365424,
|
| 1708 |
+
"grad_norm": 16.65306854248047,
|
| 1709 |
+
"learning_rate": 9.650913774142564e-06,
|
| 1710 |
+
"loss": 1.8119,
|
| 1711 |
+
"step": 12150
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 0.4171225382932166,
|
| 1715 |
+
"grad_norm": 22.357694625854492,
|
| 1716 |
+
"learning_rate": 9.645416555081129e-06,
|
| 1717 |
+
"loss": 1.7971,
|
| 1718 |
+
"step": 12200
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 0.41883205689277897,
|
| 1722 |
+
"grad_norm": 20.192245483398438,
|
| 1723 |
+
"learning_rate": 9.639877980513945e-06,
|
| 1724 |
+
"loss": 1.9192,
|
| 1725 |
+
"step": 12250
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 0.42054157549234134,
|
| 1729 |
+
"grad_norm": 11.32683277130127,
|
| 1730 |
+
"learning_rate": 9.634298099747797e-06,
|
| 1731 |
+
"loss": 1.8613,
|
| 1732 |
+
"step": 12300
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 0.4222510940919037,
|
| 1736 |
+
"grad_norm": 15.094401359558105,
|
| 1737 |
+
"learning_rate": 9.628676962457194e-06,
|
| 1738 |
+
"loss": 1.7207,
|
| 1739 |
+
"step": 12350
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 0.42396061269146607,
|
| 1743 |
+
"grad_norm": 13.93259334564209,
|
| 1744 |
+
"learning_rate": 9.62301461868393e-06,
|
| 1745 |
+
"loss": 1.7454,
|
| 1746 |
+
"step": 12400
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 0.42567013129102843,
|
| 1750 |
+
"grad_norm": 13.306478500366211,
|
| 1751 |
+
"learning_rate": 9.617311118836634e-06,
|
| 1752 |
+
"loss": 1.6855,
|
| 1753 |
+
"step": 12450
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 0.4273796498905908,
|
| 1757 |
+
"grad_norm": 16.63951873779297,
|
| 1758 |
+
"learning_rate": 9.61156651369033e-06,
|
| 1759 |
+
"loss": 1.7306,
|
| 1760 |
+
"step": 12500
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 0.42908916849015316,
|
| 1764 |
+
"grad_norm": 12.113211631774902,
|
| 1765 |
+
"learning_rate": 9.605780854385973e-06,
|
| 1766 |
+
"loss": 1.8765,
|
| 1767 |
+
"step": 12550
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 0.4307986870897155,
|
| 1771 |
+
"grad_norm": 16.40365219116211,
|
| 1772 |
+
"learning_rate": 9.599954192430004e-06,
|
| 1773 |
+
"loss": 1.8018,
|
| 1774 |
+
"step": 12600
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 0.4325082056892779,
|
| 1778 |
+
"grad_norm": 15.267725944519043,
|
| 1779 |
+
"learning_rate": 9.594086579693886e-06,
|
| 1780 |
+
"loss": 1.7398,
|
| 1781 |
+
"step": 12650
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 0.43421772428884026,
|
| 1785 |
+
"grad_norm": 16.651527404785156,
|
| 1786 |
+
"learning_rate": 9.588178068413642e-06,
|
| 1787 |
+
"loss": 1.8687,
|
| 1788 |
+
"step": 12700
|
| 1789 |
+
},
|
| 1790 |
+
{
|
| 1791 |
+
"epoch": 0.4359272428884026,
|
| 1792 |
+
"grad_norm": 11.101853370666504,
|
| 1793 |
+
"learning_rate": 9.582228711189392e-06,
|
| 1794 |
+
"loss": 1.7593,
|
| 1795 |
+
"step": 12750
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 0.437636761487965,
|
| 1799 |
+
"grad_norm": 10.085792541503906,
|
| 1800 |
+
"learning_rate": 9.576238560984887e-06,
|
| 1801 |
+
"loss": 1.8127,
|
| 1802 |
+
"step": 12800
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 0.43934628008752735,
|
| 1806 |
+
"grad_norm": 16.12364959716797,
|
| 1807 |
+
"learning_rate": 9.570207671127034e-06,
|
| 1808 |
+
"loss": 1.8309,
|
| 1809 |
+
"step": 12850
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 0.4410557986870897,
|
| 1813 |
+
"grad_norm": 9.267924308776855,
|
| 1814 |
+
"learning_rate": 9.564136095305419e-06,
|
| 1815 |
+
"loss": 1.7147,
|
| 1816 |
+
"step": 12900
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 0.4427653172866521,
|
| 1820 |
+
"grad_norm": 9.331021308898926,
|
| 1821 |
+
"learning_rate": 9.558023887571833e-06,
|
| 1822 |
+
"loss": 1.6771,
|
| 1823 |
+
"step": 12950
|
| 1824 |
+
},
|
| 1825 |
+
{
|
| 1826 |
+
"epoch": 0.44447483588621445,
|
| 1827 |
+
"grad_norm": 13.961063385009766,
|
| 1828 |
+
"learning_rate": 9.551871102339791e-06,
|
| 1829 |
+
"loss": 1.8983,
|
| 1830 |
+
"step": 13000
|
| 1831 |
+
},
|
| 1832 |
+
{
|
| 1833 |
+
"epoch": 0.4461843544857768,
|
| 1834 |
+
"grad_norm": 16.07474708557129,
|
| 1835 |
+
"learning_rate": 9.545677794384049e-06,
|
| 1836 |
+
"loss": 1.6636,
|
| 1837 |
+
"step": 13050
|
| 1838 |
+
},
|
| 1839 |
+
{
|
| 1840 |
+
"epoch": 0.4478938730853392,
|
| 1841 |
+
"grad_norm": 12.819247245788574,
|
| 1842 |
+
"learning_rate": 9.539444018840107e-06,
|
| 1843 |
+
"loss": 1.6612,
|
| 1844 |
+
"step": 13100
|
| 1845 |
+
},
|
| 1846 |
+
{
|
| 1847 |
+
"epoch": 0.44960339168490154,
|
| 1848 |
+
"grad_norm": 22.55895233154297,
|
| 1849 |
+
"learning_rate": 9.533169831203732e-06,
|
| 1850 |
+
"loss": 1.7092,
|
| 1851 |
+
"step": 13150
|
| 1852 |
+
},
|
| 1853 |
+
{
|
| 1854 |
+
"epoch": 0.4513129102844639,
|
| 1855 |
+
"grad_norm": 18.801158905029297,
|
| 1856 |
+
"learning_rate": 9.526855287330452e-06,
|
| 1857 |
+
"loss": 1.7982,
|
| 1858 |
+
"step": 13200
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 0.4530224288840263,
|
| 1862 |
+
"grad_norm": 15.08651065826416,
|
| 1863 |
+
"learning_rate": 9.520500443435066e-06,
|
| 1864 |
+
"loss": 1.7205,
|
| 1865 |
+
"step": 13250
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 0.45473194748358864,
|
| 1869 |
+
"grad_norm": 11.516852378845215,
|
| 1870 |
+
"learning_rate": 9.514105356091141e-06,
|
| 1871 |
+
"loss": 1.7198,
|
| 1872 |
+
"step": 13300
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 0.456441466083151,
|
| 1876 |
+
"grad_norm": 12.238503456115723,
|
| 1877 |
+
"learning_rate": 9.507670082230507e-06,
|
| 1878 |
+
"loss": 1.8331,
|
| 1879 |
+
"step": 13350
|
| 1880 |
+
},
|
| 1881 |
+
{
|
| 1882 |
+
"epoch": 0.45815098468271337,
|
| 1883 |
+
"grad_norm": 22.790138244628906,
|
| 1884 |
+
"learning_rate": 9.501194679142755e-06,
|
| 1885 |
+
"loss": 1.8477,
|
| 1886 |
+
"step": 13400
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 0.45986050328227573,
|
| 1890 |
+
"grad_norm": 19.264236450195312,
|
| 1891 |
+
"learning_rate": 9.49467920447472e-06,
|
| 1892 |
+
"loss": 1.8181,
|
| 1893 |
+
"step": 13450
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 0.4615700218818381,
|
| 1897 |
+
"grad_norm": 22.937997817993164,
|
| 1898 |
+
"learning_rate": 9.488123716229975e-06,
|
| 1899 |
+
"loss": 1.6858,
|
| 1900 |
+
"step": 13500
|
| 1901 |
+
},
|
| 1902 |
+
{
|
| 1903 |
+
"epoch": 0.46327954048140046,
|
| 1904 |
+
"grad_norm": 12.552448272705078,
|
| 1905 |
+
"learning_rate": 9.48152827276831e-06,
|
| 1906 |
+
"loss": 1.7433,
|
| 1907 |
+
"step": 13550
|
| 1908 |
+
},
|
| 1909 |
+
{
|
| 1910 |
+
"epoch": 0.4649890590809628,
|
| 1911 |
+
"grad_norm": 21.78132438659668,
|
| 1912 |
+
"learning_rate": 9.474892932805209e-06,
|
| 1913 |
+
"loss": 1.7088,
|
| 1914 |
+
"step": 13600
|
| 1915 |
+
},
|
| 1916 |
+
{
|
| 1917 |
+
"epoch": 0.46669857768052514,
|
| 1918 |
+
"grad_norm": 28.081968307495117,
|
| 1919 |
+
"learning_rate": 9.468217755411338e-06,
|
| 1920 |
+
"loss": 1.7497,
|
| 1921 |
+
"step": 13650
|
| 1922 |
+
},
|
| 1923 |
+
{
|
| 1924 |
+
"epoch": 0.4684080962800875,
|
| 1925 |
+
"grad_norm": 32.97182083129883,
|
| 1926 |
+
"learning_rate": 9.46150280001201e-06,
|
| 1927 |
+
"loss": 1.6363,
|
| 1928 |
+
"step": 13700
|
| 1929 |
+
},
|
| 1930 |
+
{
|
| 1931 |
+
"epoch": 0.47011761487964987,
|
| 1932 |
+
"grad_norm": 19.485626220703125,
|
| 1933 |
+
"learning_rate": 9.454748126386664e-06,
|
| 1934 |
+
"loss": 1.7147,
|
| 1935 |
+
"step": 13750
|
| 1936 |
+
},
|
| 1937 |
+
{
|
| 1938 |
+
"epoch": 0.47182713347921224,
|
| 1939 |
+
"grad_norm": 17.998210906982422,
|
| 1940 |
+
"learning_rate": 9.447953794668318e-06,
|
| 1941 |
+
"loss": 1.6463,
|
| 1942 |
+
"step": 13800
|
| 1943 |
+
},
|
| 1944 |
+
{
|
| 1945 |
+
"epoch": 0.4735366520787746,
|
| 1946 |
+
"grad_norm": 16.298301696777344,
|
| 1947 |
+
"learning_rate": 9.441119865343054e-06,
|
| 1948 |
+
"loss": 1.7713,
|
| 1949 |
+
"step": 13850
|
| 1950 |
+
},
|
| 1951 |
+
{
|
| 1952 |
+
"epoch": 0.47524617067833697,
|
| 1953 |
+
"grad_norm": 19.383695602416992,
|
| 1954 |
+
"learning_rate": 9.434246399249462e-06,
|
| 1955 |
+
"loss": 1.7253,
|
| 1956 |
+
"step": 13900
|
| 1957 |
+
},
|
| 1958 |
+
{
|
| 1959 |
+
"epoch": 0.47695568927789933,
|
| 1960 |
+
"grad_norm": 16.97551727294922,
|
| 1961 |
+
"learning_rate": 9.427333457578107e-06,
|
| 1962 |
+
"loss": 1.8148,
|
| 1963 |
+
"step": 13950
|
| 1964 |
+
},
|
| 1965 |
+
{
|
| 1966 |
+
"epoch": 0.4786652078774617,
|
| 1967 |
+
"grad_norm": 23.17900848388672,
|
| 1968 |
+
"learning_rate": 9.420381101870986e-06,
|
| 1969 |
+
"loss": 1.6749,
|
| 1970 |
+
"step": 14000
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"epoch": 0.48037472647702406,
|
| 1974 |
+
"grad_norm": 21.53219223022461,
|
| 1975 |
+
"learning_rate": 9.413389394020969e-06,
|
| 1976 |
+
"loss": 1.6393,
|
| 1977 |
+
"step": 14050
|
| 1978 |
+
},
|
| 1979 |
+
{
|
| 1980 |
+
"epoch": 0.4820842450765864,
|
| 1981 |
+
"grad_norm": 14.221118927001953,
|
| 1982 |
+
"learning_rate": 9.406358396271266e-06,
|
| 1983 |
+
"loss": 1.7049,
|
| 1984 |
+
"step": 14100
|
| 1985 |
+
},
|
| 1986 |
+
{
|
| 1987 |
+
"epoch": 0.4837937636761488,
|
| 1988 |
+
"grad_norm": 23.90619659423828,
|
| 1989 |
+
"learning_rate": 9.399288171214856e-06,
|
| 1990 |
+
"loss": 1.7358,
|
| 1991 |
+
"step": 14150
|
| 1992 |
+
},
|
| 1993 |
+
{
|
| 1994 |
+
"epoch": 0.48550328227571116,
|
| 1995 |
+
"grad_norm": 13.22474479675293,
|
| 1996 |
+
"learning_rate": 9.392178781793937e-06,
|
| 1997 |
+
"loss": 1.7955,
|
| 1998 |
+
"step": 14200
|
| 1999 |
+
},
|
| 2000 |
+
{
|
| 2001 |
+
"epoch": 0.4872128008752735,
|
| 2002 |
+
"grad_norm": 16.42545509338379,
|
| 2003 |
+
"learning_rate": 9.385030291299367e-06,
|
| 2004 |
+
"loss": 1.6907,
|
| 2005 |
+
"step": 14250
|
| 2006 |
+
},
|
| 2007 |
+
{
|
| 2008 |
+
"epoch": 0.4889223194748359,
|
| 2009 |
+
"grad_norm": 12.530423164367676,
|
| 2010 |
+
"learning_rate": 9.377842763370095e-06,
|
| 2011 |
+
"loss": 1.6234,
|
| 2012 |
+
"step": 14300
|
| 2013 |
+
},
|
| 2014 |
+
{
|
| 2015 |
+
"epoch": 0.49063183807439825,
|
| 2016 |
+
"grad_norm": 18.855403900146484,
|
| 2017 |
+
"learning_rate": 9.370616261992605e-06,
|
| 2018 |
+
"loss": 1.6885,
|
| 2019 |
+
"step": 14350
|
| 2020 |
+
},
|
| 2021 |
+
{
|
| 2022 |
+
"epoch": 0.4923413566739606,
|
| 2023 |
+
"grad_norm": 15.340056419372559,
|
| 2024 |
+
"learning_rate": 9.363350851500332e-06,
|
| 2025 |
+
"loss": 1.6178,
|
| 2026 |
+
"step": 14400
|
| 2027 |
+
},
|
| 2028 |
+
{
|
| 2029 |
+
"epoch": 0.494050875273523,
|
| 2030 |
+
"grad_norm": 17.388063430786133,
|
| 2031 |
+
"learning_rate": 9.356046596573103e-06,
|
| 2032 |
+
"loss": 1.7558,
|
| 2033 |
+
"step": 14450
|
| 2034 |
+
},
|
| 2035 |
+
{
|
| 2036 |
+
"epoch": 0.49576039387308535,
|
| 2037 |
+
"grad_norm": 21.704608917236328,
|
| 2038 |
+
"learning_rate": 9.34870356223655e-06,
|
| 2039 |
+
"loss": 1.6844,
|
| 2040 |
+
"step": 14500
|
| 2041 |
+
},
|
| 2042 |
+
{
|
| 2043 |
+
"epoch": 0.4974699124726477,
|
| 2044 |
+
"grad_norm": 13.894968032836914,
|
| 2045 |
+
"learning_rate": 9.341321813861537e-06,
|
| 2046 |
+
"loss": 1.8849,
|
| 2047 |
+
"step": 14550
|
| 2048 |
+
},
|
| 2049 |
+
{
|
| 2050 |
+
"epoch": 0.4991794310722101,
|
| 2051 |
+
"grad_norm": 13.946575164794922,
|
| 2052 |
+
"learning_rate": 9.33390141716358e-06,
|
| 2053 |
+
"loss": 1.7619,
|
| 2054 |
+
"step": 14600
|
| 2055 |
+
},
|
| 2056 |
+
{
|
| 2057 |
+
"epoch": 0.5008889496717724,
|
| 2058 |
+
"grad_norm": 29.28716468811035,
|
| 2059 |
+
"learning_rate": 9.326442438202257e-06,
|
| 2060 |
+
"loss": 1.79,
|
| 2061 |
+
"step": 14650
|
| 2062 |
+
},
|
| 2063 |
+
{
|
| 2064 |
+
"epoch": 0.5025984682713348,
|
| 2065 |
+
"grad_norm": 13.3435697555542,
|
| 2066 |
+
"learning_rate": 9.318944943380623e-06,
|
| 2067 |
+
"loss": 1.6853,
|
| 2068 |
+
"step": 14700
|
| 2069 |
+
},
|
| 2070 |
+
{
|
| 2071 |
+
"epoch": 0.5043079868708972,
|
| 2072 |
+
"grad_norm": 13.013406753540039,
|
| 2073 |
+
"learning_rate": 9.311408999444614e-06,
|
| 2074 |
+
"loss": 1.6466,
|
| 2075 |
+
"step": 14750
|
| 2076 |
+
},
|
| 2077 |
+
{
|
| 2078 |
+
"epoch": 0.5060175054704595,
|
| 2079 |
+
"grad_norm": 9.254395484924316,
|
| 2080 |
+
"learning_rate": 9.303834673482463e-06,
|
| 2081 |
+
"loss": 1.69,
|
| 2082 |
+
"step": 14800
|
| 2083 |
+
},
|
| 2084 |
+
{
|
| 2085 |
+
"epoch": 0.5077270240700219,
|
| 2086 |
+
"grad_norm": 12.798242568969727,
|
| 2087 |
+
"learning_rate": 9.296222032924092e-06,
|
| 2088 |
+
"loss": 1.5623,
|
| 2089 |
+
"step": 14850
|
| 2090 |
+
},
|
| 2091 |
+
{
|
| 2092 |
+
"epoch": 0.5094365426695843,
|
| 2093 |
+
"grad_norm": 12.265205383300781,
|
| 2094 |
+
"learning_rate": 9.288571145540516e-06,
|
| 2095 |
+
"loss": 1.6299,
|
| 2096 |
+
"step": 14900
|
| 2097 |
+
},
|
| 2098 |
+
{
|
| 2099 |
+
"epoch": 0.5111460612691466,
|
| 2100 |
+
"grad_norm": 15.084614753723145,
|
| 2101 |
+
"learning_rate": 9.280882079443242e-06,
|
| 2102 |
+
"loss": 1.67,
|
| 2103 |
+
"step": 14950
|
| 2104 |
+
},
|
| 2105 |
+
{
|
| 2106 |
+
"epoch": 0.512855579868709,
|
| 2107 |
+
"grad_norm": 12.170019149780273,
|
| 2108 |
+
"learning_rate": 9.273154903083659e-06,
|
| 2109 |
+
"loss": 1.6242,
|
| 2110 |
+
"step": 15000
|
| 2111 |
+
},
|
| 2112 |
+
{
|
| 2113 |
+
"epoch": 0.5145650984682714,
|
| 2114 |
+
"grad_norm": 11.223395347595215,
|
| 2115 |
+
"learning_rate": 9.26538968525243e-06,
|
| 2116 |
+
"loss": 1.6639,
|
| 2117 |
+
"step": 15050
|
| 2118 |
+
},
|
| 2119 |
+
{
|
| 2120 |
+
"epoch": 0.5162746170678337,
|
| 2121 |
+
"grad_norm": 11.404626846313477,
|
| 2122 |
+
"learning_rate": 9.257586495078882e-06,
|
| 2123 |
+
"loss": 1.695,
|
| 2124 |
+
"step": 15100
|
| 2125 |
+
},
|
| 2126 |
+
{
|
| 2127 |
+
"epoch": 0.5179841356673961,
|
| 2128 |
+
"grad_norm": 21.49475860595703,
|
| 2129 |
+
"learning_rate": 9.249745402030384e-06,
|
| 2130 |
+
"loss": 1.6992,
|
| 2131 |
+
"step": 15150
|
| 2132 |
+
},
|
| 2133 |
+
{
|
| 2134 |
+
"epoch": 0.5196936542669585,
|
| 2135 |
+
"grad_norm": 12.955080032348633,
|
| 2136 |
+
"learning_rate": 9.241866475911734e-06,
|
| 2137 |
+
"loss": 1.6496,
|
| 2138 |
+
"step": 15200
|
| 2139 |
+
},
|
| 2140 |
+
{
|
| 2141 |
+
"epoch": 0.5214031728665208,
|
| 2142 |
+
"grad_norm": 16.4161434173584,
|
| 2143 |
+
"learning_rate": 9.23394978686454e-06,
|
| 2144 |
+
"loss": 1.6786,
|
| 2145 |
+
"step": 15250
|
| 2146 |
+
},
|
| 2147 |
+
{
|
| 2148 |
+
"epoch": 0.5231126914660832,
|
| 2149 |
+
"grad_norm": 15.082755088806152,
|
| 2150 |
+
"learning_rate": 9.225995405366588e-06,
|
| 2151 |
+
"loss": 1.697,
|
| 2152 |
+
"step": 15300
|
| 2153 |
+
},
|
| 2154 |
+
{
|
| 2155 |
+
"epoch": 0.5248222100656456,
|
| 2156 |
+
"grad_norm": 18.073482513427734,
|
| 2157 |
+
"learning_rate": 9.21800340223122e-06,
|
| 2158 |
+
"loss": 1.6815,
|
| 2159 |
+
"step": 15350
|
| 2160 |
+
},
|
| 2161 |
+
{
|
| 2162 |
+
"epoch": 0.5265317286652079,
|
| 2163 |
+
"grad_norm": 16.651689529418945,
|
| 2164 |
+
"learning_rate": 9.209973848606702e-06,
|
| 2165 |
+
"loss": 1.6888,
|
| 2166 |
+
"step": 15400
|
| 2167 |
+
},
|
| 2168 |
+
{
|
| 2169 |
+
"epoch": 0.5282412472647703,
|
| 2170 |
+
"grad_norm": 20.97808074951172,
|
| 2171 |
+
"learning_rate": 9.201906815975589e-06,
|
| 2172 |
+
"loss": 1.8388,
|
| 2173 |
+
"step": 15450
|
| 2174 |
+
},
|
| 2175 |
+
{
|
| 2176 |
+
"epoch": 0.5299507658643327,
|
| 2177 |
+
"grad_norm": 14.572290420532227,
|
| 2178 |
+
"learning_rate": 9.193802376154093e-06,
|
| 2179 |
+
"loss": 1.6681,
|
| 2180 |
+
"step": 15500
|
| 2181 |
+
},
|
| 2182 |
+
{
|
| 2183 |
+
"epoch": 0.531660284463895,
|
| 2184 |
+
"grad_norm": 13.417821884155273,
|
| 2185 |
+
"learning_rate": 9.185660601291438e-06,
|
| 2186 |
+
"loss": 1.7012,
|
| 2187 |
+
"step": 15550
|
| 2188 |
+
},
|
| 2189 |
+
{
|
| 2190 |
+
"epoch": 0.5333698030634574,
|
| 2191 |
+
"grad_norm": 11.648053169250488,
|
| 2192 |
+
"learning_rate": 9.177481563869226e-06,
|
| 2193 |
+
"loss": 1.5878,
|
| 2194 |
+
"step": 15600
|
| 2195 |
+
},
|
| 2196 |
+
{
|
| 2197 |
+
"epoch": 0.5350793216630197,
|
| 2198 |
+
"grad_norm": 14.75922679901123,
|
| 2199 |
+
"learning_rate": 9.169265336700778e-06,
|
| 2200 |
+
"loss": 1.7528,
|
| 2201 |
+
"step": 15650
|
| 2202 |
+
},
|
| 2203 |
+
{
|
| 2204 |
+
"epoch": 0.5367888402625821,
|
| 2205 |
+
"grad_norm": 19.131927490234375,
|
| 2206 |
+
"learning_rate": 9.161011992930504e-06,
|
| 2207 |
+
"loss": 1.726,
|
| 2208 |
+
"step": 15700
|
| 2209 |
+
},
|
| 2210 |
+
{
|
| 2211 |
+
"epoch": 0.5384983588621444,
|
| 2212 |
+
"grad_norm": 13.348299026489258,
|
| 2213 |
+
"learning_rate": 9.152721606033234e-06,
|
| 2214 |
+
"loss": 1.7196,
|
| 2215 |
+
"step": 15750
|
| 2216 |
+
},
|
| 2217 |
+
{
|
| 2218 |
+
"epoch": 0.5402078774617067,
|
| 2219 |
+
"grad_norm": 15.433631896972656,
|
| 2220 |
+
"learning_rate": 9.144394249813576e-06,
|
| 2221 |
+
"loss": 1.6885,
|
| 2222 |
+
"step": 15800
|
| 2223 |
+
},
|
| 2224 |
+
{
|
| 2225 |
+
"epoch": 0.5419173960612691,
|
| 2226 |
+
"grad_norm": 15.60571002960205,
|
| 2227 |
+
"learning_rate": 9.136029998405253e-06,
|
| 2228 |
+
"loss": 1.658,
|
| 2229 |
+
"step": 15850
|
| 2230 |
+
},
|
| 2231 |
+
{
|
| 2232 |
+
"epoch": 0.5436269146608315,
|
| 2233 |
+
"grad_norm": 9.433021545410156,
|
| 2234 |
+
"learning_rate": 9.127628926270446e-06,
|
| 2235 |
+
"loss": 1.6522,
|
| 2236 |
+
"step": 15900
|
| 2237 |
+
},
|
| 2238 |
+
{
|
| 2239 |
+
"epoch": 0.5453364332603938,
|
| 2240 |
+
"grad_norm": 18.910202026367188,
|
| 2241 |
+
"learning_rate": 9.119191108199131e-06,
|
| 2242 |
+
"loss": 1.6854,
|
| 2243 |
+
"step": 15950
|
| 2244 |
+
},
|
| 2245 |
+
{
|
| 2246 |
+
"epoch": 0.5470459518599562,
|
| 2247 |
+
"grad_norm": 20.025436401367188,
|
| 2248 |
+
"learning_rate": 9.110716619308407e-06,
|
| 2249 |
+
"loss": 1.7808,
|
| 2250 |
+
"step": 16000
|
| 2251 |
+
},
|
| 2252 |
+
{
|
| 2253 |
+
"epoch": 0.5487554704595186,
|
| 2254 |
+
"grad_norm": 12.032959938049316,
|
| 2255 |
+
"learning_rate": 9.102205535041842e-06,
|
| 2256 |
+
"loss": 1.495,
|
| 2257 |
+
"step": 16050
|
| 2258 |
+
},
|
| 2259 |
+
{
|
| 2260 |
+
"epoch": 0.5504649890590809,
|
| 2261 |
+
"grad_norm": 12.012452125549316,
|
| 2262 |
+
"learning_rate": 9.093657931168782e-06,
|
| 2263 |
+
"loss": 1.7121,
|
| 2264 |
+
"step": 16100
|
| 2265 |
+
},
|
| 2266 |
+
{
|
| 2267 |
+
"epoch": 0.5521745076586433,
|
| 2268 |
+
"grad_norm": 17.101211547851562,
|
| 2269 |
+
"learning_rate": 9.085073883783694e-06,
|
| 2270 |
+
"loss": 1.744,
|
| 2271 |
+
"step": 16150
|
| 2272 |
+
},
|
| 2273 |
+
{
|
| 2274 |
+
"epoch": 0.5538840262582057,
|
| 2275 |
+
"grad_norm": 20.24106216430664,
|
| 2276 |
+
"learning_rate": 9.076453469305476e-06,
|
| 2277 |
+
"loss": 1.5711,
|
| 2278 |
+
"step": 16200
|
| 2279 |
+
},
|
| 2280 |
+
{
|
| 2281 |
+
"epoch": 0.555593544857768,
|
| 2282 |
+
"grad_norm": 14.256794929504395,
|
| 2283 |
+
"learning_rate": 9.067796764476782e-06,
|
| 2284 |
+
"loss": 1.5904,
|
| 2285 |
+
"step": 16250
|
| 2286 |
+
},
|
| 2287 |
+
{
|
| 2288 |
+
"epoch": 0.5573030634573304,
|
| 2289 |
+
"grad_norm": 13.574074745178223,
|
| 2290 |
+
"learning_rate": 9.059103846363342e-06,
|
| 2291 |
+
"loss": 1.6485,
|
| 2292 |
+
"step": 16300
|
| 2293 |
+
},
|
| 2294 |
+
{
|
| 2295 |
+
"epoch": 0.5590125820568927,
|
| 2296 |
+
"grad_norm": 17.243623733520508,
|
| 2297 |
+
"learning_rate": 9.050374792353265e-06,
|
| 2298 |
+
"loss": 1.6143,
|
| 2299 |
+
"step": 16350
|
| 2300 |
+
},
|
| 2301 |
+
{
|
| 2302 |
+
"epoch": 0.5607221006564551,
|
| 2303 |
+
"grad_norm": 18.815284729003906,
|
| 2304 |
+
"learning_rate": 9.041609680156367e-06,
|
| 2305 |
+
"loss": 1.6382,
|
| 2306 |
+
"step": 16400
|
| 2307 |
+
},
|
| 2308 |
+
{
|
| 2309 |
+
"epoch": 0.5624316192560175,
|
| 2310 |
+
"grad_norm": 18.413740158081055,
|
| 2311 |
+
"learning_rate": 9.032808587803465e-06,
|
| 2312 |
+
"loss": 1.7215,
|
| 2313 |
+
"step": 16450
|
| 2314 |
+
},
|
| 2315 |
+
{
|
| 2316 |
+
"epoch": 0.5641411378555798,
|
| 2317 |
+
"grad_norm": 17.65328025817871,
|
| 2318 |
+
"learning_rate": 9.023971593645683e-06,
|
| 2319 |
+
"loss": 1.6278,
|
| 2320 |
+
"step": 16500
|
| 2321 |
+
},
|
| 2322 |
+
{
|
| 2323 |
+
"epoch": 0.5658506564551422,
|
| 2324 |
+
"grad_norm": 18.530925750732422,
|
| 2325 |
+
"learning_rate": 9.015098776353763e-06,
|
| 2326 |
+
"loss": 1.7608,
|
| 2327 |
+
"step": 16550
|
| 2328 |
+
},
|
| 2329 |
+
{
|
| 2330 |
+
"epoch": 0.5675601750547046,
|
| 2331 |
+
"grad_norm": 15.51563549041748,
|
| 2332 |
+
"learning_rate": 9.006190214917363e-06,
|
| 2333 |
+
"loss": 1.6316,
|
| 2334 |
+
"step": 16600
|
| 2335 |
+
},
|
| 2336 |
+
{
|
| 2337 |
+
"epoch": 0.5692696936542669,
|
| 2338 |
+
"grad_norm": 15.27429485321045,
|
| 2339 |
+
"learning_rate": 8.997245988644341e-06,
|
| 2340 |
+
"loss": 1.4942,
|
| 2341 |
+
"step": 16650
|
| 2342 |
+
},
|
| 2343 |
+
{
|
| 2344 |
+
"epoch": 0.5709792122538293,
|
| 2345 |
+
"grad_norm": 10.738313674926758,
|
| 2346 |
+
"learning_rate": 8.988266177160068e-06,
|
| 2347 |
+
"loss": 1.5061,
|
| 2348 |
+
"step": 16700
|
| 2349 |
+
},
|
| 2350 |
+
{
|
| 2351 |
+
"epoch": 0.5726887308533917,
|
| 2352 |
+
"grad_norm": 24.891115188598633,
|
| 2353 |
+
"learning_rate": 8.979250860406707e-06,
|
| 2354 |
+
"loss": 1.571,
|
| 2355 |
+
"step": 16750
|
| 2356 |
+
},
|
| 2357 |
+
{
|
| 2358 |
+
"epoch": 0.574398249452954,
|
| 2359 |
+
"grad_norm": 19.412364959716797,
|
| 2360 |
+
"learning_rate": 8.9702001186425e-06,
|
| 2361 |
+
"loss": 1.7011,
|
| 2362 |
+
"step": 16800
|
| 2363 |
+
},
|
| 2364 |
+
{
|
| 2365 |
+
"epoch": 0.5761077680525164,
|
| 2366 |
+
"grad_norm": 16.005048751831055,
|
| 2367 |
+
"learning_rate": 8.961114032441067e-06,
|
| 2368 |
+
"loss": 1.6718,
|
| 2369 |
+
"step": 16850
|
| 2370 |
+
},
|
| 2371 |
+
{
|
| 2372 |
+
"epoch": 0.5778172866520788,
|
| 2373 |
+
"grad_norm": 16.86431312561035,
|
| 2374 |
+
"learning_rate": 8.951992682690671e-06,
|
| 2375 |
+
"loss": 1.6379,
|
| 2376 |
+
"step": 16900
|
| 2377 |
+
},
|
| 2378 |
+
{
|
| 2379 |
+
"epoch": 0.5795268052516411,
|
| 2380 |
+
"grad_norm": 12.988998413085938,
|
| 2381 |
+
"learning_rate": 8.942836150593509e-06,
|
| 2382 |
+
"loss": 1.58,
|
| 2383 |
+
"step": 16950
|
| 2384 |
+
},
|
| 2385 |
+
{
|
| 2386 |
+
"epoch": 0.5812363238512035,
|
| 2387 |
+
"grad_norm": 20.16266632080078,
|
| 2388 |
+
"learning_rate": 8.933644517664988e-06,
|
| 2389 |
+
"loss": 1.5307,
|
| 2390 |
+
"step": 17000
|
| 2391 |
+
},
|
| 2392 |
+
{
|
| 2393 |
+
"epoch": 0.5829458424507659,
|
| 2394 |
+
"grad_norm": 14.7272367477417,
|
| 2395 |
+
"learning_rate": 8.924417865732996e-06,
|
| 2396 |
+
"loss": 1.5679,
|
| 2397 |
+
"step": 17050
|
| 2398 |
+
},
|
| 2399 |
+
{
|
| 2400 |
+
"epoch": 0.5846553610503282,
|
| 2401 |
+
"grad_norm": 10.363537788391113,
|
| 2402 |
+
"learning_rate": 8.915156276937175e-06,
|
| 2403 |
+
"loss": 1.554,
|
| 2404 |
+
"step": 17100
|
| 2405 |
+
},
|
| 2406 |
+
{
|
| 2407 |
+
"epoch": 0.5863648796498906,
|
| 2408 |
+
"grad_norm": 14.92949104309082,
|
| 2409 |
+
"learning_rate": 8.905859833728194e-06,
|
| 2410 |
+
"loss": 1.7207,
|
| 2411 |
+
"step": 17150
|
| 2412 |
+
},
|
| 2413 |
+
{
|
| 2414 |
+
"epoch": 0.588074398249453,
|
| 2415 |
+
"grad_norm": 8.86705493927002,
|
| 2416 |
+
"learning_rate": 8.896528618867005e-06,
|
| 2417 |
+
"loss": 1.6822,
|
| 2418 |
+
"step": 17200
|
| 2419 |
+
},
|
| 2420 |
+
{
|
| 2421 |
+
"epoch": 0.5897839168490153,
|
| 2422 |
+
"grad_norm": 16.97774887084961,
|
| 2423 |
+
"learning_rate": 8.887162715424117e-06,
|
| 2424 |
+
"loss": 1.6769,
|
| 2425 |
+
"step": 17250
|
| 2426 |
+
},
|
| 2427 |
+
{
|
| 2428 |
+
"epoch": 0.5914934354485777,
|
| 2429 |
+
"grad_norm": 19.52352523803711,
|
| 2430 |
+
"learning_rate": 8.877762206778848e-06,
|
| 2431 |
+
"loss": 1.609,
|
| 2432 |
+
"step": 17300
|
| 2433 |
+
},
|
| 2434 |
+
{
|
| 2435 |
+
"epoch": 0.59320295404814,
|
| 2436 |
+
"grad_norm": 16.821683883666992,
|
| 2437 |
+
"learning_rate": 8.868327176618592e-06,
|
| 2438 |
+
"loss": 1.547,
|
| 2439 |
+
"step": 17350
|
| 2440 |
+
},
|
| 2441 |
+
{
|
| 2442 |
+
"epoch": 0.5949124726477024,
|
| 2443 |
+
"grad_norm": 14.35383129119873,
|
| 2444 |
+
"learning_rate": 8.858857708938062e-06,
|
| 2445 |
+
"loss": 1.6044,
|
| 2446 |
+
"step": 17400
|
| 2447 |
+
},
|
| 2448 |
+
{
|
| 2449 |
+
"epoch": 0.5966219912472648,
|
| 2450 |
+
"grad_norm": 16.436189651489258,
|
| 2451 |
+
"learning_rate": 8.849353888038553e-06,
|
| 2452 |
+
"loss": 1.7153,
|
| 2453 |
+
"step": 17450
|
| 2454 |
+
},
|
| 2455 |
+
{
|
| 2456 |
+
"epoch": 0.5983315098468271,
|
| 2457 |
+
"grad_norm": 11.066549301147461,
|
| 2458 |
+
"learning_rate": 8.839815798527184e-06,
|
| 2459 |
+
"loss": 1.5481,
|
| 2460 |
+
"step": 17500
|
| 2461 |
+
},
|
| 2462 |
+
{
|
| 2463 |
+
"epoch": 0.6000410284463895,
|
| 2464 |
+
"grad_norm": 10.95409107208252,
|
| 2465 |
+
"learning_rate": 8.830243525316154e-06,
|
| 2466 |
+
"loss": 1.5702,
|
| 2467 |
+
"step": 17550
|
| 2468 |
+
},
|
| 2469 |
+
{
|
| 2470 |
+
"epoch": 0.6017505470459519,
|
| 2471 |
+
"grad_norm": 13.464219093322754,
|
| 2472 |
+
"learning_rate": 8.82063715362197e-06,
|
| 2473 |
+
"loss": 1.6198,
|
| 2474 |
+
"step": 17600
|
| 2475 |
+
},
|
| 2476 |
+
{
|
| 2477 |
+
"epoch": 0.6034600656455142,
|
| 2478 |
+
"grad_norm": 17.773595809936523,
|
| 2479 |
+
"learning_rate": 8.810996768964709e-06,
|
| 2480 |
+
"loss": 1.6901,
|
| 2481 |
+
"step": 17650
|
| 2482 |
+
},
|
| 2483 |
+
{
|
| 2484 |
+
"epoch": 0.6051695842450766,
|
| 2485 |
+
"grad_norm": 12.184327125549316,
|
| 2486 |
+
"learning_rate": 8.801322457167241e-06,
|
| 2487 |
+
"loss": 1.636,
|
| 2488 |
+
"step": 17700
|
| 2489 |
+
},
|
| 2490 |
+
{
|
| 2491 |
+
"epoch": 0.606879102844639,
|
| 2492 |
+
"grad_norm": 10.474329948425293,
|
| 2493 |
+
"learning_rate": 8.791614304354466e-06,
|
| 2494 |
+
"loss": 1.5326,
|
| 2495 |
+
"step": 17750
|
| 2496 |
+
},
|
| 2497 |
+
{
|
| 2498 |
+
"epoch": 0.6085886214442013,
|
| 2499 |
+
"grad_norm": 19.226255416870117,
|
| 2500 |
+
"learning_rate": 8.781872396952561e-06,
|
| 2501 |
+
"loss": 1.7762,
|
| 2502 |
+
"step": 17800
|
| 2503 |
+
},
|
| 2504 |
+
{
|
| 2505 |
+
"epoch": 0.6102981400437637,
|
| 2506 |
+
"grad_norm": 15.047229766845703,
|
| 2507 |
+
"learning_rate": 8.772096821688194e-06,
|
| 2508 |
+
"loss": 1.5175,
|
| 2509 |
+
"step": 17850
|
| 2510 |
+
},
|
| 2511 |
+
{
|
| 2512 |
+
"epoch": 0.6120076586433261,
|
| 2513 |
+
"grad_norm": 17.31934356689453,
|
| 2514 |
+
"learning_rate": 8.762287665587763e-06,
|
| 2515 |
+
"loss": 1.5603,
|
| 2516 |
+
"step": 17900
|
| 2517 |
+
},
|
| 2518 |
+
{
|
| 2519 |
+
"epoch": 0.6137171772428884,
|
| 2520 |
+
"grad_norm": 13.261528968811035,
|
| 2521 |
+
"learning_rate": 8.75244501597661e-06,
|
| 2522 |
+
"loss": 1.6176,
|
| 2523 |
+
"step": 17950
|
| 2524 |
+
},
|
| 2525 |
+
{
|
| 2526 |
+
"epoch": 0.6154266958424508,
|
| 2527 |
+
"grad_norm": 15.576045989990234,
|
| 2528 |
+
"learning_rate": 8.742568960478258e-06,
|
| 2529 |
+
"loss": 1.4301,
|
| 2530 |
+
"step": 18000
|
| 2531 |
+
},
|
| 2532 |
+
{
|
| 2533 |
+
"epoch": 0.6171362144420132,
|
| 2534 |
+
"grad_norm": 18.78702735900879,
|
| 2535 |
+
"learning_rate": 8.73265958701362e-06,
|
| 2536 |
+
"loss": 1.5584,
|
| 2537 |
+
"step": 18050
|
| 2538 |
+
},
|
| 2539 |
+
{
|
| 2540 |
+
"epoch": 0.6188457330415755,
|
| 2541 |
+
"grad_norm": 11.820853233337402,
|
| 2542 |
+
"learning_rate": 8.722716983800226e-06,
|
| 2543 |
+
"loss": 1.5778,
|
| 2544 |
+
"step": 18100
|
| 2545 |
+
},
|
| 2546 |
+
{
|
| 2547 |
+
"epoch": 0.6205552516411379,
|
| 2548 |
+
"grad_norm": 14.161349296569824,
|
| 2549 |
+
"learning_rate": 8.712741239351419e-06,
|
| 2550 |
+
"loss": 1.5241,
|
| 2551 |
+
"step": 18150
|
| 2552 |
+
},
|
| 2553 |
+
{
|
| 2554 |
+
"epoch": 0.6222647702407003,
|
| 2555 |
+
"grad_norm": 13.215728759765625,
|
| 2556 |
+
"learning_rate": 8.702732442475591e-06,
|
| 2557 |
+
"loss": 1.7183,
|
| 2558 |
+
"step": 18200
|
| 2559 |
+
},
|
| 2560 |
+
{
|
| 2561 |
+
"epoch": 0.6239742888402626,
|
| 2562 |
+
"grad_norm": 14.183741569519043,
|
| 2563 |
+
"learning_rate": 8.69269068227538e-06,
|
| 2564 |
+
"loss": 1.6953,
|
| 2565 |
+
"step": 18250
|
| 2566 |
+
},
|
| 2567 |
+
{
|
| 2568 |
+
"epoch": 0.625683807439825,
|
| 2569 |
+
"grad_norm": 18.153400421142578,
|
| 2570 |
+
"learning_rate": 8.68261604814687e-06,
|
| 2571 |
+
"loss": 1.5347,
|
| 2572 |
+
"step": 18300
|
| 2573 |
+
},
|
| 2574 |
+
{
|
| 2575 |
+
"epoch": 0.6273933260393874,
|
| 2576 |
+
"grad_norm": 16.9625186920166,
|
| 2577 |
+
"learning_rate": 8.672508629778809e-06,
|
| 2578 |
+
"loss": 1.6878,
|
| 2579 |
+
"step": 18350
|
| 2580 |
+
},
|
| 2581 |
+
{
|
| 2582 |
+
"epoch": 0.6291028446389497,
|
| 2583 |
+
"grad_norm": 24.220521926879883,
|
| 2584 |
+
"learning_rate": 8.662368517151806e-06,
|
| 2585 |
+
"loss": 1.5002,
|
| 2586 |
+
"step": 18400
|
| 2587 |
+
},
|
| 2588 |
+
{
|
| 2589 |
+
"epoch": 0.6308123632385121,
|
| 2590 |
+
"grad_norm": 17.07057762145996,
|
| 2591 |
+
"learning_rate": 8.652195800537525e-06,
|
| 2592 |
+
"loss": 1.5457,
|
| 2593 |
+
"step": 18450
|
| 2594 |
+
},
|
| 2595 |
+
{
|
| 2596 |
+
"epoch": 0.6325218818380745,
|
| 2597 |
+
"grad_norm": 13.600142478942871,
|
| 2598 |
+
"learning_rate": 8.641990570497882e-06,
|
| 2599 |
+
"loss": 1.5162,
|
| 2600 |
+
"step": 18500
|
| 2601 |
+
},
|
| 2602 |
+
{
|
| 2603 |
+
"epoch": 0.6342314004376368,
|
| 2604 |
+
"grad_norm": 19.408395767211914,
|
| 2605 |
+
"learning_rate": 8.63175291788425e-06,
|
| 2606 |
+
"loss": 1.6628,
|
| 2607 |
+
"step": 18550
|
| 2608 |
+
},
|
| 2609 |
+
{
|
| 2610 |
+
"epoch": 0.6359409190371991,
|
| 2611 |
+
"grad_norm": 14.208587646484375,
|
| 2612 |
+
"learning_rate": 8.621482933836634e-06,
|
| 2613 |
+
"loss": 1.6041,
|
| 2614 |
+
"step": 18600
|
| 2615 |
+
},
|
| 2616 |
+
{
|
| 2617 |
+
"epoch": 0.6376504376367614,
|
| 2618 |
+
"grad_norm": 12.20449161529541,
|
| 2619 |
+
"learning_rate": 8.611180709782871e-06,
|
| 2620 |
+
"loss": 1.6295,
|
| 2621 |
+
"step": 18650
|
| 2622 |
+
},
|
| 2623 |
+
{
|
| 2624 |
+
"epoch": 0.6393599562363238,
|
| 2625 |
+
"grad_norm": 25.629989624023438,
|
| 2626 |
+
"learning_rate": 8.60084633743781e-06,
|
| 2627 |
+
"loss": 1.5895,
|
| 2628 |
+
"step": 18700
|
| 2629 |
+
},
|
| 2630 |
+
{
|
| 2631 |
+
"epoch": 0.6410694748358862,
|
| 2632 |
+
"grad_norm": 11.610821723937988,
|
| 2633 |
+
"learning_rate": 8.590479908802504e-06,
|
| 2634 |
+
"loss": 1.6074,
|
| 2635 |
+
"step": 18750
|
| 2636 |
+
},
|
| 2637 |
+
{
|
| 2638 |
+
"epoch": 0.6427789934354485,
|
| 2639 |
+
"grad_norm": 53.59501647949219,
|
| 2640 |
+
"learning_rate": 8.58008151616338e-06,
|
| 2641 |
+
"loss": 1.6231,
|
| 2642 |
+
"step": 18800
|
| 2643 |
+
},
|
| 2644 |
+
{
|
| 2645 |
+
"epoch": 0.6444885120350109,
|
| 2646 |
+
"grad_norm": 11.70449161529541,
|
| 2647 |
+
"learning_rate": 8.569651252091418e-06,
|
| 2648 |
+
"loss": 1.5634,
|
| 2649 |
+
"step": 18850
|
| 2650 |
+
},
|
| 2651 |
+
{
|
| 2652 |
+
"epoch": 0.6461980306345733,
|
| 2653 |
+
"grad_norm": 13.599007606506348,
|
| 2654 |
+
"learning_rate": 8.559189209441342e-06,
|
| 2655 |
+
"loss": 1.6246,
|
| 2656 |
+
"step": 18900
|
| 2657 |
+
},
|
| 2658 |
+
{
|
| 2659 |
+
"epoch": 0.6479075492341356,
|
| 2660 |
+
"grad_norm": 11.615180015563965,
|
| 2661 |
+
"learning_rate": 8.548695481350772e-06,
|
| 2662 |
+
"loss": 1.601,
|
| 2663 |
+
"step": 18950
|
| 2664 |
+
},
|
| 2665 |
+
{
|
| 2666 |
+
"epoch": 0.649617067833698,
|
| 2667 |
+
"grad_norm": 12.768202781677246,
|
| 2668 |
+
"learning_rate": 8.538170161239413e-06,
|
| 2669 |
+
"loss": 1.5335,
|
| 2670 |
+
"step": 19000
|
| 2671 |
+
},
|
| 2672 |
+
{
|
| 2673 |
+
"epoch": 0.6513265864332604,
|
| 2674 |
+
"grad_norm": 25.282073974609375,
|
| 2675 |
+
"learning_rate": 8.527613342808215e-06,
|
| 2676 |
+
"loss": 1.6012,
|
| 2677 |
+
"step": 19050
|
| 2678 |
+
},
|
| 2679 |
+
{
|
| 2680 |
+
"epoch": 0.6530361050328227,
|
| 2681 |
+
"grad_norm": 8.525103569030762,
|
| 2682 |
+
"learning_rate": 8.517025120038536e-06,
|
| 2683 |
+
"loss": 1.5949,
|
| 2684 |
+
"step": 19100
|
| 2685 |
+
},
|
| 2686 |
+
{
|
| 2687 |
+
"epoch": 0.6547456236323851,
|
| 2688 |
+
"grad_norm": 13.596376419067383,
|
| 2689 |
+
"learning_rate": 8.506405587191312e-06,
|
| 2690 |
+
"loss": 1.6334,
|
| 2691 |
+
"step": 19150
|
| 2692 |
+
},
|
| 2693 |
+
{
|
| 2694 |
+
"epoch": 0.6564551422319475,
|
| 2695 |
+
"grad_norm": 17.294708251953125,
|
| 2696 |
+
"learning_rate": 8.495754838806211e-06,
|
| 2697 |
+
"loss": 1.5229,
|
| 2698 |
+
"step": 19200
|
| 2699 |
+
},
|
| 2700 |
+
{
|
| 2701 |
+
"epoch": 0.6581646608315098,
|
| 2702 |
+
"grad_norm": 12.102405548095703,
|
| 2703 |
+
"learning_rate": 8.485072969700802e-06,
|
| 2704 |
+
"loss": 1.5039,
|
| 2705 |
+
"step": 19250
|
| 2706 |
+
},
|
| 2707 |
+
{
|
| 2708 |
+
"epoch": 0.6598741794310722,
|
| 2709 |
+
"grad_norm": 24.811744689941406,
|
| 2710 |
+
"learning_rate": 8.474360074969699e-06,
|
| 2711 |
+
"loss": 1.5927,
|
| 2712 |
+
"step": 19300
|
| 2713 |
+
},
|
| 2714 |
+
{
|
| 2715 |
+
"epoch": 0.6615836980306345,
|
| 2716 |
+
"grad_norm": 13.432709693908691,
|
| 2717 |
+
"learning_rate": 8.463616249983718e-06,
|
| 2718 |
+
"loss": 1.6262,
|
| 2719 |
+
"step": 19350
|
| 2720 |
+
},
|
| 2721 |
+
{
|
| 2722 |
+
"epoch": 0.6632932166301969,
|
| 2723 |
+
"grad_norm": 9.415167808532715,
|
| 2724 |
+
"learning_rate": 8.452841590389032e-06,
|
| 2725 |
+
"loss": 1.6397,
|
| 2726 |
+
"step": 19400
|
| 2727 |
+
},
|
| 2728 |
+
{
|
| 2729 |
+
"epoch": 0.6650027352297593,
|
| 2730 |
+
"grad_norm": 8.890748023986816,
|
| 2731 |
+
"learning_rate": 8.442036192106322e-06,
|
| 2732 |
+
"loss": 1.609,
|
| 2733 |
+
"step": 19450
|
| 2734 |
+
},
|
| 2735 |
+
{
|
| 2736 |
+
"epoch": 0.6667122538293216,
|
| 2737 |
+
"grad_norm": 18.73973274230957,
|
| 2738 |
+
"learning_rate": 8.431200151329908e-06,
|
| 2739 |
+
"loss": 1.5954,
|
| 2740 |
+
"step": 19500
|
| 2741 |
+
},
|
| 2742 |
+
{
|
| 2743 |
+
"epoch": 0.668421772428884,
|
| 2744 |
+
"grad_norm": 17.701303482055664,
|
| 2745 |
+
"learning_rate": 8.420333564526912e-06,
|
| 2746 |
+
"loss": 1.5266,
|
| 2747 |
+
"step": 19550
|
| 2748 |
+
},
|
| 2749 |
+
{
|
| 2750 |
+
"epoch": 0.6701312910284464,
|
| 2751 |
+
"grad_norm": 13.644699096679688,
|
| 2752 |
+
"learning_rate": 8.409436528436381e-06,
|
| 2753 |
+
"loss": 1.5745,
|
| 2754 |
+
"step": 19600
|
| 2755 |
+
},
|
| 2756 |
+
{
|
| 2757 |
+
"epoch": 0.6718408096280087,
|
| 2758 |
+
"grad_norm": 11.665263175964355,
|
| 2759 |
+
"learning_rate": 8.398509140068445e-06,
|
| 2760 |
+
"loss": 1.6409,
|
| 2761 |
+
"step": 19650
|
| 2762 |
+
},
|
| 2763 |
+
{
|
| 2764 |
+
"epoch": 0.6735503282275711,
|
| 2765 |
+
"grad_norm": 11.529803276062012,
|
| 2766 |
+
"learning_rate": 8.387551496703434e-06,
|
| 2767 |
+
"loss": 1.6331,
|
| 2768 |
+
"step": 19700
|
| 2769 |
+
},
|
| 2770 |
+
{
|
| 2771 |
+
"epoch": 0.6752598468271335,
|
| 2772 |
+
"grad_norm": 20.098817825317383,
|
| 2773 |
+
"learning_rate": 8.376563695891027e-06,
|
| 2774 |
+
"loss": 1.5196,
|
| 2775 |
+
"step": 19750
|
| 2776 |
+
},
|
| 2777 |
+
{
|
| 2778 |
+
"epoch": 0.6769693654266958,
|
| 2779 |
+
"grad_norm": 13.883611679077148,
|
| 2780 |
+
"learning_rate": 8.365545835449373e-06,
|
| 2781 |
+
"loss": 1.5656,
|
| 2782 |
+
"step": 19800
|
| 2783 |
+
},
|
| 2784 |
+
{
|
| 2785 |
+
"epoch": 0.6786788840262582,
|
| 2786 |
+
"grad_norm": 25.94344139099121,
|
| 2787 |
+
"learning_rate": 8.354498013464228e-06,
|
| 2788 |
+
"loss": 1.5701,
|
| 2789 |
+
"step": 19850
|
| 2790 |
+
},
|
| 2791 |
+
{
|
| 2792 |
+
"epoch": 0.6803884026258206,
|
| 2793 |
+
"grad_norm": 12.425202369689941,
|
| 2794 |
+
"learning_rate": 8.343420328288078e-06,
|
| 2795 |
+
"loss": 1.6734,
|
| 2796 |
+
"step": 19900
|
| 2797 |
+
},
|
| 2798 |
+
{
|
| 2799 |
+
"epoch": 0.6820979212253829,
|
| 2800 |
+
"grad_norm": 13.595332145690918,
|
| 2801 |
+
"learning_rate": 8.332312878539265e-06,
|
| 2802 |
+
"loss": 1.5087,
|
| 2803 |
+
"step": 19950
|
| 2804 |
+
},
|
| 2805 |
+
{
|
| 2806 |
+
"epoch": 0.6838074398249453,
|
| 2807 |
+
"grad_norm": 12.277334213256836,
|
| 2808 |
+
"learning_rate": 8.321175763101107e-06,
|
| 2809 |
+
"loss": 1.6765,
|
| 2810 |
+
"step": 20000
|
| 2811 |
+
},
|
| 2812 |
+
{
|
| 2813 |
+
"epoch": 0.6855169584245077,
|
| 2814 |
+
"grad_norm": 16.924724578857422,
|
| 2815 |
+
"learning_rate": 8.310009081121016e-06,
|
| 2816 |
+
"loss": 1.6516,
|
| 2817 |
+
"step": 20050
|
| 2818 |
+
},
|
| 2819 |
+
{
|
| 2820 |
+
"epoch": 0.68722647702407,
|
| 2821 |
+
"grad_norm": 21.384986877441406,
|
| 2822 |
+
"learning_rate": 8.298812932009622e-06,
|
| 2823 |
+
"loss": 1.5168,
|
| 2824 |
+
"step": 20100
|
| 2825 |
+
},
|
| 2826 |
+
{
|
| 2827 |
+
"epoch": 0.6889359956236324,
|
| 2828 |
+
"grad_norm": 16.34136962890625,
|
| 2829 |
+
"learning_rate": 8.287587415439884e-06,
|
| 2830 |
+
"loss": 1.5464,
|
| 2831 |
+
"step": 20150
|
| 2832 |
+
},
|
| 2833 |
+
{
|
| 2834 |
+
"epoch": 0.6906455142231948,
|
| 2835 |
+
"grad_norm": 9.525656700134277,
|
| 2836 |
+
"learning_rate": 8.2763326313462e-06,
|
| 2837 |
+
"loss": 1.6537,
|
| 2838 |
+
"step": 20200
|
| 2839 |
+
},
|
| 2840 |
+
{
|
| 2841 |
+
"epoch": 0.6923550328227571,
|
| 2842 |
+
"grad_norm": 13.81106948852539,
|
| 2843 |
+
"learning_rate": 8.265048679923524e-06,
|
| 2844 |
+
"loss": 1.5948,
|
| 2845 |
+
"step": 20250
|
| 2846 |
+
},
|
| 2847 |
+
{
|
| 2848 |
+
"epoch": 0.6940645514223195,
|
| 2849 |
+
"grad_norm": 15.567239761352539,
|
| 2850 |
+
"learning_rate": 8.253735661626466e-06,
|
| 2851 |
+
"loss": 1.5805,
|
| 2852 |
+
"step": 20300
|
| 2853 |
+
},
|
| 2854 |
+
{
|
| 2855 |
+
"epoch": 0.6957740700218819,
|
| 2856 |
+
"grad_norm": 11.069811820983887,
|
| 2857 |
+
"learning_rate": 8.242393677168406e-06,
|
| 2858 |
+
"loss": 1.6091,
|
| 2859 |
+
"step": 20350
|
| 2860 |
+
},
|
| 2861 |
+
{
|
| 2862 |
+
"epoch": 0.6974835886214442,
|
| 2863 |
+
"grad_norm": 12.312210083007812,
|
| 2864 |
+
"learning_rate": 8.23102282752059e-06,
|
| 2865 |
+
"loss": 1.6556,
|
| 2866 |
+
"step": 20400
|
| 2867 |
+
},
|
| 2868 |
+
{
|
| 2869 |
+
"epoch": 0.6991931072210066,
|
| 2870 |
+
"grad_norm": 10.122139930725098,
|
| 2871 |
+
"learning_rate": 8.219623213911235e-06,
|
| 2872 |
+
"loss": 1.6089,
|
| 2873 |
+
"step": 20450
|
| 2874 |
+
},
|
| 2875 |
+
{
|
| 2876 |
+
"epoch": 0.700902625820569,
|
| 2877 |
+
"grad_norm": 13.965560913085938,
|
| 2878 |
+
"learning_rate": 8.208194937824629e-06,
|
| 2879 |
+
"loss": 1.56,
|
| 2880 |
+
"step": 20500
|
| 2881 |
+
},
|
| 2882 |
+
{
|
| 2883 |
+
"epoch": 0.7026121444201313,
|
| 2884 |
+
"grad_norm": 11.255056381225586,
|
| 2885 |
+
"learning_rate": 8.196738101000223e-06,
|
| 2886 |
+
"loss": 1.5501,
|
| 2887 |
+
"step": 20550
|
| 2888 |
+
},
|
| 2889 |
+
{
|
| 2890 |
+
"epoch": 0.7043216630196937,
|
| 2891 |
+
"grad_norm": 10.740253448486328,
|
| 2892 |
+
"learning_rate": 8.185252805431732e-06,
|
| 2893 |
+
"loss": 1.6276,
|
| 2894 |
+
"step": 20600
|
| 2895 |
+
},
|
| 2896 |
+
{
|
| 2897 |
+
"epoch": 0.706031181619256,
|
| 2898 |
+
"grad_norm": 17.22785186767578,
|
| 2899 |
+
"learning_rate": 8.173739153366221e-06,
|
| 2900 |
+
"loss": 1.5278,
|
| 2901 |
+
"step": 20650
|
| 2902 |
+
},
|
| 2903 |
+
{
|
| 2904 |
+
"epoch": 0.7077407002188184,
|
| 2905 |
+
"grad_norm": 12.74496078491211,
|
| 2906 |
+
"learning_rate": 8.162197247303191e-06,
|
| 2907 |
+
"loss": 1.6329,
|
| 2908 |
+
"step": 20700
|
| 2909 |
+
},
|
| 2910 |
+
{
|
| 2911 |
+
"epoch": 0.7094502188183808,
|
| 2912 |
+
"grad_norm": 20.722795486450195,
|
| 2913 |
+
"learning_rate": 8.150627189993685e-06,
|
| 2914 |
+
"loss": 1.4698,
|
| 2915 |
+
"step": 20750
|
| 2916 |
+
},
|
| 2917 |
+
{
|
| 2918 |
+
"epoch": 0.7111597374179431,
|
| 2919 |
+
"grad_norm": 13.336268424987793,
|
| 2920 |
+
"learning_rate": 8.13902908443935e-06,
|
| 2921 |
+
"loss": 1.5665,
|
| 2922 |
+
"step": 20800
|
| 2923 |
+
},
|
| 2924 |
+
{
|
| 2925 |
+
"epoch": 0.7128692560175055,
|
| 2926 |
+
"grad_norm": 16.339872360229492,
|
| 2927 |
+
"learning_rate": 8.127403033891532e-06,
|
| 2928 |
+
"loss": 1.7627,
|
| 2929 |
+
"step": 20850
|
| 2930 |
+
},
|
| 2931 |
+
{
|
| 2932 |
+
"epoch": 0.7145787746170679,
|
| 2933 |
+
"grad_norm": 42.65546798706055,
|
| 2934 |
+
"learning_rate": 8.115749141850361e-06,
|
| 2935 |
+
"loss": 1.5398,
|
| 2936 |
+
"step": 20900
|
| 2937 |
+
},
|
| 2938 |
+
{
|
| 2939 |
+
"epoch": 0.7162882932166302,
|
| 2940 |
+
"grad_norm": 11.890351295471191,
|
| 2941 |
+
"learning_rate": 8.104067512063818e-06,
|
| 2942 |
+
"loss": 1.7166,
|
| 2943 |
+
"step": 20950
|
| 2944 |
+
},
|
| 2945 |
+
{
|
| 2946 |
+
"epoch": 0.7179978118161926,
|
| 2947 |
+
"grad_norm": 10.205952644348145,
|
| 2948 |
+
"learning_rate": 8.09235824852682e-06,
|
| 2949 |
+
"loss": 1.5697,
|
| 2950 |
+
"step": 21000
|
| 2951 |
+
},
|
| 2952 |
+
{
|
| 2953 |
+
"epoch": 0.719707330415755,
|
| 2954 |
+
"grad_norm": 14.7802152633667,
|
| 2955 |
+
"learning_rate": 8.080621455480293e-06,
|
| 2956 |
+
"loss": 1.5494,
|
| 2957 |
+
"step": 21050
|
| 2958 |
+
},
|
| 2959 |
+
{
|
| 2960 |
+
"epoch": 0.7214168490153173,
|
| 2961 |
+
"grad_norm": 17.576860427856445,
|
| 2962 |
+
"learning_rate": 8.068857237410237e-06,
|
| 2963 |
+
"loss": 1.6525,
|
| 2964 |
+
"step": 21100
|
| 2965 |
+
},
|
| 2966 |
+
{
|
| 2967 |
+
"epoch": 0.7231263676148797,
|
| 2968 |
+
"grad_norm": 11.901483535766602,
|
| 2969 |
+
"learning_rate": 8.05706569904681e-06,
|
| 2970 |
+
"loss": 1.4601,
|
| 2971 |
+
"step": 21150
|
| 2972 |
+
},
|
| 2973 |
+
{
|
| 2974 |
+
"epoch": 0.7248358862144421,
|
| 2975 |
+
"grad_norm": 16.720991134643555,
|
| 2976 |
+
"learning_rate": 8.04524694536338e-06,
|
| 2977 |
+
"loss": 1.5249,
|
| 2978 |
+
"step": 21200
|
| 2979 |
+
},
|
| 2980 |
+
{
|
| 2981 |
+
"epoch": 0.7265454048140044,
|
| 2982 |
+
"grad_norm": 36.35121536254883,
|
| 2983 |
+
"learning_rate": 8.0334010815756e-06,
|
| 2984 |
+
"loss": 1.535,
|
| 2985 |
+
"step": 21250
|
| 2986 |
+
},
|
| 2987 |
+
{
|
| 2988 |
+
"epoch": 0.7282549234135668,
|
| 2989 |
+
"grad_norm": 16.62126350402832,
|
| 2990 |
+
"learning_rate": 8.021528213140468e-06,
|
| 2991 |
+
"loss": 1.7457,
|
| 2992 |
+
"step": 21300
|
| 2993 |
+
},
|
| 2994 |
+
{
|
| 2995 |
+
"epoch": 0.7299644420131292,
|
| 2996 |
+
"grad_norm": 29.15338897705078,
|
| 2997 |
+
"learning_rate": 8.00962844575539e-06,
|
| 2998 |
+
"loss": 1.497,
|
| 2999 |
+
"step": 21350
|
| 3000 |
+
},
|
| 3001 |
+
{
|
| 3002 |
+
"epoch": 0.7316739606126915,
|
| 3003 |
+
"grad_norm": 19.574871063232422,
|
| 3004 |
+
"learning_rate": 7.99770188535724e-06,
|
| 3005 |
+
"loss": 1.5962,
|
| 3006 |
+
"step": 21400
|
| 3007 |
+
},
|
| 3008 |
+
{
|
| 3009 |
+
"epoch": 0.7333834792122538,
|
| 3010 |
+
"grad_norm": 15.899367332458496,
|
| 3011 |
+
"learning_rate": 7.985748638121412e-06,
|
| 3012 |
+
"loss": 1.6591,
|
| 3013 |
+
"step": 21450
|
| 3014 |
+
},
|
| 3015 |
+
{
|
| 3016 |
+
"epoch": 0.7350929978118161,
|
| 3017 |
+
"grad_norm": 14.965877532958984,
|
| 3018 |
+
"learning_rate": 7.973768810460877e-06,
|
| 3019 |
+
"loss": 1.6033,
|
| 3020 |
+
"step": 21500
|
| 3021 |
+
},
|
| 3022 |
+
{
|
| 3023 |
+
"epoch": 0.7368025164113785,
|
| 3024 |
+
"grad_norm": 11.571911811828613,
|
| 3025 |
+
"learning_rate": 7.96176250902524e-06,
|
| 3026 |
+
"loss": 1.5823,
|
| 3027 |
+
"step": 21550
|
| 3028 |
+
},
|
| 3029 |
+
{
|
| 3030 |
+
"epoch": 0.7385120350109409,
|
| 3031 |
+
"grad_norm": 17.080463409423828,
|
| 3032 |
+
"learning_rate": 7.949729840699784e-06,
|
| 3033 |
+
"loss": 1.4398,
|
| 3034 |
+
"step": 21600
|
| 3035 |
+
},
|
| 3036 |
+
{
|
| 3037 |
+
"epoch": 0.7402215536105032,
|
| 3038 |
+
"grad_norm": 14.194506645202637,
|
| 3039 |
+
"learning_rate": 7.937670912604525e-06,
|
| 3040 |
+
"loss": 1.6121,
|
| 3041 |
+
"step": 21650
|
| 3042 |
+
},
|
| 3043 |
+
{
|
| 3044 |
+
"epoch": 0.7419310722100656,
|
| 3045 |
+
"grad_norm": 15.90092945098877,
|
| 3046 |
+
"learning_rate": 7.925585832093248e-06,
|
| 3047 |
+
"loss": 1.6138,
|
| 3048 |
+
"step": 21700
|
| 3049 |
+
},
|
| 3050 |
+
{
|
| 3051 |
+
"epoch": 0.743640590809628,
|
| 3052 |
+
"grad_norm": 11.342020034790039,
|
| 3053 |
+
"learning_rate": 7.913474706752563e-06,
|
| 3054 |
+
"loss": 1.5002,
|
| 3055 |
+
"step": 21750
|
| 3056 |
+
},
|
| 3057 |
+
{
|
| 3058 |
+
"epoch": 0.7453501094091903,
|
| 3059 |
+
"grad_norm": 21.87693214416504,
|
| 3060 |
+
"learning_rate": 7.901337644400946e-06,
|
| 3061 |
+
"loss": 1.537,
|
| 3062 |
+
"step": 21800
|
| 3063 |
+
},
|
| 3064 |
+
{
|
| 3065 |
+
"epoch": 0.7470596280087527,
|
| 3066 |
+
"grad_norm": 9.886853218078613,
|
| 3067 |
+
"learning_rate": 7.889174753087767e-06,
|
| 3068 |
+
"loss": 1.5428,
|
| 3069 |
+
"step": 21850
|
| 3070 |
+
},
|
| 3071 |
+
{
|
| 3072 |
+
"epoch": 0.7487691466083151,
|
| 3073 |
+
"grad_norm": 12.133123397827148,
|
| 3074 |
+
"learning_rate": 7.876986141092342e-06,
|
| 3075 |
+
"loss": 1.511,
|
| 3076 |
+
"step": 21900
|
| 3077 |
+
},
|
| 3078 |
+
{
|
| 3079 |
+
"epoch": 0.7504786652078774,
|
| 3080 |
+
"grad_norm": 10.766824722290039,
|
| 3081 |
+
"learning_rate": 7.864771916922966e-06,
|
| 3082 |
+
"loss": 1.4932,
|
| 3083 |
+
"step": 21950
|
| 3084 |
+
},
|
| 3085 |
+
{
|
| 3086 |
+
"epoch": 0.7521881838074398,
|
| 3087 |
+
"grad_norm": 11.094717979431152,
|
| 3088 |
+
"learning_rate": 7.852532189315934e-06,
|
| 3089 |
+
"loss": 1.5041,
|
| 3090 |
+
"step": 22000
|
| 3091 |
+
},
|
| 3092 |
+
{
|
| 3093 |
+
"epoch": 0.7538977024070022,
|
| 3094 |
+
"grad_norm": 15.205076217651367,
|
| 3095 |
+
"learning_rate": 7.840267067234597e-06,
|
| 3096 |
+
"loss": 1.5348,
|
| 3097 |
+
"step": 22050
|
| 3098 |
+
},
|
| 3099 |
+
{
|
| 3100 |
+
"epoch": 0.7556072210065645,
|
| 3101 |
+
"grad_norm": 11.801196098327637,
|
| 3102 |
+
"learning_rate": 7.827976659868368e-06,
|
| 3103 |
+
"loss": 1.4939,
|
| 3104 |
+
"step": 22100
|
| 3105 |
+
},
|
| 3106 |
+
{
|
| 3107 |
+
"epoch": 0.7573167396061269,
|
| 3108 |
+
"grad_norm": 10.897517204284668,
|
| 3109 |
+
"learning_rate": 7.815661076631769e-06,
|
| 3110 |
+
"loss": 1.6581,
|
| 3111 |
+
"step": 22150
|
| 3112 |
+
},
|
| 3113 |
+
{
|
| 3114 |
+
"epoch": 0.7590262582056893,
|
| 3115 |
+
"grad_norm": 9.412324905395508,
|
| 3116 |
+
"learning_rate": 7.803320427163442e-06,
|
| 3117 |
+
"loss": 1.6009,
|
| 3118 |
+
"step": 22200
|
| 3119 |
+
},
|
| 3120 |
+
{
|
| 3121 |
+
"epoch": 0.7607357768052516,
|
| 3122 |
+
"grad_norm": 11.223960876464844,
|
| 3123 |
+
"learning_rate": 7.790954821325178e-06,
|
| 3124 |
+
"loss": 1.4414,
|
| 3125 |
+
"step": 22250
|
| 3126 |
+
},
|
| 3127 |
+
{
|
| 3128 |
+
"epoch": 0.762445295404814,
|
| 3129 |
+
"grad_norm": 21.10007095336914,
|
| 3130 |
+
"learning_rate": 7.778564369200952e-06,
|
| 3131 |
+
"loss": 1.4084,
|
| 3132 |
+
"step": 22300
|
| 3133 |
+
},
|
| 3134 |
+
{
|
| 3135 |
+
"epoch": 0.7641548140043763,
|
| 3136 |
+
"grad_norm": 8.32995891571045,
|
| 3137 |
+
"learning_rate": 7.766149181095916e-06,
|
| 3138 |
+
"loss": 1.5338,
|
| 3139 |
+
"step": 22350
|
| 3140 |
+
},
|
| 3141 |
+
{
|
| 3142 |
+
"epoch": 0.7658643326039387,
|
| 3143 |
+
"grad_norm": 14.99540901184082,
|
| 3144 |
+
"learning_rate": 7.753709367535447e-06,
|
| 3145 |
+
"loss": 1.6023,
|
| 3146 |
+
"step": 22400
|
| 3147 |
+
},
|
| 3148 |
+
{
|
| 3149 |
+
"epoch": 0.7675738512035011,
|
| 3150 |
+
"grad_norm": 17.552499771118164,
|
| 3151 |
+
"learning_rate": 7.741245039264135e-06,
|
| 3152 |
+
"loss": 1.623,
|
| 3153 |
+
"step": 22450
|
| 3154 |
+
},
|
| 3155 |
+
{
|
| 3156 |
+
"epoch": 0.7692833698030634,
|
| 3157 |
+
"grad_norm": 18.489717483520508,
|
| 3158 |
+
"learning_rate": 7.728756307244821e-06,
|
| 3159 |
+
"loss": 1.5708,
|
| 3160 |
+
"step": 22500
|
| 3161 |
+
},
|
| 3162 |
+
{
|
| 3163 |
+
"epoch": 0.7709928884026258,
|
| 3164 |
+
"grad_norm": 29.87468147277832,
|
| 3165 |
+
"learning_rate": 7.716243282657591e-06,
|
| 3166 |
+
"loss": 1.5358,
|
| 3167 |
+
"step": 22550
|
| 3168 |
+
},
|
| 3169 |
+
{
|
| 3170 |
+
"epoch": 0.7727024070021882,
|
| 3171 |
+
"grad_norm": 18.17164421081543,
|
| 3172 |
+
"learning_rate": 7.703706076898803e-06,
|
| 3173 |
+
"loss": 1.6353,
|
| 3174 |
+
"step": 22600
|
| 3175 |
+
},
|
| 3176 |
+
{
|
| 3177 |
+
"epoch": 0.7744119256017505,
|
| 3178 |
+
"grad_norm": 21.323930740356445,
|
| 3179 |
+
"learning_rate": 7.691144801580075e-06,
|
| 3180 |
+
"loss": 1.4801,
|
| 3181 |
+
"step": 22650
|
| 3182 |
+
},
|
| 3183 |
+
{
|
| 3184 |
+
"epoch": 0.7761214442013129,
|
| 3185 |
+
"grad_norm": 15.789224624633789,
|
| 3186 |
+
"learning_rate": 7.678559568527312e-06,
|
| 3187 |
+
"loss": 1.5236,
|
| 3188 |
+
"step": 22700
|
| 3189 |
+
},
|
| 3190 |
+
{
|
| 3191 |
+
"epoch": 0.7778309628008753,
|
| 3192 |
+
"grad_norm": 26.40544319152832,
|
| 3193 |
+
"learning_rate": 7.665950489779696e-06,
|
| 3194 |
+
"loss": 1.5576,
|
| 3195 |
+
"step": 22750
|
| 3196 |
+
},
|
| 3197 |
+
{
|
| 3198 |
+
"epoch": 0.7795404814004376,
|
| 3199 |
+
"grad_norm": 29.84250831604004,
|
| 3200 |
+
"learning_rate": 7.653317677588694e-06,
|
| 3201 |
+
"loss": 1.5585,
|
| 3202 |
+
"step": 22800
|
| 3203 |
+
},
|
| 3204 |
+
{
|
| 3205 |
+
"epoch": 0.78125,
|
| 3206 |
+
"grad_norm": 17.470285415649414,
|
| 3207 |
+
"learning_rate": 7.640661244417064e-06,
|
| 3208 |
+
"loss": 1.5082,
|
| 3209 |
+
"step": 22850
|
| 3210 |
+
},
|
| 3211 |
+
{
|
| 3212 |
+
"epoch": 0.7829595185995624,
|
| 3213 |
+
"grad_norm": 16.64007568359375,
|
| 3214 |
+
"learning_rate": 7.627981302937839e-06,
|
| 3215 |
+
"loss": 1.4479,
|
| 3216 |
+
"step": 22900
|
| 3217 |
+
},
|
| 3218 |
+
{
|
| 3219 |
+
"epoch": 0.7846690371991247,
|
| 3220 |
+
"grad_norm": 12.073901176452637,
|
| 3221 |
+
"learning_rate": 7.6152779660333406e-06,
|
| 3222 |
+
"loss": 1.47,
|
| 3223 |
+
"step": 22950
|
| 3224 |
+
},
|
| 3225 |
+
{
|
| 3226 |
+
"epoch": 0.7863785557986871,
|
| 3227 |
+
"grad_norm": 8.669178009033203,
|
| 3228 |
+
"learning_rate": 7.602551346794161e-06,
|
| 3229 |
+
"loss": 1.5941,
|
| 3230 |
+
"step": 23000
|
| 3231 |
+
}
|
| 3232 |
+
],
|
| 3233 |
+
"logging_steps": 50,
|
| 3234 |
+
"max_steps": 58496,
|
| 3235 |
+
"num_input_tokens_seen": 0,
|
| 3236 |
+
"num_train_epochs": 2,
|
| 3237 |
+
"save_steps": 1000,
|
| 3238 |
+
"stateful_callbacks": {
|
| 3239 |
+
"TrainerControl": {
|
| 3240 |
+
"args": {
|
| 3241 |
+
"should_epoch_stop": false,
|
| 3242 |
+
"should_evaluate": false,
|
| 3243 |
+
"should_log": false,
|
| 3244 |
+
"should_save": true,
|
| 3245 |
+
"should_training_stop": false
|
| 3246 |
+
},
|
| 3247 |
+
"attributes": {}
|
| 3248 |
+
}
|
| 3249 |
+
},
|
| 3250 |
+
"total_flos": 0.0,
|
| 3251 |
+
"train_batch_size": 1,
|
| 3252 |
+
"trial_name": null,
|
| 3253 |
+
"trial_params": null
|
| 3254 |
+
}
|