Upload folder using huggingface_hub
Browse files- train_5k-quantized-4-default/README.md +202 -0
- train_5k-quantized-4-default/adapter_config.json +34 -0
- train_5k-quantized-4-default/adapter_model.safetensors +3 -0
- train_5k-quantized-4-default/config.json +66 -0
- train_5k-quantized-4-default/non_lora_trainables.bin +3 -0
- train_5k-quantized-4-default/trainer_state.json +1902 -0
train_5k-quantized-4-default/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: microsoft/llava-med-v1.5-mistral-7b
|
| 3 |
+
library_name: peft
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.10.0
|
train_5k-quantized-4-default/adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "microsoft/llava-med-v1.5-mistral-7b",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 256,
|
| 14 |
+
"lora_dropout": 0.05,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 128,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"q_proj",
|
| 24 |
+
"down_proj",
|
| 25 |
+
"o_proj",
|
| 26 |
+
"v_proj",
|
| 27 |
+
"gate_proj",
|
| 28 |
+
"k_proj",
|
| 29 |
+
"up_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
train_5k-quantized-4-default/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:862cc43cb436bb28a89044300b95d558e6e65c2aafdd7aff95bee8d7420dfeef
|
| 3 |
+
size 671150064
|
train_5k-quantized-4-default/config.json
ADDED
|
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "microsoft/llava-med-v1.5-mistral-7b",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlavaMistralForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"bos_token_id": 1,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"feature_outs": "encoder+decoder",
|
| 11 |
+
"freeze_mm_mlp_adapter": false,
|
| 12 |
+
"hidden_act": "silu",
|
| 13 |
+
"hidden_size": 4096,
|
| 14 |
+
"image_aspect_ratio": "pad",
|
| 15 |
+
"img_size": 640,
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"intermediate_size": 14336,
|
| 18 |
+
"max_position_embeddings": 32768,
|
| 19 |
+
"mm_hidden_size": 1024,
|
| 20 |
+
"mm_patch_merge_type": "flat",
|
| 21 |
+
"mm_projector_lr": 2e-05,
|
| 22 |
+
"mm_projector_type": "mlp2x_gelu",
|
| 23 |
+
"mm_use_im_patch_token": false,
|
| 24 |
+
"mm_use_im_start_end": false,
|
| 25 |
+
"mm_vision_select_feature": "patch",
|
| 26 |
+
"mm_vision_select_layer": -2,
|
| 27 |
+
"mm_vision_tower": "openai/clip-vit-large-patch14-336",
|
| 28 |
+
"model_type": "llava_llama",
|
| 29 |
+
"num_attention_heads": 32,
|
| 30 |
+
"num_hidden_layers": 32,
|
| 31 |
+
"num_key_value_heads": 8,
|
| 32 |
+
"pretraining_tp": 1,
|
| 33 |
+
"proj_vis_to_txt_tokens": false,
|
| 34 |
+
"prompt_segtok_w_instruct": false,
|
| 35 |
+
"quantization_config": {
|
| 36 |
+
"bnb_4bit_compute_dtype": "bfloat16",
|
| 37 |
+
"bnb_4bit_quant_type": "nf4",
|
| 38 |
+
"bnb_4bit_use_double_quant": true,
|
| 39 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
| 40 |
+
"llm_int8_has_fp16_weight": false,
|
| 41 |
+
"llm_int8_skip_modules": [
|
| 42 |
+
"mm_projector"
|
| 43 |
+
],
|
| 44 |
+
"llm_int8_threshold": 6.0,
|
| 45 |
+
"load_in_4bit": true,
|
| 46 |
+
"load_in_8bit": false,
|
| 47 |
+
"quant_method": "bitsandbytes"
|
| 48 |
+
},
|
| 49 |
+
"rms_norm_eps": 1e-05,
|
| 50 |
+
"rope_scaling": null,
|
| 51 |
+
"rope_theta": 1000000.0,
|
| 52 |
+
"segtok_posembed": "sincos",
|
| 53 |
+
"sliding_window": null,
|
| 54 |
+
"tie_word_embeddings": false,
|
| 55 |
+
"tokenizer_model_max_length": 2048,
|
| 56 |
+
"tokenizer_padding_side": "right",
|
| 57 |
+
"torch_dtype": "bfloat16",
|
| 58 |
+
"transformers_version": "4.37.2",
|
| 59 |
+
"tune_mm_mlp_adapter": false,
|
| 60 |
+
"tune_vision_tokenizer": "none",
|
| 61 |
+
"use_cache": true,
|
| 62 |
+
"use_mm_proj": true,
|
| 63 |
+
"vision_backbone": "convnextlarge",
|
| 64 |
+
"vision_tokenizer_lr": null,
|
| 65 |
+
"vocab_size": 32000
|
| 66 |
+
}
|
train_5k-quantized-4-default/non_lora_trainables.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c790e1c865435ef643aec4544c0fe28c379fc58d945bae51dc7001cd56380d81
|
| 3 |
+
size 41961648
|
train_5k-quantized-4-default/trainer_state.json
ADDED
|
@@ -0,0 +1,1902 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9984,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 312,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0,
|
| 13 |
+
"learning_rate": 2e-05,
|
| 14 |
+
"loss": 2.3172,
|
| 15 |
+
"step": 1
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.01,
|
| 19 |
+
"learning_rate": 4e-05,
|
| 20 |
+
"loss": 2.5335,
|
| 21 |
+
"step": 2
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.01,
|
| 25 |
+
"learning_rate": 6e-05,
|
| 26 |
+
"loss": 2.1376,
|
| 27 |
+
"step": 3
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.01,
|
| 31 |
+
"learning_rate": 8e-05,
|
| 32 |
+
"loss": 1.9307,
|
| 33 |
+
"step": 4
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.02,
|
| 37 |
+
"learning_rate": 0.0001,
|
| 38 |
+
"loss": 1.8922,
|
| 39 |
+
"step": 5
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.02,
|
| 43 |
+
"learning_rate": 0.00012,
|
| 44 |
+
"loss": 1.6593,
|
| 45 |
+
"step": 6
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.02,
|
| 49 |
+
"learning_rate": 0.00014,
|
| 50 |
+
"loss": 1.8319,
|
| 51 |
+
"step": 7
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.03,
|
| 55 |
+
"learning_rate": 0.00016,
|
| 56 |
+
"loss": 1.7492,
|
| 57 |
+
"step": 8
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.03,
|
| 61 |
+
"learning_rate": 0.00018,
|
| 62 |
+
"loss": 1.6805,
|
| 63 |
+
"step": 9
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.03,
|
| 67 |
+
"learning_rate": 0.0002,
|
| 68 |
+
"loss": 1.7235,
|
| 69 |
+
"step": 10
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.04,
|
| 73 |
+
"learning_rate": 0.00019999458931878073,
|
| 74 |
+
"loss": 1.4492,
|
| 75 |
+
"step": 11
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.04,
|
| 79 |
+
"learning_rate": 0.0001999783578606323,
|
| 80 |
+
"loss": 1.6036,
|
| 81 |
+
"step": 12
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.04,
|
| 85 |
+
"learning_rate": 0.00019995130738201966,
|
| 86 |
+
"loss": 1.6278,
|
| 87 |
+
"step": 13
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.04,
|
| 91 |
+
"learning_rate": 0.0001999134408101731,
|
| 92 |
+
"loss": 1.7926,
|
| 93 |
+
"step": 14
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.05,
|
| 97 |
+
"learning_rate": 0.00019986476224277165,
|
| 98 |
+
"loss": 1.7498,
|
| 99 |
+
"step": 15
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.05,
|
| 103 |
+
"learning_rate": 0.00019980527694749952,
|
| 104 |
+
"loss": 1.6711,
|
| 105 |
+
"step": 16
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.05,
|
| 109 |
+
"learning_rate": 0.00019973499136147606,
|
| 110 |
+
"loss": 1.526,
|
| 111 |
+
"step": 17
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.06,
|
| 115 |
+
"learning_rate": 0.0001996539130905593,
|
| 116 |
+
"loss": 1.5105,
|
| 117 |
+
"step": 18
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.06,
|
| 121 |
+
"learning_rate": 0.0001995620509085228,
|
| 122 |
+
"loss": 1.6764,
|
| 123 |
+
"step": 19
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.06,
|
| 127 |
+
"learning_rate": 0.00019945941475610623,
|
| 128 |
+
"loss": 1.5464,
|
| 129 |
+
"step": 20
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.07,
|
| 133 |
+
"learning_rate": 0.0001993460157399396,
|
| 134 |
+
"loss": 1.6566,
|
| 135 |
+
"step": 21
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.07,
|
| 139 |
+
"learning_rate": 0.0001992218661313415,
|
| 140 |
+
"loss": 1.7459,
|
| 141 |
+
"step": 22
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.07,
|
| 145 |
+
"learning_rate": 0.00019908697936499103,
|
| 146 |
+
"loss": 1.52,
|
| 147 |
+
"step": 23
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.08,
|
| 151 |
+
"learning_rate": 0.00019894137003747403,
|
| 152 |
+
"loss": 1.3941,
|
| 153 |
+
"step": 24
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.08,
|
| 157 |
+
"learning_rate": 0.00019878505390570362,
|
| 158 |
+
"loss": 1.4971,
|
| 159 |
+
"step": 25
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.08,
|
| 163 |
+
"learning_rate": 0.00019861804788521493,
|
| 164 |
+
"loss": 1.6746,
|
| 165 |
+
"step": 26
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.09,
|
| 169 |
+
"learning_rate": 0.00019844037004833473,
|
| 170 |
+
"loss": 1.5774,
|
| 171 |
+
"step": 27
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.09,
|
| 175 |
+
"learning_rate": 0.00019825203962222572,
|
| 176 |
+
"loss": 1.5899,
|
| 177 |
+
"step": 28
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.09,
|
| 181 |
+
"learning_rate": 0.0001980530769868059,
|
| 182 |
+
"loss": 1.3888,
|
| 183 |
+
"step": 29
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.1,
|
| 187 |
+
"learning_rate": 0.00019784350367254322,
|
| 188 |
+
"loss": 1.5598,
|
| 189 |
+
"step": 30
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.1,
|
| 193 |
+
"learning_rate": 0.0001976233423581255,
|
| 194 |
+
"loss": 1.5839,
|
| 195 |
+
"step": 31
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.1,
|
| 199 |
+
"learning_rate": 0.0001973926168680066,
|
| 200 |
+
"loss": 1.4904,
|
| 201 |
+
"step": 32
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.11,
|
| 205 |
+
"learning_rate": 0.00019715135216982798,
|
| 206 |
+
"loss": 1.666,
|
| 207 |
+
"step": 33
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.11,
|
| 211 |
+
"learning_rate": 0.0001968995743717171,
|
| 212 |
+
"loss": 1.6375,
|
| 213 |
+
"step": 34
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.11,
|
| 217 |
+
"learning_rate": 0.00019663731071946206,
|
| 218 |
+
"loss": 1.5643,
|
| 219 |
+
"step": 35
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.12,
|
| 223 |
+
"learning_rate": 0.00019636458959356316,
|
| 224 |
+
"loss": 1.548,
|
| 225 |
+
"step": 36
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.12,
|
| 229 |
+
"learning_rate": 0.0001960814405061619,
|
| 230 |
+
"loss": 1.5101,
|
| 231 |
+
"step": 37
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.12,
|
| 235 |
+
"learning_rate": 0.00019578789409784727,
|
| 236 |
+
"loss": 1.4541,
|
| 237 |
+
"step": 38
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.12,
|
| 241 |
+
"learning_rate": 0.00019548398213434007,
|
| 242 |
+
"loss": 1.4757,
|
| 243 |
+
"step": 39
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.13,
|
| 247 |
+
"learning_rate": 0.00019516973750305532,
|
| 248 |
+
"loss": 1.4002,
|
| 249 |
+
"step": 40
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.13,
|
| 253 |
+
"learning_rate": 0.00019484519420954354,
|
| 254 |
+
"loss": 1.3392,
|
| 255 |
+
"step": 41
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.13,
|
| 259 |
+
"learning_rate": 0.00019451038737381077,
|
| 260 |
+
"loss": 1.7327,
|
| 261 |
+
"step": 42
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.14,
|
| 265 |
+
"learning_rate": 0.00019416535322651818,
|
| 266 |
+
"loss": 1.7479,
|
| 267 |
+
"step": 43
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.14,
|
| 271 |
+
"learning_rate": 0.00019381012910506146,
|
| 272 |
+
"loss": 1.4793,
|
| 273 |
+
"step": 44
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.14,
|
| 277 |
+
"learning_rate": 0.00019344475344953012,
|
| 278 |
+
"loss": 1.4659,
|
| 279 |
+
"step": 45
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.15,
|
| 283 |
+
"learning_rate": 0.00019306926579854821,
|
| 284 |
+
"loss": 1.5368,
|
| 285 |
+
"step": 46
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.15,
|
| 289 |
+
"learning_rate": 0.00019268370678499533,
|
| 290 |
+
"loss": 1.3053,
|
| 291 |
+
"step": 47
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.15,
|
| 295 |
+
"learning_rate": 0.0001922881181316097,
|
| 296 |
+
"loss": 1.4054,
|
| 297 |
+
"step": 48
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.16,
|
| 301 |
+
"learning_rate": 0.00019188254264647337,
|
| 302 |
+
"loss": 1.4907,
|
| 303 |
+
"step": 49
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.16,
|
| 307 |
+
"learning_rate": 0.0001914670242183795,
|
| 308 |
+
"loss": 1.5888,
|
| 309 |
+
"step": 50
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.16,
|
| 313 |
+
"learning_rate": 0.0001910416078120832,
|
| 314 |
+
"loss": 1.485,
|
| 315 |
+
"step": 51
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 0.17,
|
| 319 |
+
"learning_rate": 0.0001906063394634356,
|
| 320 |
+
"loss": 1.5769,
|
| 321 |
+
"step": 52
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.17,
|
| 325 |
+
"learning_rate": 0.00019016126627440237,
|
| 326 |
+
"loss": 1.5748,
|
| 327 |
+
"step": 53
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.17,
|
| 331 |
+
"learning_rate": 0.00018970643640796642,
|
| 332 |
+
"loss": 1.4148,
|
| 333 |
+
"step": 54
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.18,
|
| 337 |
+
"learning_rate": 0.000189241899082916,
|
| 338 |
+
"loss": 1.4344,
|
| 339 |
+
"step": 55
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.18,
|
| 343 |
+
"learning_rate": 0.00018876770456851877,
|
| 344 |
+
"loss": 1.3535,
|
| 345 |
+
"step": 56
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.18,
|
| 349 |
+
"learning_rate": 0.0001882839041790818,
|
| 350 |
+
"loss": 1.5111,
|
| 351 |
+
"step": 57
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.19,
|
| 355 |
+
"learning_rate": 0.00018779055026839868,
|
| 356 |
+
"loss": 1.3816,
|
| 357 |
+
"step": 58
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 0.19,
|
| 361 |
+
"learning_rate": 0.00018728769622408423,
|
| 362 |
+
"loss": 1.6916,
|
| 363 |
+
"step": 59
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.19,
|
| 367 |
+
"learning_rate": 0.00018677539646179707,
|
| 368 |
+
"loss": 1.4465,
|
| 369 |
+
"step": 60
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.2,
|
| 373 |
+
"learning_rate": 0.00018625370641935129,
|
| 374 |
+
"loss": 1.4713,
|
| 375 |
+
"step": 61
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.2,
|
| 379 |
+
"learning_rate": 0.00018572268255071718,
|
| 380 |
+
"loss": 1.3415,
|
| 381 |
+
"step": 62
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.2,
|
| 385 |
+
"learning_rate": 0.00018518238231991218,
|
| 386 |
+
"loss": 1.5171,
|
| 387 |
+
"step": 63
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.2,
|
| 391 |
+
"learning_rate": 0.00018463286419478255,
|
| 392 |
+
"loss": 1.5282,
|
| 393 |
+
"step": 64
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.21,
|
| 397 |
+
"learning_rate": 0.00018407418764067627,
|
| 398 |
+
"loss": 1.4299,
|
| 399 |
+
"step": 65
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.21,
|
| 403 |
+
"learning_rate": 0.00018350641311400812,
|
| 404 |
+
"loss": 1.6962,
|
| 405 |
+
"step": 66
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 0.21,
|
| 409 |
+
"learning_rate": 0.0001829296020557174,
|
| 410 |
+
"loss": 1.4995,
|
| 411 |
+
"step": 67
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.22,
|
| 415 |
+
"learning_rate": 0.00018234381688461942,
|
| 416 |
+
"loss": 1.2594,
|
| 417 |
+
"step": 68
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.22,
|
| 421 |
+
"learning_rate": 0.0001817491209906506,
|
| 422 |
+
"loss": 1.5057,
|
| 423 |
+
"step": 69
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.22,
|
| 427 |
+
"learning_rate": 0.00018114557872800905,
|
| 428 |
+
"loss": 2.7638,
|
| 429 |
+
"step": 70
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.23,
|
| 433 |
+
"learning_rate": 0.00018053325540819045,
|
| 434 |
+
"loss": 1.6238,
|
| 435 |
+
"step": 71
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.23,
|
| 439 |
+
"learning_rate": 0.0001799122172929206,
|
| 440 |
+
"loss": 1.4466,
|
| 441 |
+
"step": 72
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.23,
|
| 445 |
+
"learning_rate": 0.00017928253158698473,
|
| 446 |
+
"loss": 1.9276,
|
| 447 |
+
"step": 73
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 0.24,
|
| 451 |
+
"learning_rate": 0.0001786442664309554,
|
| 452 |
+
"loss": 4.1286,
|
| 453 |
+
"step": 74
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.24,
|
| 457 |
+
"learning_rate": 0.0001779974908938184,
|
| 458 |
+
"loss": 6.6009,
|
| 459 |
+
"step": 75
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.24,
|
| 463 |
+
"learning_rate": 0.0001773422749654988,
|
| 464 |
+
"loss": 3.5854,
|
| 465 |
+
"step": 76
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.25,
|
| 469 |
+
"learning_rate": 0.00017667868954928694,
|
| 470 |
+
"loss": 2.2687,
|
| 471 |
+
"step": 77
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.25,
|
| 475 |
+
"learning_rate": 0.00017600680645416583,
|
| 476 |
+
"loss": 1.8341,
|
| 477 |
+
"step": 78
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.25,
|
| 481 |
+
"learning_rate": 0.00017532669838704035,
|
| 482 |
+
"loss": 1.4794,
|
| 483 |
+
"step": 79
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 0.26,
|
| 487 |
+
"learning_rate": 0.00017463843894486937,
|
| 488 |
+
"loss": 1.9379,
|
| 489 |
+
"step": 80
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.26,
|
| 493 |
+
"learning_rate": 0.0001739421026067017,
|
| 494 |
+
"loss": 1.8017,
|
| 495 |
+
"step": 81
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.26,
|
| 499 |
+
"learning_rate": 0.00017323776472561627,
|
| 500 |
+
"loss": 1.5887,
|
| 501 |
+
"step": 82
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.27,
|
| 505 |
+
"learning_rate": 0.00017252550152056795,
|
| 506 |
+
"loss": 1.7066,
|
| 507 |
+
"step": 83
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.27,
|
| 511 |
+
"learning_rate": 0.0001718053900681397,
|
| 512 |
+
"loss": 1.3569,
|
| 513 |
+
"step": 84
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.27,
|
| 517 |
+
"learning_rate": 0.00017107750829420176,
|
| 518 |
+
"loss": 1.5293,
|
| 519 |
+
"step": 85
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.28,
|
| 523 |
+
"learning_rate": 0.00017034193496547902,
|
| 524 |
+
"loss": 1.6686,
|
| 525 |
+
"step": 86
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.28,
|
| 529 |
+
"learning_rate": 0.00016959874968102735,
|
| 530 |
+
"loss": 1.6846,
|
| 531 |
+
"step": 87
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 0.28,
|
| 535 |
+
"learning_rate": 0.00016884803286362,
|
| 536 |
+
"loss": 1.5077,
|
| 537 |
+
"step": 88
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.28,
|
| 541 |
+
"learning_rate": 0.00016808986575104465,
|
| 542 |
+
"loss": 2.0585,
|
| 543 |
+
"step": 89
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.29,
|
| 547 |
+
"learning_rate": 0.00016732433038731242,
|
| 548 |
+
"loss": 1.4112,
|
| 549 |
+
"step": 90
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.29,
|
| 553 |
+
"learning_rate": 0.0001665515096137797,
|
| 554 |
+
"loss": 1.633,
|
| 555 |
+
"step": 91
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.29,
|
| 559 |
+
"learning_rate": 0.00016577148706018328,
|
| 560 |
+
"loss": 6.6799,
|
| 561 |
+
"step": 92
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 0.3,
|
| 565 |
+
"learning_rate": 0.00016498434713559088,
|
| 566 |
+
"loss": 2.0208,
|
| 567 |
+
"step": 93
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 0.3,
|
| 571 |
+
"learning_rate": 0.00016419017501926656,
|
| 572 |
+
"loss": 1.755,
|
| 573 |
+
"step": 94
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 0.3,
|
| 577 |
+
"learning_rate": 0.0001633890566514535,
|
| 578 |
+
"loss": 1.6762,
|
| 579 |
+
"step": 95
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 0.31,
|
| 583 |
+
"learning_rate": 0.00016258107872407375,
|
| 584 |
+
"loss": 1.6067,
|
| 585 |
+
"step": 96
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.31,
|
| 589 |
+
"learning_rate": 0.0001617663286713474,
|
| 590 |
+
"loss": 1.6935,
|
| 591 |
+
"step": 97
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.31,
|
| 595 |
+
"learning_rate": 0.00016094489466033043,
|
| 596 |
+
"loss": 1.4747,
|
| 597 |
+
"step": 98
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.32,
|
| 601 |
+
"learning_rate": 0.00016011686558137448,
|
| 602 |
+
"loss": 2.21,
|
| 603 |
+
"step": 99
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 0.32,
|
| 607 |
+
"learning_rate": 0.0001592823310385073,
|
| 608 |
+
"loss": 1.6612,
|
| 609 |
+
"step": 100
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 0.32,
|
| 613 |
+
"learning_rate": 0.0001584413813397364,
|
| 614 |
+
"loss": 1.5383,
|
| 615 |
+
"step": 101
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 0.33,
|
| 619 |
+
"learning_rate": 0.00015759410748727662,
|
| 620 |
+
"loss": 1.5223,
|
| 621 |
+
"step": 102
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 0.33,
|
| 625 |
+
"learning_rate": 0.00015674060116770236,
|
| 626 |
+
"loss": 1.5046,
|
| 627 |
+
"step": 103
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.33,
|
| 631 |
+
"learning_rate": 0.00015588095474202595,
|
| 632 |
+
"loss": 1.8203,
|
| 633 |
+
"step": 104
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.34,
|
| 637 |
+
"learning_rate": 0.00015501526123570277,
|
| 638 |
+
"loss": 1.6742,
|
| 639 |
+
"step": 105
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.34,
|
| 643 |
+
"learning_rate": 0.00015414361432856475,
|
| 644 |
+
"loss": 1.406,
|
| 645 |
+
"step": 106
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 0.34,
|
| 649 |
+
"learning_rate": 0.0001532661083446829,
|
| 650 |
+
"loss": 1.3389,
|
| 651 |
+
"step": 107
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 0.35,
|
| 655 |
+
"learning_rate": 0.00015238283824216015,
|
| 656 |
+
"loss": 1.4524,
|
| 657 |
+
"step": 108
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 0.35,
|
| 661 |
+
"learning_rate": 0.00015149389960285558,
|
| 662 |
+
"loss": 1.5875,
|
| 663 |
+
"step": 109
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 0.35,
|
| 667 |
+
"learning_rate": 0.00015059938862204127,
|
| 668 |
+
"loss": 1.5332,
|
| 669 |
+
"step": 110
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.36,
|
| 673 |
+
"learning_rate": 0.00014969940209799248,
|
| 674 |
+
"loss": 1.5215,
|
| 675 |
+
"step": 111
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.36,
|
| 679 |
+
"learning_rate": 0.00014879403742151283,
|
| 680 |
+
"loss": 1.598,
|
| 681 |
+
"step": 112
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.36,
|
| 685 |
+
"learning_rate": 0.00014788339256539544,
|
| 686 |
+
"loss": 1.3058,
|
| 687 |
+
"step": 113
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 0.36,
|
| 691 |
+
"learning_rate": 0.0001469675660738206,
|
| 692 |
+
"loss": 1.5053,
|
| 693 |
+
"step": 114
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 0.37,
|
| 697 |
+
"learning_rate": 0.00014604665705169237,
|
| 698 |
+
"loss": 1.415,
|
| 699 |
+
"step": 115
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 0.37,
|
| 703 |
+
"learning_rate": 0.00014512076515391375,
|
| 704 |
+
"loss": 1.5635,
|
| 705 |
+
"step": 116
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 0.37,
|
| 709 |
+
"learning_rate": 0.00014418999057460276,
|
| 710 |
+
"loss": 1.5195,
|
| 711 |
+
"step": 117
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.38,
|
| 715 |
+
"learning_rate": 0.0001432544340362501,
|
| 716 |
+
"loss": 1.4387,
|
| 717 |
+
"step": 118
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.38,
|
| 721 |
+
"learning_rate": 0.00014231419677881966,
|
| 722 |
+
"loss": 1.4878,
|
| 723 |
+
"step": 119
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.38,
|
| 727 |
+
"learning_rate": 0.00014136938054879283,
|
| 728 |
+
"loss": 1.2613,
|
| 729 |
+
"step": 120
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 0.39,
|
| 733 |
+
"learning_rate": 0.00014042008758815818,
|
| 734 |
+
"loss": 1.4854,
|
| 735 |
+
"step": 121
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 0.39,
|
| 739 |
+
"learning_rate": 0.00013946642062334766,
|
| 740 |
+
"loss": 1.2463,
|
| 741 |
+
"step": 122
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 0.39,
|
| 745 |
+
"learning_rate": 0.00013850848285411994,
|
| 746 |
+
"loss": 1.4409,
|
| 747 |
+
"step": 123
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.4,
|
| 751 |
+
"learning_rate": 0.000137546377942393,
|
| 752 |
+
"loss": 1.2753,
|
| 753 |
+
"step": 124
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 0.4,
|
| 757 |
+
"learning_rate": 0.00013658021000102636,
|
| 758 |
+
"loss": 1.5054,
|
| 759 |
+
"step": 125
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.4,
|
| 763 |
+
"learning_rate": 0.00013561008358255468,
|
| 764 |
+
"loss": 1.3089,
|
| 765 |
+
"step": 126
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.41,
|
| 769 |
+
"learning_rate": 0.00013463610366787392,
|
| 770 |
+
"loss": 1.5815,
|
| 771 |
+
"step": 127
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 0.41,
|
| 775 |
+
"learning_rate": 0.00013365837565488064,
|
| 776 |
+
"loss": 1.4093,
|
| 777 |
+
"step": 128
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 0.41,
|
| 781 |
+
"learning_rate": 0.0001326770053470668,
|
| 782 |
+
"loss": 1.3878,
|
| 783 |
+
"step": 129
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 0.42,
|
| 787 |
+
"learning_rate": 0.0001316920989420703,
|
| 788 |
+
"loss": 1.3379,
|
| 789 |
+
"step": 130
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 0.42,
|
| 793 |
+
"learning_rate": 0.00013070376302018287,
|
| 794 |
+
"loss": 1.2651,
|
| 795 |
+
"step": 131
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 0.42,
|
| 799 |
+
"learning_rate": 0.00012971210453281674,
|
| 800 |
+
"loss": 1.3203,
|
| 801 |
+
"step": 132
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.43,
|
| 805 |
+
"learning_rate": 0.000128717230790931,
|
| 806 |
+
"loss": 1.2712,
|
| 807 |
+
"step": 133
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.43,
|
| 811 |
+
"learning_rate": 0.00012771924945341906,
|
| 812 |
+
"loss": 1.2382,
|
| 813 |
+
"step": 134
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 0.43,
|
| 817 |
+
"learning_rate": 0.00012671826851545851,
|
| 818 |
+
"loss": 1.2974,
|
| 819 |
+
"step": 135
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 0.44,
|
| 823 |
+
"learning_rate": 0.0001257143962968246,
|
| 824 |
+
"loss": 1.3225,
|
| 825 |
+
"step": 136
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 0.44,
|
| 829 |
+
"learning_rate": 0.00012470774143016853,
|
| 830 |
+
"loss": 1.4874,
|
| 831 |
+
"step": 137
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 0.44,
|
| 835 |
+
"learning_rate": 0.00012369841284926188,
|
| 836 |
+
"loss": 1.4654,
|
| 837 |
+
"step": 138
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 0.44,
|
| 841 |
+
"learning_rate": 0.00012268651977720866,
|
| 842 |
+
"loss": 1.3508,
|
| 843 |
+
"step": 139
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.45,
|
| 847 |
+
"learning_rate": 0.00012167217171462566,
|
| 848 |
+
"loss": 1.3048,
|
| 849 |
+
"step": 140
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.45,
|
| 853 |
+
"learning_rate": 0.0001206554784277931,
|
| 854 |
+
"loss": 1.4731,
|
| 855 |
+
"step": 141
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 0.45,
|
| 859 |
+
"learning_rate": 0.00011963654993677645,
|
| 860 |
+
"loss": 1.2144,
|
| 861 |
+
"step": 142
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 0.46,
|
| 865 |
+
"learning_rate": 0.00011861549650352069,
|
| 866 |
+
"loss": 1.3876,
|
| 867 |
+
"step": 143
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 0.46,
|
| 871 |
+
"learning_rate": 0.00011759242861991855,
|
| 872 |
+
"loss": 1.3118,
|
| 873 |
+
"step": 144
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 0.46,
|
| 877 |
+
"learning_rate": 0.00011656745699585371,
|
| 878 |
+
"loss": 1.2132,
|
| 879 |
+
"step": 145
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 0.47,
|
| 883 |
+
"learning_rate": 0.00011554069254722051,
|
| 884 |
+
"loss": 1.4687,
|
| 885 |
+
"step": 146
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.47,
|
| 889 |
+
"learning_rate": 0.00011451224638392129,
|
| 890 |
+
"loss": 1.2314,
|
| 891 |
+
"step": 147
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.47,
|
| 895 |
+
"learning_rate": 0.00011348222979784289,
|
| 896 |
+
"loss": 1.2831,
|
| 897 |
+
"step": 148
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 0.48,
|
| 901 |
+
"learning_rate": 0.00011245075425081328,
|
| 902 |
+
"loss": 1.4453,
|
| 903 |
+
"step": 149
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 0.48,
|
| 907 |
+
"learning_rate": 0.00011141793136253986,
|
| 908 |
+
"loss": 1.2795,
|
| 909 |
+
"step": 150
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 0.48,
|
| 913 |
+
"learning_rate": 0.0001103838728985307,
|
| 914 |
+
"loss": 1.446,
|
| 915 |
+
"step": 151
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 0.49,
|
| 919 |
+
"learning_rate": 0.000109348690758,
|
| 920 |
+
"loss": 1.1897,
|
| 921 |
+
"step": 152
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 0.49,
|
| 925 |
+
"learning_rate": 0.00010831249696175918,
|
| 926 |
+
"loss": 1.193,
|
| 927 |
+
"step": 153
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.49,
|
| 931 |
+
"learning_rate": 0.0001072754036400944,
|
| 932 |
+
"loss": 1.2859,
|
| 933 |
+
"step": 154
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.5,
|
| 937 |
+
"learning_rate": 0.00010623752302063283,
|
| 938 |
+
"loss": 1.2807,
|
| 939 |
+
"step": 155
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 0.5,
|
| 943 |
+
"learning_rate": 0.00010519896741619803,
|
| 944 |
+
"loss": 1.353,
|
| 945 |
+
"step": 156
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 0.5,
|
| 949 |
+
"learning_rate": 0.00010415984921265609,
|
| 950 |
+
"loss": 1.3964,
|
| 951 |
+
"step": 157
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 0.51,
|
| 955 |
+
"learning_rate": 0.00010312028085675391,
|
| 956 |
+
"loss": 1.4053,
|
| 957 |
+
"step": 158
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 0.51,
|
| 961 |
+
"learning_rate": 0.00010208037484395114,
|
| 962 |
+
"loss": 1.5299,
|
| 963 |
+
"step": 159
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 0.51,
|
| 967 |
+
"learning_rate": 0.00010104024370624644,
|
| 968 |
+
"loss": 1.369,
|
| 969 |
+
"step": 160
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.52,
|
| 973 |
+
"learning_rate": 0.0001,
|
| 974 |
+
"loss": 1.3394,
|
| 975 |
+
"step": 161
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.52,
|
| 979 |
+
"learning_rate": 9.895975629375359e-05,
|
| 980 |
+
"loss": 1.3759,
|
| 981 |
+
"step": 162
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 0.52,
|
| 985 |
+
"learning_rate": 9.791962515604887e-05,
|
| 986 |
+
"loss": 1.4539,
|
| 987 |
+
"step": 163
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 0.52,
|
| 991 |
+
"learning_rate": 9.687971914324607e-05,
|
| 992 |
+
"loss": 1.2923,
|
| 993 |
+
"step": 164
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 0.53,
|
| 997 |
+
"learning_rate": 9.584015078734395e-05,
|
| 998 |
+
"loss": 1.2475,
|
| 999 |
+
"step": 165
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.53,
|
| 1003 |
+
"learning_rate": 9.480103258380198e-05,
|
| 1004 |
+
"loss": 1.3727,
|
| 1005 |
+
"step": 166
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 0.53,
|
| 1009 |
+
"learning_rate": 9.376247697936719e-05,
|
| 1010 |
+
"loss": 1.397,
|
| 1011 |
+
"step": 167
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 0.54,
|
| 1015 |
+
"learning_rate": 9.272459635990562e-05,
|
| 1016 |
+
"loss": 1.5032,
|
| 1017 |
+
"step": 168
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.54,
|
| 1021 |
+
"learning_rate": 9.168750303824084e-05,
|
| 1022 |
+
"loss": 1.2606,
|
| 1023 |
+
"step": 169
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 0.54,
|
| 1027 |
+
"learning_rate": 9.065130924199998e-05,
|
| 1028 |
+
"loss": 1.3416,
|
| 1029 |
+
"step": 170
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 0.55,
|
| 1033 |
+
"learning_rate": 8.961612710146934e-05,
|
| 1034 |
+
"loss": 1.2814,
|
| 1035 |
+
"step": 171
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 0.55,
|
| 1039 |
+
"learning_rate": 8.858206863746018e-05,
|
| 1040 |
+
"loss": 1.2964,
|
| 1041 |
+
"step": 172
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 0.55,
|
| 1045 |
+
"learning_rate": 8.754924574918675e-05,
|
| 1046 |
+
"loss": 1.426,
|
| 1047 |
+
"step": 173
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 0.56,
|
| 1051 |
+
"learning_rate": 8.651777020215712e-05,
|
| 1052 |
+
"loss": 1.3554,
|
| 1053 |
+
"step": 174
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 0.56,
|
| 1057 |
+
"learning_rate": 8.548775361607872e-05,
|
| 1058 |
+
"loss": 1.3504,
|
| 1059 |
+
"step": 175
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.56,
|
| 1063 |
+
"learning_rate": 8.445930745277953e-05,
|
| 1064 |
+
"loss": 1.2102,
|
| 1065 |
+
"step": 176
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 0.57,
|
| 1069 |
+
"learning_rate": 8.343254300414628e-05,
|
| 1070 |
+
"loss": 1.3667,
|
| 1071 |
+
"step": 177
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 0.57,
|
| 1075 |
+
"learning_rate": 8.240757138008149e-05,
|
| 1076 |
+
"loss": 1.319,
|
| 1077 |
+
"step": 178
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 0.57,
|
| 1081 |
+
"learning_rate": 8.138450349647936e-05,
|
| 1082 |
+
"loss": 1.2481,
|
| 1083 |
+
"step": 179
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 0.58,
|
| 1087 |
+
"learning_rate": 8.036345006322359e-05,
|
| 1088 |
+
"loss": 1.3552,
|
| 1089 |
+
"step": 180
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 0.58,
|
| 1093 |
+
"learning_rate": 7.934452157220694e-05,
|
| 1094 |
+
"loss": 1.1693,
|
| 1095 |
+
"step": 181
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 0.58,
|
| 1099 |
+
"learning_rate": 7.832782828537437e-05,
|
| 1100 |
+
"loss": 1.1172,
|
| 1101 |
+
"step": 182
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.59,
|
| 1105 |
+
"learning_rate": 7.731348022279134e-05,
|
| 1106 |
+
"loss": 1.1956,
|
| 1107 |
+
"step": 183
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 0.59,
|
| 1111 |
+
"learning_rate": 7.630158715073813e-05,
|
| 1112 |
+
"loss": 1.1351,
|
| 1113 |
+
"step": 184
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 0.59,
|
| 1117 |
+
"learning_rate": 7.52922585698315e-05,
|
| 1118 |
+
"loss": 1.2686,
|
| 1119 |
+
"step": 185
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.6,
|
| 1123 |
+
"learning_rate": 7.428560370317542e-05,
|
| 1124 |
+
"loss": 1.3301,
|
| 1125 |
+
"step": 186
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 0.6,
|
| 1129 |
+
"learning_rate": 7.328173148454151e-05,
|
| 1130 |
+
"loss": 1.3624,
|
| 1131 |
+
"step": 187
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 0.6,
|
| 1135 |
+
"learning_rate": 7.228075054658096e-05,
|
| 1136 |
+
"loss": 1.24,
|
| 1137 |
+
"step": 188
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 0.6,
|
| 1141 |
+
"learning_rate": 7.1282769209069e-05,
|
| 1142 |
+
"loss": 1.3894,
|
| 1143 |
+
"step": 189
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.61,
|
| 1147 |
+
"learning_rate": 7.028789546718326e-05,
|
| 1148 |
+
"loss": 1.3425,
|
| 1149 |
+
"step": 190
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 0.61,
|
| 1153 |
+
"learning_rate": 6.929623697981718e-05,
|
| 1154 |
+
"loss": 1.2425,
|
| 1155 |
+
"step": 191
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 0.61,
|
| 1159 |
+
"learning_rate": 6.830790105792973e-05,
|
| 1160 |
+
"loss": 1.3314,
|
| 1161 |
+
"step": 192
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.62,
|
| 1165 |
+
"learning_rate": 6.732299465293322e-05,
|
| 1166 |
+
"loss": 1.3288,
|
| 1167 |
+
"step": 193
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"epoch": 0.62,
|
| 1171 |
+
"learning_rate": 6.63416243451194e-05,
|
| 1172 |
+
"loss": 1.2598,
|
| 1173 |
+
"step": 194
|
| 1174 |
+
},
|
| 1175 |
+
{
|
| 1176 |
+
"epoch": 0.62,
|
| 1177 |
+
"learning_rate": 6.536389633212609e-05,
|
| 1178 |
+
"loss": 1.41,
|
| 1179 |
+
"step": 195
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 0.63,
|
| 1183 |
+
"learning_rate": 6.43899164174453e-05,
|
| 1184 |
+
"loss": 1.0983,
|
| 1185 |
+
"step": 196
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.63,
|
| 1189 |
+
"learning_rate": 6.341978999897365e-05,
|
| 1190 |
+
"loss": 1.348,
|
| 1191 |
+
"step": 197
|
| 1192 |
+
},
|
| 1193 |
+
{
|
| 1194 |
+
"epoch": 0.63,
|
| 1195 |
+
"learning_rate": 6.245362205760704e-05,
|
| 1196 |
+
"loss": 1.0783,
|
| 1197 |
+
"step": 198
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"epoch": 0.64,
|
| 1201 |
+
"learning_rate": 6.149151714588009e-05,
|
| 1202 |
+
"loss": 1.4513,
|
| 1203 |
+
"step": 199
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.64,
|
| 1207 |
+
"learning_rate": 6.053357937665237e-05,
|
| 1208 |
+
"loss": 1.3207,
|
| 1209 |
+
"step": 200
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 0.64,
|
| 1213 |
+
"learning_rate": 5.957991241184184e-05,
|
| 1214 |
+
"loss": 1.3934,
|
| 1215 |
+
"step": 201
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"epoch": 0.65,
|
| 1219 |
+
"learning_rate": 5.863061945120719e-05,
|
| 1220 |
+
"loss": 1.1897,
|
| 1221 |
+
"step": 202
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 0.65,
|
| 1225 |
+
"learning_rate": 5.768580322118034e-05,
|
| 1226 |
+
"loss": 1.2173,
|
| 1227 |
+
"step": 203
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.65,
|
| 1231 |
+
"learning_rate": 5.6745565963749925e-05,
|
| 1232 |
+
"loss": 1.321,
|
| 1233 |
+
"step": 204
|
| 1234 |
+
},
|
| 1235 |
+
{
|
| 1236 |
+
"epoch": 0.66,
|
| 1237 |
+
"learning_rate": 5.5810009425397294e-05,
|
| 1238 |
+
"loss": 1.3495,
|
| 1239 |
+
"step": 205
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 0.66,
|
| 1243 |
+
"learning_rate": 5.487923484608629e-05,
|
| 1244 |
+
"loss": 1.1517,
|
| 1245 |
+
"step": 206
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.66,
|
| 1249 |
+
"learning_rate": 5.395334294830765e-05,
|
| 1250 |
+
"loss": 1.3929,
|
| 1251 |
+
"step": 207
|
| 1252 |
+
},
|
| 1253 |
+
{
|
| 1254 |
+
"epoch": 0.67,
|
| 1255 |
+
"learning_rate": 5.3032433926179395e-05,
|
| 1256 |
+
"loss": 1.5032,
|
| 1257 |
+
"step": 208
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 0.67,
|
| 1261 |
+
"learning_rate": 5.211660743460458e-05,
|
| 1262 |
+
"loss": 1.2021,
|
| 1263 |
+
"step": 209
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 0.67,
|
| 1267 |
+
"learning_rate": 5.1205962578487155e-05,
|
| 1268 |
+
"loss": 1.5604,
|
| 1269 |
+
"step": 210
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.68,
|
| 1273 |
+
"learning_rate": 5.030059790200756e-05,
|
| 1274 |
+
"loss": 1.251,
|
| 1275 |
+
"step": 211
|
| 1276 |
+
},
|
| 1277 |
+
{
|
| 1278 |
+
"epoch": 0.68,
|
| 1279 |
+
"learning_rate": 4.940061137795876e-05,
|
| 1280 |
+
"loss": 1.474,
|
| 1281 |
+
"step": 212
|
| 1282 |
+
},
|
| 1283 |
+
{
|
| 1284 |
+
"epoch": 0.68,
|
| 1285 |
+
"learning_rate": 4.850610039714444e-05,
|
| 1286 |
+
"loss": 1.1798,
|
| 1287 |
+
"step": 213
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.68,
|
| 1291 |
+
"learning_rate": 4.761716175783989e-05,
|
| 1292 |
+
"loss": 1.2076,
|
| 1293 |
+
"step": 214
|
| 1294 |
+
},
|
| 1295 |
+
{
|
| 1296 |
+
"epoch": 0.69,
|
| 1297 |
+
"learning_rate": 4.673389165531714e-05,
|
| 1298 |
+
"loss": 1.1569,
|
| 1299 |
+
"step": 215
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 0.69,
|
| 1303 |
+
"learning_rate": 4.585638567143529e-05,
|
| 1304 |
+
"loss": 1.0849,
|
| 1305 |
+
"step": 216
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 0.69,
|
| 1309 |
+
"learning_rate": 4.498473876429726e-05,
|
| 1310 |
+
"loss": 1.1121,
|
| 1311 |
+
"step": 217
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.7,
|
| 1315 |
+
"learning_rate": 4.411904525797408e-05,
|
| 1316 |
+
"loss": 1.4072,
|
| 1317 |
+
"step": 218
|
| 1318 |
+
},
|
| 1319 |
+
{
|
| 1320 |
+
"epoch": 0.7,
|
| 1321 |
+
"learning_rate": 4.325939883229766e-05,
|
| 1322 |
+
"loss": 1.2595,
|
| 1323 |
+
"step": 219
|
| 1324 |
+
},
|
| 1325 |
+
{
|
| 1326 |
+
"epoch": 0.7,
|
| 1327 |
+
"learning_rate": 4.240589251272342e-05,
|
| 1328 |
+
"loss": 1.2651,
|
| 1329 |
+
"step": 220
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.71,
|
| 1333 |
+
"learning_rate": 4.155861866026364e-05,
|
| 1334 |
+
"loss": 1.0955,
|
| 1335 |
+
"step": 221
|
| 1336 |
+
},
|
| 1337 |
+
{
|
| 1338 |
+
"epoch": 0.71,
|
| 1339 |
+
"learning_rate": 4.071766896149273e-05,
|
| 1340 |
+
"loss": 1.2663,
|
| 1341 |
+
"step": 222
|
| 1342 |
+
},
|
| 1343 |
+
{
|
| 1344 |
+
"epoch": 0.71,
|
| 1345 |
+
"learning_rate": 3.988313441862553e-05,
|
| 1346 |
+
"loss": 1.1684,
|
| 1347 |
+
"step": 223
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 0.72,
|
| 1351 |
+
"learning_rate": 3.9055105339669595e-05,
|
| 1352 |
+
"loss": 1.5317,
|
| 1353 |
+
"step": 224
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 0.72,
|
| 1357 |
+
"learning_rate": 3.823367132865265e-05,
|
| 1358 |
+
"loss": 1.3378,
|
| 1359 |
+
"step": 225
|
| 1360 |
+
},
|
| 1361 |
+
{
|
| 1362 |
+
"epoch": 0.72,
|
| 1363 |
+
"learning_rate": 3.741892127592625e-05,
|
| 1364 |
+
"loss": 1.2381,
|
| 1365 |
+
"step": 226
|
| 1366 |
+
},
|
| 1367 |
+
{
|
| 1368 |
+
"epoch": 0.73,
|
| 1369 |
+
"learning_rate": 3.6610943348546526e-05,
|
| 1370 |
+
"loss": 1.2223,
|
| 1371 |
+
"step": 227
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.73,
|
| 1375 |
+
"learning_rate": 3.580982498073344e-05,
|
| 1376 |
+
"loss": 1.4056,
|
| 1377 |
+
"step": 228
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 0.73,
|
| 1381 |
+
"learning_rate": 3.501565286440914e-05,
|
| 1382 |
+
"loss": 1.1969,
|
| 1383 |
+
"step": 229
|
| 1384 |
+
},
|
| 1385 |
+
{
|
| 1386 |
+
"epoch": 0.74,
|
| 1387 |
+
"learning_rate": 3.422851293981676e-05,
|
| 1388 |
+
"loss": 1.1027,
|
| 1389 |
+
"step": 230
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 0.74,
|
| 1393 |
+
"learning_rate": 3.3448490386220355e-05,
|
| 1394 |
+
"loss": 1.0746,
|
| 1395 |
+
"step": 231
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 0.74,
|
| 1399 |
+
"learning_rate": 3.2675669612687565e-05,
|
| 1400 |
+
"loss": 1.2298,
|
| 1401 |
+
"step": 232
|
| 1402 |
+
},
|
| 1403 |
+
{
|
| 1404 |
+
"epoch": 0.75,
|
| 1405 |
+
"learning_rate": 3.191013424895536e-05,
|
| 1406 |
+
"loss": 1.2005,
|
| 1407 |
+
"step": 233
|
| 1408 |
+
},
|
| 1409 |
+
{
|
| 1410 |
+
"epoch": 0.75,
|
| 1411 |
+
"learning_rate": 3.115196713638e-05,
|
| 1412 |
+
"loss": 1.0378,
|
| 1413 |
+
"step": 234
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.75,
|
| 1417 |
+
"learning_rate": 3.040125031897264e-05,
|
| 1418 |
+
"loss": 1.3243,
|
| 1419 |
+
"step": 235
|
| 1420 |
+
},
|
| 1421 |
+
{
|
| 1422 |
+
"epoch": 0.76,
|
| 1423 |
+
"learning_rate": 2.9658065034520978e-05,
|
| 1424 |
+
"loss": 1.2563,
|
| 1425 |
+
"step": 236
|
| 1426 |
+
},
|
| 1427 |
+
{
|
| 1428 |
+
"epoch": 0.76,
|
| 1429 |
+
"learning_rate": 2.892249170579826e-05,
|
| 1430 |
+
"loss": 1.2879,
|
| 1431 |
+
"step": 237
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 0.76,
|
| 1435 |
+
"learning_rate": 2.8194609931860316e-05,
|
| 1436 |
+
"loss": 1.1762,
|
| 1437 |
+
"step": 238
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 0.76,
|
| 1441 |
+
"learning_rate": 2.7474498479432087e-05,
|
| 1442 |
+
"loss": 1.1478,
|
| 1443 |
+
"step": 239
|
| 1444 |
+
},
|
| 1445 |
+
{
|
| 1446 |
+
"epoch": 0.77,
|
| 1447 |
+
"learning_rate": 2.6762235274383772e-05,
|
| 1448 |
+
"loss": 1.2598,
|
| 1449 |
+
"step": 240
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 0.77,
|
| 1453 |
+
"learning_rate": 2.6057897393298324e-05,
|
| 1454 |
+
"loss": 1.3739,
|
| 1455 |
+
"step": 241
|
| 1456 |
+
},
|
| 1457 |
+
{
|
| 1458 |
+
"epoch": 0.77,
|
| 1459 |
+
"learning_rate": 2.536156105513062e-05,
|
| 1460 |
+
"loss": 1.2612,
|
| 1461 |
+
"step": 242
|
| 1462 |
+
},
|
| 1463 |
+
{
|
| 1464 |
+
"epoch": 0.78,
|
| 1465 |
+
"learning_rate": 2.4673301612959654e-05,
|
| 1466 |
+
"loss": 1.2202,
|
| 1467 |
+
"step": 243
|
| 1468 |
+
},
|
| 1469 |
+
{
|
| 1470 |
+
"epoch": 0.78,
|
| 1471 |
+
"learning_rate": 2.399319354583418e-05,
|
| 1472 |
+
"loss": 1.1055,
|
| 1473 |
+
"step": 244
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 0.78,
|
| 1477 |
+
"learning_rate": 2.3321310450713062e-05,
|
| 1478 |
+
"loss": 1.3746,
|
| 1479 |
+
"step": 245
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 0.79,
|
| 1483 |
+
"learning_rate": 2.265772503450122e-05,
|
| 1484 |
+
"loss": 1.3418,
|
| 1485 |
+
"step": 246
|
| 1486 |
+
},
|
| 1487 |
+
{
|
| 1488 |
+
"epoch": 0.79,
|
| 1489 |
+
"learning_rate": 2.2002509106181624e-05,
|
| 1490 |
+
"loss": 1.3636,
|
| 1491 |
+
"step": 247
|
| 1492 |
+
},
|
| 1493 |
+
{
|
| 1494 |
+
"epoch": 0.79,
|
| 1495 |
+
"learning_rate": 2.1355733569044635e-05,
|
| 1496 |
+
"loss": 1.3,
|
| 1497 |
+
"step": 248
|
| 1498 |
+
},
|
| 1499 |
+
{
|
| 1500 |
+
"epoch": 0.8,
|
| 1501 |
+
"learning_rate": 2.0717468413015283e-05,
|
| 1502 |
+
"loss": 1.2459,
|
| 1503 |
+
"step": 249
|
| 1504 |
+
},
|
| 1505 |
+
{
|
| 1506 |
+
"epoch": 0.8,
|
| 1507 |
+
"learning_rate": 2.008778270707944e-05,
|
| 1508 |
+
"loss": 1.3297,
|
| 1509 |
+
"step": 250
|
| 1510 |
+
},
|
| 1511 |
+
{
|
| 1512 |
+
"epoch": 0.8,
|
| 1513 |
+
"learning_rate": 1.946674459180955e-05,
|
| 1514 |
+
"loss": 1.1628,
|
| 1515 |
+
"step": 251
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 0.81,
|
| 1519 |
+
"learning_rate": 1.8854421271990964e-05,
|
| 1520 |
+
"loss": 1.0611,
|
| 1521 |
+
"step": 252
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 0.81,
|
| 1525 |
+
"learning_rate": 1.8250879009349398e-05,
|
| 1526 |
+
"loss": 1.2078,
|
| 1527 |
+
"step": 253
|
| 1528 |
+
},
|
| 1529 |
+
{
|
| 1530 |
+
"epoch": 0.81,
|
| 1531 |
+
"learning_rate": 1.7656183115380577e-05,
|
| 1532 |
+
"loss": 1.072,
|
| 1533 |
+
"step": 254
|
| 1534 |
+
},
|
| 1535 |
+
{
|
| 1536 |
+
"epoch": 0.82,
|
| 1537 |
+
"learning_rate": 1.707039794428259e-05,
|
| 1538 |
+
"loss": 1.3753,
|
| 1539 |
+
"step": 255
|
| 1540 |
+
},
|
| 1541 |
+
{
|
| 1542 |
+
"epoch": 0.82,
|
| 1543 |
+
"learning_rate": 1.649358688599191e-05,
|
| 1544 |
+
"loss": 1.2396,
|
| 1545 |
+
"step": 256
|
| 1546 |
+
},
|
| 1547 |
+
{
|
| 1548 |
+
"epoch": 0.82,
|
| 1549 |
+
"learning_rate": 1.5925812359323745e-05,
|
| 1550 |
+
"loss": 1.02,
|
| 1551 |
+
"step": 257
|
| 1552 |
+
},
|
| 1553 |
+
{
|
| 1554 |
+
"epoch": 0.83,
|
| 1555 |
+
"learning_rate": 1.5367135805217458e-05,
|
| 1556 |
+
"loss": 1.1991,
|
| 1557 |
+
"step": 258
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 0.83,
|
| 1561 |
+
"learning_rate": 1.4817617680087825e-05,
|
| 1562 |
+
"loss": 1.4701,
|
| 1563 |
+
"step": 259
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 0.83,
|
| 1567 |
+
"learning_rate": 1.4277317449282834e-05,
|
| 1568 |
+
"loss": 1.1954,
|
| 1569 |
+
"step": 260
|
| 1570 |
+
},
|
| 1571 |
+
{
|
| 1572 |
+
"epoch": 0.84,
|
| 1573 |
+
"learning_rate": 1.3746293580648717e-05,
|
| 1574 |
+
"loss": 1.2761,
|
| 1575 |
+
"step": 261
|
| 1576 |
+
},
|
| 1577 |
+
{
|
| 1578 |
+
"epoch": 0.84,
|
| 1579 |
+
"learning_rate": 1.3224603538202929e-05,
|
| 1580 |
+
"loss": 1.1929,
|
| 1581 |
+
"step": 262
|
| 1582 |
+
},
|
| 1583 |
+
{
|
| 1584 |
+
"epoch": 0.84,
|
| 1585 |
+
"learning_rate": 1.2712303775915802e-05,
|
| 1586 |
+
"loss": 1.2954,
|
| 1587 |
+
"step": 263
|
| 1588 |
+
},
|
| 1589 |
+
{
|
| 1590 |
+
"epoch": 0.84,
|
| 1591 |
+
"learning_rate": 1.220944973160133e-05,
|
| 1592 |
+
"loss": 1.253,
|
| 1593 |
+
"step": 264
|
| 1594 |
+
},
|
| 1595 |
+
{
|
| 1596 |
+
"epoch": 0.85,
|
| 1597 |
+
"learning_rate": 1.1716095820918216e-05,
|
| 1598 |
+
"loss": 1.0924,
|
| 1599 |
+
"step": 265
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 0.85,
|
| 1603 |
+
"learning_rate": 1.1232295431481222e-05,
|
| 1604 |
+
"loss": 1.1281,
|
| 1605 |
+
"step": 266
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 0.85,
|
| 1609 |
+
"learning_rate": 1.0758100917083991e-05,
|
| 1610 |
+
"loss": 1.2917,
|
| 1611 |
+
"step": 267
|
| 1612 |
+
},
|
| 1613 |
+
{
|
| 1614 |
+
"epoch": 0.86,
|
| 1615 |
+
"learning_rate": 1.0293563592033595e-05,
|
| 1616 |
+
"loss": 1.2331,
|
| 1617 |
+
"step": 268
|
| 1618 |
+
},
|
| 1619 |
+
{
|
| 1620 |
+
"epoch": 0.86,
|
| 1621 |
+
"learning_rate": 9.838733725597615e-06,
|
| 1622 |
+
"loss": 1.0373,
|
| 1623 |
+
"step": 269
|
| 1624 |
+
},
|
| 1625 |
+
{
|
| 1626 |
+
"epoch": 0.86,
|
| 1627 |
+
"learning_rate": 9.393660536564408e-06,
|
| 1628 |
+
"loss": 1.2092,
|
| 1629 |
+
"step": 270
|
| 1630 |
+
},
|
| 1631 |
+
{
|
| 1632 |
+
"epoch": 0.87,
|
| 1633 |
+
"learning_rate": 8.958392187916841e-06,
|
| 1634 |
+
"loss": 1.3602,
|
| 1635 |
+
"step": 271
|
| 1636 |
+
},
|
| 1637 |
+
{
|
| 1638 |
+
"epoch": 0.87,
|
| 1639 |
+
"learning_rate": 8.532975781620512e-06,
|
| 1640 |
+
"loss": 1.0881,
|
| 1641 |
+
"step": 272
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 0.87,
|
| 1645 |
+
"learning_rate": 8.117457353526625e-06,
|
| 1646 |
+
"loss": 1.2997,
|
| 1647 |
+
"step": 273
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 0.88,
|
| 1651 |
+
"learning_rate": 7.711881868390291e-06,
|
| 1652 |
+
"loss": 1.1992,
|
| 1653 |
+
"step": 274
|
| 1654 |
+
},
|
| 1655 |
+
{
|
| 1656 |
+
"epoch": 0.88,
|
| 1657 |
+
"learning_rate": 7.3162932150046885e-06,
|
| 1658 |
+
"loss": 1.198,
|
| 1659 |
+
"step": 275
|
| 1660 |
+
},
|
| 1661 |
+
{
|
| 1662 |
+
"epoch": 0.88,
|
| 1663 |
+
"learning_rate": 6.930734201451816e-06,
|
| 1664 |
+
"loss": 1.2064,
|
| 1665 |
+
"step": 276
|
| 1666 |
+
},
|
| 1667 |
+
{
|
| 1668 |
+
"epoch": 0.89,
|
| 1669 |
+
"learning_rate": 6.555246550469907e-06,
|
| 1670 |
+
"loss": 1.3395,
|
| 1671 |
+
"step": 277
|
| 1672 |
+
},
|
| 1673 |
+
{
|
| 1674 |
+
"epoch": 0.89,
|
| 1675 |
+
"learning_rate": 6.189870894938587e-06,
|
| 1676 |
+
"loss": 1.1888,
|
| 1677 |
+
"step": 278
|
| 1678 |
+
},
|
| 1679 |
+
{
|
| 1680 |
+
"epoch": 0.89,
|
| 1681 |
+
"learning_rate": 5.834646773481811e-06,
|
| 1682 |
+
"loss": 1.2374,
|
| 1683 |
+
"step": 279
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 0.9,
|
| 1687 |
+
"learning_rate": 5.489612626189245e-06,
|
| 1688 |
+
"loss": 1.149,
|
| 1689 |
+
"step": 280
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 0.9,
|
| 1693 |
+
"learning_rate": 5.154805790456485e-06,
|
| 1694 |
+
"loss": 1.3549,
|
| 1695 |
+
"step": 281
|
| 1696 |
+
},
|
| 1697 |
+
{
|
| 1698 |
+
"epoch": 0.9,
|
| 1699 |
+
"learning_rate": 4.830262496944693e-06,
|
| 1700 |
+
"loss": 1.3259,
|
| 1701 |
+
"step": 282
|
| 1702 |
+
},
|
| 1703 |
+
{
|
| 1704 |
+
"epoch": 0.91,
|
| 1705 |
+
"learning_rate": 4.516017865659949e-06,
|
| 1706 |
+
"loss": 1.2184,
|
| 1707 |
+
"step": 283
|
| 1708 |
+
},
|
| 1709 |
+
{
|
| 1710 |
+
"epoch": 0.91,
|
| 1711 |
+
"learning_rate": 4.21210590215273e-06,
|
| 1712 |
+
"loss": 1.2918,
|
| 1713 |
+
"step": 284
|
| 1714 |
+
},
|
| 1715 |
+
{
|
| 1716 |
+
"epoch": 0.91,
|
| 1717 |
+
"learning_rate": 3.918559493838114e-06,
|
| 1718 |
+
"loss": 1.2417,
|
| 1719 |
+
"step": 285
|
| 1720 |
+
},
|
| 1721 |
+
{
|
| 1722 |
+
"epoch": 0.92,
|
| 1723 |
+
"learning_rate": 3.6354104064368566e-06,
|
| 1724 |
+
"loss": 1.4384,
|
| 1725 |
+
"step": 286
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 0.92,
|
| 1729 |
+
"learning_rate": 3.3626892805379562e-06,
|
| 1730 |
+
"loss": 1.3165,
|
| 1731 |
+
"step": 287
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 0.92,
|
| 1735 |
+
"learning_rate": 3.100425628282899e-06,
|
| 1736 |
+
"loss": 1.2784,
|
| 1737 |
+
"step": 288
|
| 1738 |
+
},
|
| 1739 |
+
{
|
| 1740 |
+
"epoch": 0.92,
|
| 1741 |
+
"learning_rate": 2.848647830172024e-06,
|
| 1742 |
+
"loss": 1.5392,
|
| 1743 |
+
"step": 289
|
| 1744 |
+
},
|
| 1745 |
+
{
|
| 1746 |
+
"epoch": 0.93,
|
| 1747 |
+
"learning_rate": 2.607383131993424e-06,
|
| 1748 |
+
"loss": 1.0516,
|
| 1749 |
+
"step": 290
|
| 1750 |
+
},
|
| 1751 |
+
{
|
| 1752 |
+
"epoch": 0.93,
|
| 1753 |
+
"learning_rate": 2.3766576418745022e-06,
|
| 1754 |
+
"loss": 1.3022,
|
| 1755 |
+
"step": 291
|
| 1756 |
+
},
|
| 1757 |
+
{
|
| 1758 |
+
"epoch": 0.93,
|
| 1759 |
+
"learning_rate": 2.1564963274568027e-06,
|
| 1760 |
+
"loss": 1.2401,
|
| 1761 |
+
"step": 292
|
| 1762 |
+
},
|
| 1763 |
+
{
|
| 1764 |
+
"epoch": 0.94,
|
| 1765 |
+
"learning_rate": 1.9469230131940907e-06,
|
| 1766 |
+
"loss": 1.1793,
|
| 1767 |
+
"step": 293
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 0.94,
|
| 1771 |
+
"learning_rate": 1.7479603777742938e-06,
|
| 1772 |
+
"loss": 1.3182,
|
| 1773 |
+
"step": 294
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 0.94,
|
| 1777 |
+
"learning_rate": 1.559629951665298e-06,
|
| 1778 |
+
"loss": 1.1788,
|
| 1779 |
+
"step": 295
|
| 1780 |
+
},
|
| 1781 |
+
{
|
| 1782 |
+
"epoch": 0.95,
|
| 1783 |
+
"learning_rate": 1.3819521147851123e-06,
|
| 1784 |
+
"loss": 1.3857,
|
| 1785 |
+
"step": 296
|
| 1786 |
+
},
|
| 1787 |
+
{
|
| 1788 |
+
"epoch": 0.95,
|
| 1789 |
+
"learning_rate": 1.2149460942964098e-06,
|
| 1790 |
+
"loss": 1.1947,
|
| 1791 |
+
"step": 297
|
| 1792 |
+
},
|
| 1793 |
+
{
|
| 1794 |
+
"epoch": 0.95,
|
| 1795 |
+
"learning_rate": 1.05862996252597e-06,
|
| 1796 |
+
"loss": 1.2379,
|
| 1797 |
+
"step": 298
|
| 1798 |
+
},
|
| 1799 |
+
{
|
| 1800 |
+
"epoch": 0.96,
|
| 1801 |
+
"learning_rate": 9.130206350089765e-07,
|
| 1802 |
+
"loss": 1.0906,
|
| 1803 |
+
"step": 299
|
| 1804 |
+
},
|
| 1805 |
+
{
|
| 1806 |
+
"epoch": 0.96,
|
| 1807 |
+
"learning_rate": 7.781338686584927e-07,
|
| 1808 |
+
"loss": 1.181,
|
| 1809 |
+
"step": 300
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 0.96,
|
| 1813 |
+
"learning_rate": 6.539842600603918e-07,
|
| 1814 |
+
"loss": 1.2511,
|
| 1815 |
+
"step": 301
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 0.97,
|
| 1819 |
+
"learning_rate": 5.405852438937764e-07,
|
| 1820 |
+
"loss": 1.3397,
|
| 1821 |
+
"step": 302
|
| 1822 |
+
},
|
| 1823 |
+
{
|
| 1824 |
+
"epoch": 0.97,
|
| 1825 |
+
"learning_rate": 4.3794909147720773e-07,
|
| 1826 |
+
"loss": 1.1058,
|
| 1827 |
+
"step": 303
|
| 1828 |
+
},
|
| 1829 |
+
{
|
| 1830 |
+
"epoch": 0.97,
|
| 1831 |
+
"learning_rate": 3.4608690944071263e-07,
|
| 1832 |
+
"loss": 1.258,
|
| 1833 |
+
"step": 304
|
| 1834 |
+
},
|
| 1835 |
+
{
|
| 1836 |
+
"epoch": 0.98,
|
| 1837 |
+
"learning_rate": 2.6500863852395584e-07,
|
| 1838 |
+
"loss": 1.4846,
|
| 1839 |
+
"step": 305
|
| 1840 |
+
},
|
| 1841 |
+
{
|
| 1842 |
+
"epoch": 0.98,
|
| 1843 |
+
"learning_rate": 1.947230525005006e-07,
|
| 1844 |
+
"loss": 1.2382,
|
| 1845 |
+
"step": 306
|
| 1846 |
+
},
|
| 1847 |
+
{
|
| 1848 |
+
"epoch": 0.98,
|
| 1849 |
+
"learning_rate": 1.3523775722834587e-07,
|
| 1850 |
+
"loss": 1.3235,
|
| 1851 |
+
"step": 307
|
| 1852 |
+
},
|
| 1853 |
+
{
|
| 1854 |
+
"epoch": 0.99,
|
| 1855 |
+
"learning_rate": 8.655918982689581e-08,
|
| 1856 |
+
"loss": 1.2589,
|
| 1857 |
+
"step": 308
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 0.99,
|
| 1861 |
+
"learning_rate": 4.8692617980350406e-08,
|
| 1862 |
+
"loss": 1.2572,
|
| 1863 |
+
"step": 309
|
| 1864 |
+
},
|
| 1865 |
+
{
|
| 1866 |
+
"epoch": 0.99,
|
| 1867 |
+
"learning_rate": 2.164213936770576e-08,
|
| 1868 |
+
"loss": 1.1785,
|
| 1869 |
+
"step": 310
|
| 1870 |
+
},
|
| 1871 |
+
{
|
| 1872 |
+
"epoch": 1.0,
|
| 1873 |
+
"learning_rate": 5.410681219286673e-09,
|
| 1874 |
+
"loss": 1.1204,
|
| 1875 |
+
"step": 311
|
| 1876 |
+
},
|
| 1877 |
+
{
|
| 1878 |
+
"epoch": 1.0,
|
| 1879 |
+
"learning_rate": 0.0,
|
| 1880 |
+
"loss": 1.0616,
|
| 1881 |
+
"step": 312
|
| 1882 |
+
},
|
| 1883 |
+
{
|
| 1884 |
+
"epoch": 1.0,
|
| 1885 |
+
"step": 312,
|
| 1886 |
+
"total_flos": 3.181343428260659e+16,
|
| 1887 |
+
"train_loss": 1.4551883145020559,
|
| 1888 |
+
"train_runtime": 2400.5166,
|
| 1889 |
+
"train_samples_per_second": 2.083,
|
| 1890 |
+
"train_steps_per_second": 0.13
|
| 1891 |
+
}
|
| 1892 |
+
],
|
| 1893 |
+
"logging_steps": 1.0,
|
| 1894 |
+
"max_steps": 312,
|
| 1895 |
+
"num_input_tokens_seen": 0,
|
| 1896 |
+
"num_train_epochs": 1,
|
| 1897 |
+
"save_steps": 50000,
|
| 1898 |
+
"total_flos": 3.181343428260659e+16,
|
| 1899 |
+
"train_batch_size": 2,
|
| 1900 |
+
"trial_name": null,
|
| 1901 |
+
"trial_params": null
|
| 1902 |
+
}
|