SFT checkpoint-4610 (loss 0.8109576225280761)
Browse files- .gitattributes +1 -0
- checkpoint-4610/README.md +207 -0
- checkpoint-4610/adapter_config.json +43 -0
- checkpoint-4610/adapter_model.safetensors +3 -0
- checkpoint-4610/chat_template.jinja +3 -0
- checkpoint-4610/optimizer.pt +3 -0
- checkpoint-4610/rng_state.pth +3 -0
- checkpoint-4610/scaler.pt +3 -0
- checkpoint-4610/scheduler.pt +3 -0
- checkpoint-4610/tokenizer.json +3 -0
- checkpoint-4610/tokenizer_config.json +19 -0
- checkpoint-4610/trainer_state.json +3261 -0
- checkpoint-4610/training_args.bin +3 -0
.gitattributes
CHANGED
|
@@ -50,3 +50,4 @@ checkpoint-3600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
| 50 |
checkpoint-3900/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 51 |
checkpoint-4200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 52 |
checkpoint-4500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 50 |
checkpoint-3900/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 51 |
checkpoint-4200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 52 |
checkpoint-4500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 53 |
+
checkpoint-4610/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
checkpoint-4610/README.md
ADDED
|
@@ -0,0 +1,207 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: google/gemma-2-9b
|
| 3 |
+
library_name: peft
|
| 4 |
+
pipeline_tag: text-generation
|
| 5 |
+
tags:
|
| 6 |
+
- base_model:adapter:google/gemma-2-9b
|
| 7 |
+
- lora
|
| 8 |
+
- transformers
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
# Model Card for Model ID
|
| 12 |
+
|
| 13 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 14 |
+
|
| 15 |
+
|
| 16 |
+
|
| 17 |
+
## Model Details
|
| 18 |
+
|
| 19 |
+
### Model Description
|
| 20 |
+
|
| 21 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 22 |
+
|
| 23 |
+
|
| 24 |
+
|
| 25 |
+
- **Developed by:** [More Information Needed]
|
| 26 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 27 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 28 |
+
- **Model type:** [More Information Needed]
|
| 29 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 30 |
+
- **License:** [More Information Needed]
|
| 31 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 32 |
+
|
| 33 |
+
### Model Sources [optional]
|
| 34 |
+
|
| 35 |
+
<!-- Provide the basic links for the model. -->
|
| 36 |
+
|
| 37 |
+
- **Repository:** [More Information Needed]
|
| 38 |
+
- **Paper [optional]:** [More Information Needed]
|
| 39 |
+
- **Demo [optional]:** [More Information Needed]
|
| 40 |
+
|
| 41 |
+
## Uses
|
| 42 |
+
|
| 43 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 44 |
+
|
| 45 |
+
### Direct Use
|
| 46 |
+
|
| 47 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 48 |
+
|
| 49 |
+
[More Information Needed]
|
| 50 |
+
|
| 51 |
+
### Downstream Use [optional]
|
| 52 |
+
|
| 53 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 54 |
+
|
| 55 |
+
[More Information Needed]
|
| 56 |
+
|
| 57 |
+
### Out-of-Scope Use
|
| 58 |
+
|
| 59 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 60 |
+
|
| 61 |
+
[More Information Needed]
|
| 62 |
+
|
| 63 |
+
## Bias, Risks, and Limitations
|
| 64 |
+
|
| 65 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 66 |
+
|
| 67 |
+
[More Information Needed]
|
| 68 |
+
|
| 69 |
+
### Recommendations
|
| 70 |
+
|
| 71 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 72 |
+
|
| 73 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 74 |
+
|
| 75 |
+
## How to Get Started with the Model
|
| 76 |
+
|
| 77 |
+
Use the code below to get started with the model.
|
| 78 |
+
|
| 79 |
+
[More Information Needed]
|
| 80 |
+
|
| 81 |
+
## Training Details
|
| 82 |
+
|
| 83 |
+
### Training Data
|
| 84 |
+
|
| 85 |
+
<!-- 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. -->
|
| 86 |
+
|
| 87 |
+
[More Information Needed]
|
| 88 |
+
|
| 89 |
+
### Training Procedure
|
| 90 |
+
|
| 91 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 92 |
+
|
| 93 |
+
#### Preprocessing [optional]
|
| 94 |
+
|
| 95 |
+
[More Information Needed]
|
| 96 |
+
|
| 97 |
+
|
| 98 |
+
#### Training Hyperparameters
|
| 99 |
+
|
| 100 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 101 |
+
|
| 102 |
+
#### Speeds, Sizes, Times [optional]
|
| 103 |
+
|
| 104 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 105 |
+
|
| 106 |
+
[More Information Needed]
|
| 107 |
+
|
| 108 |
+
## Evaluation
|
| 109 |
+
|
| 110 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 111 |
+
|
| 112 |
+
### Testing Data, Factors & Metrics
|
| 113 |
+
|
| 114 |
+
#### Testing Data
|
| 115 |
+
|
| 116 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 117 |
+
|
| 118 |
+
[More Information Needed]
|
| 119 |
+
|
| 120 |
+
#### Factors
|
| 121 |
+
|
| 122 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 123 |
+
|
| 124 |
+
[More Information Needed]
|
| 125 |
+
|
| 126 |
+
#### Metrics
|
| 127 |
+
|
| 128 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 129 |
+
|
| 130 |
+
[More Information Needed]
|
| 131 |
+
|
| 132 |
+
### Results
|
| 133 |
+
|
| 134 |
+
[More Information Needed]
|
| 135 |
+
|
| 136 |
+
#### Summary
|
| 137 |
+
|
| 138 |
+
|
| 139 |
+
|
| 140 |
+
## Model Examination [optional]
|
| 141 |
+
|
| 142 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 143 |
+
|
| 144 |
+
[More Information Needed]
|
| 145 |
+
|
| 146 |
+
## Environmental Impact
|
| 147 |
+
|
| 148 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 149 |
+
|
| 150 |
+
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).
|
| 151 |
+
|
| 152 |
+
- **Hardware Type:** [More Information Needed]
|
| 153 |
+
- **Hours used:** [More Information Needed]
|
| 154 |
+
- **Cloud Provider:** [More Information Needed]
|
| 155 |
+
- **Compute Region:** [More Information Needed]
|
| 156 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 157 |
+
|
| 158 |
+
## Technical Specifications [optional]
|
| 159 |
+
|
| 160 |
+
### Model Architecture and Objective
|
| 161 |
+
|
| 162 |
+
[More Information Needed]
|
| 163 |
+
|
| 164 |
+
### Compute Infrastructure
|
| 165 |
+
|
| 166 |
+
[More Information Needed]
|
| 167 |
+
|
| 168 |
+
#### Hardware
|
| 169 |
+
|
| 170 |
+
[More Information Needed]
|
| 171 |
+
|
| 172 |
+
#### Software
|
| 173 |
+
|
| 174 |
+
[More Information Needed]
|
| 175 |
+
|
| 176 |
+
## Citation [optional]
|
| 177 |
+
|
| 178 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 179 |
+
|
| 180 |
+
**BibTeX:**
|
| 181 |
+
|
| 182 |
+
[More Information Needed]
|
| 183 |
+
|
| 184 |
+
**APA:**
|
| 185 |
+
|
| 186 |
+
[More Information Needed]
|
| 187 |
+
|
| 188 |
+
## Glossary [optional]
|
| 189 |
+
|
| 190 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 191 |
+
|
| 192 |
+
[More Information Needed]
|
| 193 |
+
|
| 194 |
+
## More Information [optional]
|
| 195 |
+
|
| 196 |
+
[More Information Needed]
|
| 197 |
+
|
| 198 |
+
## Model Card Authors [optional]
|
| 199 |
+
|
| 200 |
+
[More Information Needed]
|
| 201 |
+
|
| 202 |
+
## Model Card Contact
|
| 203 |
+
|
| 204 |
+
[More Information Needed]
|
| 205 |
+
### Framework versions
|
| 206 |
+
|
| 207 |
+
- PEFT 0.18.1
|
checkpoint-4610/adapter_config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alora_invocation_tokens": null,
|
| 3 |
+
"alpha_pattern": {},
|
| 4 |
+
"arrow_config": null,
|
| 5 |
+
"auto_mapping": null,
|
| 6 |
+
"base_model_name_or_path": "google/gemma-2-9b",
|
| 7 |
+
"bias": "none",
|
| 8 |
+
"corda_config": null,
|
| 9 |
+
"ensure_weight_tying": false,
|
| 10 |
+
"eva_config": null,
|
| 11 |
+
"exclude_modules": null,
|
| 12 |
+
"fan_in_fan_out": false,
|
| 13 |
+
"inference_mode": true,
|
| 14 |
+
"init_lora_weights": true,
|
| 15 |
+
"layer_replication": null,
|
| 16 |
+
"layers_pattern": null,
|
| 17 |
+
"layers_to_transform": null,
|
| 18 |
+
"loftq_config": {},
|
| 19 |
+
"lora_alpha": 64,
|
| 20 |
+
"lora_bias": false,
|
| 21 |
+
"lora_dropout": 0.05,
|
| 22 |
+
"megatron_config": null,
|
| 23 |
+
"megatron_core": "megatron.core",
|
| 24 |
+
"modules_to_save": null,
|
| 25 |
+
"peft_type": "LORA",
|
| 26 |
+
"peft_version": "0.18.1",
|
| 27 |
+
"qalora_group_size": 16,
|
| 28 |
+
"r": 32,
|
| 29 |
+
"rank_pattern": {},
|
| 30 |
+
"revision": null,
|
| 31 |
+
"target_modules": [
|
| 32 |
+
"k_proj",
|
| 33 |
+
"q_proj",
|
| 34 |
+
"o_proj",
|
| 35 |
+
"v_proj"
|
| 36 |
+
],
|
| 37 |
+
"target_parameters": null,
|
| 38 |
+
"task_type": "CAUSAL_LM",
|
| 39 |
+
"trainable_token_indices": null,
|
| 40 |
+
"use_dora": false,
|
| 41 |
+
"use_qalora": false,
|
| 42 |
+
"use_rslora": false
|
| 43 |
+
}
|
checkpoint-4610/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c8ed9f488513da7bc7b23dc79de78b24a8a05e0806ffc0b8f105922b05412265
|
| 3 |
+
size 7745357608
|
checkpoint-4610/chat_template.jinja
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{% for message in messages %}<|im_start|>{{ message.role }}
|
| 2 |
+
{{ message.content }}<|im_end|>
|
| 3 |
+
{% endfor %}
|
checkpoint-4610/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aa8be18565aa9701834d9780468265c33723451e26f34d2f0e0a734b6bad96dc
|
| 3 |
+
size 286549651
|
checkpoint-4610/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b3e72f9c2e46edd34a58823ecd75ab50b6020ac1ea780f07dd849afc1f2144a2
|
| 3 |
+
size 14645
|
checkpoint-4610/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1aca501aa57bafc06a184dfc77f5cfa6bf7ba53014d979f783253773fe306e5c
|
| 3 |
+
size 1383
|
checkpoint-4610/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7c0e05fb40b56901b91d188a57ccf572da2eae8f3bfc92cf2141cd9c2815cb84
|
| 3 |
+
size 1465
|
checkpoint-4610/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7f2b28401239ea54549b69663eba4d452433425a3a42eadef0e50d7838e73113
|
| 3 |
+
size 36243847
|
checkpoint-4610/tokenizer_config.json
ADDED
|
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"backend": "tokenizers",
|
| 3 |
+
"bos_token": "<bos>",
|
| 4 |
+
"clean_up_tokenization_spaces": false,
|
| 5 |
+
"eos_token": "<eos>",
|
| 6 |
+
"extra_special_tokens": [
|
| 7 |
+
"<start_of_turn>",
|
| 8 |
+
"<end_of_turn>"
|
| 9 |
+
],
|
| 10 |
+
"is_local": false,
|
| 11 |
+
"mask_token": "<mask>",
|
| 12 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 13 |
+
"pad_token": "<pad>",
|
| 14 |
+
"sp_model_kwargs": {},
|
| 15 |
+
"spaces_between_special_tokens": false,
|
| 16 |
+
"tokenizer_class": "GemmaTokenizer",
|
| 17 |
+
"unk_token": "<unk>",
|
| 18 |
+
"use_default_system_prompt": false
|
| 19 |
+
}
|
checkpoint-4610/trainer_state.json
ADDED
|
@@ -0,0 +1,3261 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.3557441882897656,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 4610,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.0007716793672229189,
|
| 14 |
+
"grad_norm": 0.16996131837368011,
|
| 15 |
+
"learning_rate": 1.3899613899613899e-06,
|
| 16 |
+
"loss": 1.937258529663086,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.0015433587344458378,
|
| 21 |
+
"grad_norm": 0.1882886439561844,
|
| 22 |
+
"learning_rate": 2.9343629343629344e-06,
|
| 23 |
+
"loss": 1.773158073425293,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.0023150381016687565,
|
| 28 |
+
"grad_norm": 0.20707373321056366,
|
| 29 |
+
"learning_rate": 4.478764478764479e-06,
|
| 30 |
+
"loss": 1.7095542907714845,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.0030867174688916756,
|
| 35 |
+
"grad_norm": 0.18671941757202148,
|
| 36 |
+
"learning_rate": 6.023166023166024e-06,
|
| 37 |
+
"loss": 1.6669628143310546,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.0038583968361145943,
|
| 42 |
+
"grad_norm": 0.14743703603744507,
|
| 43 |
+
"learning_rate": 7.567567567567568e-06,
|
| 44 |
+
"loss": 1.5012624740600586,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.004630076203337513,
|
| 49 |
+
"grad_norm": 0.13592934608459473,
|
| 50 |
+
"learning_rate": 9.111969111969113e-06,
|
| 51 |
+
"loss": 1.3985330581665039,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.0054017555705604325,
|
| 56 |
+
"grad_norm": 0.16905024647712708,
|
| 57 |
+
"learning_rate": 1.0656370656370657e-05,
|
| 58 |
+
"loss": 1.3338945388793946,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.006173434937783351,
|
| 63 |
+
"grad_norm": 0.1601494997739792,
|
| 64 |
+
"learning_rate": 1.2200772200772201e-05,
|
| 65 |
+
"loss": 1.3430834770202638,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.00694511430500627,
|
| 70 |
+
"grad_norm": 0.131796196103096,
|
| 71 |
+
"learning_rate": 1.3745173745173745e-05,
|
| 72 |
+
"loss": 1.3148032188415528,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.0077167936722291885,
|
| 77 |
+
"grad_norm": 0.13276071846485138,
|
| 78 |
+
"learning_rate": 1.5289575289575288e-05,
|
| 79 |
+
"loss": 1.2003187179565429,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.008488473039452108,
|
| 84 |
+
"grad_norm": 0.16983681917190552,
|
| 85 |
+
"learning_rate": 1.6833976833976835e-05,
|
| 86 |
+
"loss": 1.2972237586975097,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.009260152406675026,
|
| 91 |
+
"grad_norm": 0.18364885449409485,
|
| 92 |
+
"learning_rate": 1.837837837837838e-05,
|
| 93 |
+
"loss": 1.2159050941467284,
|
| 94 |
+
"step": 120
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.010031831773897945,
|
| 98 |
+
"grad_norm": 0.16437186300754547,
|
| 99 |
+
"learning_rate": 1.9922779922779923e-05,
|
| 100 |
+
"loss": 1.2633441925048827,
|
| 101 |
+
"step": 130
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.010803511141120865,
|
| 105 |
+
"grad_norm": 0.20116814970970154,
|
| 106 |
+
"learning_rate": 2.1467181467181467e-05,
|
| 107 |
+
"loss": 1.2092578887939454,
|
| 108 |
+
"step": 140
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.011575190508343783,
|
| 112 |
+
"grad_norm": 0.1781621277332306,
|
| 113 |
+
"learning_rate": 2.301158301158301e-05,
|
| 114 |
+
"loss": 1.186624526977539,
|
| 115 |
+
"step": 150
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.012346869875566702,
|
| 119 |
+
"grad_norm": 0.18782109022140503,
|
| 120 |
+
"learning_rate": 2.4555984555984556e-05,
|
| 121 |
+
"loss": 1.099991512298584,
|
| 122 |
+
"step": 160
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.01311854924278962,
|
| 126 |
+
"grad_norm": 0.1972387135028839,
|
| 127 |
+
"learning_rate": 2.6100386100386103e-05,
|
| 128 |
+
"loss": 1.121781826019287,
|
| 129 |
+
"step": 170
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.01389022861001254,
|
| 133 |
+
"grad_norm": 0.1974383294582367,
|
| 134 |
+
"learning_rate": 2.7644787644787644e-05,
|
| 135 |
+
"loss": 1.1148104667663574,
|
| 136 |
+
"step": 180
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.01466190797723546,
|
| 140 |
+
"grad_norm": 0.20797985792160034,
|
| 141 |
+
"learning_rate": 2.918918918918919e-05,
|
| 142 |
+
"loss": 1.1362589836120605,
|
| 143 |
+
"step": 190
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.015433587344458377,
|
| 147 |
+
"grad_norm": 0.18044413626194,
|
| 148 |
+
"learning_rate": 3.073359073359073e-05,
|
| 149 |
+
"loss": 1.130545425415039,
|
| 150 |
+
"step": 200
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.016205266711681297,
|
| 154 |
+
"grad_norm": 0.18559624254703522,
|
| 155 |
+
"learning_rate": 3.227799227799228e-05,
|
| 156 |
+
"loss": 1.1351449966430665,
|
| 157 |
+
"step": 210
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.016976946078904216,
|
| 161 |
+
"grad_norm": 0.23771214485168457,
|
| 162 |
+
"learning_rate": 3.382239382239382e-05,
|
| 163 |
+
"loss": 1.1352075576782226,
|
| 164 |
+
"step": 220
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.017748625446127136,
|
| 168 |
+
"grad_norm": 0.19858677685260773,
|
| 169 |
+
"learning_rate": 3.536679536679537e-05,
|
| 170 |
+
"loss": 1.155667495727539,
|
| 171 |
+
"step": 230
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.018520304813350052,
|
| 175 |
+
"grad_norm": 0.19712069630622864,
|
| 176 |
+
"learning_rate": 3.691119691119691e-05,
|
| 177 |
+
"loss": 0.9542052268981933,
|
| 178 |
+
"step": 240
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.01929198418057297,
|
| 182 |
+
"grad_norm": 0.1643419712781906,
|
| 183 |
+
"learning_rate": 3.8455598455598456e-05,
|
| 184 |
+
"loss": 1.1352619171142577,
|
| 185 |
+
"step": 250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.02006366354779589,
|
| 189 |
+
"grad_norm": 0.17200475931167603,
|
| 190 |
+
"learning_rate": 4e-05,
|
| 191 |
+
"loss": 1.055178451538086,
|
| 192 |
+
"step": 260
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.02083534291501881,
|
| 196 |
+
"grad_norm": 0.2140629142522812,
|
| 197 |
+
"learning_rate": 4.1544401544401544e-05,
|
| 198 |
+
"loss": 1.1110715866088867,
|
| 199 |
+
"step": 270
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.02160702228224173,
|
| 203 |
+
"grad_norm": 0.1658836156129837,
|
| 204 |
+
"learning_rate": 4.308880308880309e-05,
|
| 205 |
+
"loss": 1.0160120964050292,
|
| 206 |
+
"step": 280
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.022378701649464646,
|
| 210 |
+
"grad_norm": 0.20209717750549316,
|
| 211 |
+
"learning_rate": 4.463320463320463e-05,
|
| 212 |
+
"loss": 1.2165130615234374,
|
| 213 |
+
"step": 290
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.023150381016687566,
|
| 217 |
+
"grad_norm": 0.18639937043190002,
|
| 218 |
+
"learning_rate": 4.617760617760618e-05,
|
| 219 |
+
"loss": 1.074045467376709,
|
| 220 |
+
"step": 300
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.023922060383910485,
|
| 224 |
+
"grad_norm": 0.18107382953166962,
|
| 225 |
+
"learning_rate": 4.772200772200772e-05,
|
| 226 |
+
"loss": 1.100408172607422,
|
| 227 |
+
"step": 310
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.024693739751133405,
|
| 231 |
+
"grad_norm": 0.18550734221935272,
|
| 232 |
+
"learning_rate": 4.926640926640927e-05,
|
| 233 |
+
"loss": 0.9446431159973144,
|
| 234 |
+
"step": 320
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.025465419118356324,
|
| 238 |
+
"grad_norm": 0.24888084828853607,
|
| 239 |
+
"learning_rate": 5.0810810810810815e-05,
|
| 240 |
+
"loss": 1.019780158996582,
|
| 241 |
+
"step": 330
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.02623709848557924,
|
| 245 |
+
"grad_norm": 0.1900169849395752,
|
| 246 |
+
"learning_rate": 5.2355212355212356e-05,
|
| 247 |
+
"loss": 1.066290283203125,
|
| 248 |
+
"step": 340
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.02700877785280216,
|
| 252 |
+
"grad_norm": 0.19299696385860443,
|
| 253 |
+
"learning_rate": 5.38996138996139e-05,
|
| 254 |
+
"loss": 1.0028789520263672,
|
| 255 |
+
"step": 350
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.02778045722002508,
|
| 259 |
+
"grad_norm": 0.15513072907924652,
|
| 260 |
+
"learning_rate": 5.544401544401545e-05,
|
| 261 |
+
"loss": 1.002441120147705,
|
| 262 |
+
"step": 360
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.028552136587248,
|
| 266 |
+
"grad_norm": 0.19387617707252502,
|
| 267 |
+
"learning_rate": 5.698841698841699e-05,
|
| 268 |
+
"loss": 1.0937806129455567,
|
| 269 |
+
"step": 370
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.02932381595447092,
|
| 273 |
+
"grad_norm": 0.13289429247379303,
|
| 274 |
+
"learning_rate": 5.853281853281853e-05,
|
| 275 |
+
"loss": 1.0398863792419433,
|
| 276 |
+
"step": 380
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.030095495321693835,
|
| 280 |
+
"grad_norm": 0.1527375429868698,
|
| 281 |
+
"learning_rate": 6.007722007722007e-05,
|
| 282 |
+
"loss": 0.959206485748291,
|
| 283 |
+
"step": 390
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.030867174688916754,
|
| 287 |
+
"grad_norm": 0.1617506742477417,
|
| 288 |
+
"learning_rate": 6.162162162162163e-05,
|
| 289 |
+
"loss": 1.048958969116211,
|
| 290 |
+
"step": 400
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.03163885405613968,
|
| 294 |
+
"grad_norm": 0.3012467920780182,
|
| 295 |
+
"learning_rate": 6.316602316602317e-05,
|
| 296 |
+
"loss": 0.9629308700561523,
|
| 297 |
+
"step": 410
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.03241053342336259,
|
| 301 |
+
"grad_norm": 0.15288439393043518,
|
| 302 |
+
"learning_rate": 6.471042471042472e-05,
|
| 303 |
+
"loss": 1.02709903717041,
|
| 304 |
+
"step": 420
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.03318221279058551,
|
| 308 |
+
"grad_norm": 0.1398162543773651,
|
| 309 |
+
"learning_rate": 6.625482625482627e-05,
|
| 310 |
+
"loss": 0.9591814041137695,
|
| 311 |
+
"step": 430
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.03395389215780843,
|
| 315 |
+
"grad_norm": 0.15535490214824677,
|
| 316 |
+
"learning_rate": 6.779922779922781e-05,
|
| 317 |
+
"loss": 0.9994503021240234,
|
| 318 |
+
"step": 440
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.03472557152503135,
|
| 322 |
+
"grad_norm": 0.15020038187503815,
|
| 323 |
+
"learning_rate": 6.934362934362935e-05,
|
| 324 |
+
"loss": 0.9528783798217774,
|
| 325 |
+
"step": 450
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.03549725089225427,
|
| 329 |
+
"grad_norm": 0.1734347939491272,
|
| 330 |
+
"learning_rate": 7.088803088803089e-05,
|
| 331 |
+
"loss": 0.9716519355773926,
|
| 332 |
+
"step": 460
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.03626893025947719,
|
| 336 |
+
"grad_norm": 0.14533282816410065,
|
| 337 |
+
"learning_rate": 7.243243243243245e-05,
|
| 338 |
+
"loss": 0.9922411918640137,
|
| 339 |
+
"step": 470
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.037040609626700104,
|
| 343 |
+
"grad_norm": 0.15392670035362244,
|
| 344 |
+
"learning_rate": 7.397683397683399e-05,
|
| 345 |
+
"loss": 0.9835933685302735,
|
| 346 |
+
"step": 480
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.03781228899392303,
|
| 350 |
+
"grad_norm": 0.15519730746746063,
|
| 351 |
+
"learning_rate": 7.552123552123553e-05,
|
| 352 |
+
"loss": 0.96371488571167,
|
| 353 |
+
"step": 490
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.03858396836114594,
|
| 357 |
+
"grad_norm": 0.1377173811197281,
|
| 358 |
+
"learning_rate": 7.706563706563707e-05,
|
| 359 |
+
"loss": 0.9519417762756348,
|
| 360 |
+
"step": 500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.039355647728368866,
|
| 364 |
+
"grad_norm": 0.14820078015327454,
|
| 365 |
+
"learning_rate": 7.861003861003862e-05,
|
| 366 |
+
"loss": 1.0663246154785155,
|
| 367 |
+
"step": 510
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.04012732709559178,
|
| 371 |
+
"grad_norm": 0.1553962677717209,
|
| 372 |
+
"learning_rate": 8.015444015444016e-05,
|
| 373 |
+
"loss": 0.9961751937866211,
|
| 374 |
+
"step": 520
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.0408990064628147,
|
| 378 |
+
"grad_norm": 0.1502590775489807,
|
| 379 |
+
"learning_rate": 8.16988416988417e-05,
|
| 380 |
+
"loss": 1.0495684623718262,
|
| 381 |
+
"step": 530
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.04167068583003762,
|
| 385 |
+
"grad_norm": 0.15323589742183685,
|
| 386 |
+
"learning_rate": 8.324324324324326e-05,
|
| 387 |
+
"loss": 1.0317422866821289,
|
| 388 |
+
"step": 540
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.04244236519726054,
|
| 392 |
+
"grad_norm": 0.11740688234567642,
|
| 393 |
+
"learning_rate": 8.47876447876448e-05,
|
| 394 |
+
"loss": 1.0751480102539062,
|
| 395 |
+
"step": 550
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.04321404456448346,
|
| 399 |
+
"grad_norm": 0.13047188520431519,
|
| 400 |
+
"learning_rate": 8.633204633204634e-05,
|
| 401 |
+
"loss": 1.0331148147583007,
|
| 402 |
+
"step": 560
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.043985723931706376,
|
| 406 |
+
"grad_norm": 0.14131630957126617,
|
| 407 |
+
"learning_rate": 8.787644787644788e-05,
|
| 408 |
+
"loss": 0.9371702194213867,
|
| 409 |
+
"step": 570
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.04475740329892929,
|
| 413 |
+
"grad_norm": 0.13744156062602997,
|
| 414 |
+
"learning_rate": 8.942084942084943e-05,
|
| 415 |
+
"loss": 0.9680840492248535,
|
| 416 |
+
"step": 580
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.045529082666152215,
|
| 420 |
+
"grad_norm": 0.12264937162399292,
|
| 421 |
+
"learning_rate": 9.096525096525098e-05,
|
| 422 |
+
"loss": 0.9658163070678711,
|
| 423 |
+
"step": 590
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.04630076203337513,
|
| 427 |
+
"grad_norm": 0.14490118622779846,
|
| 428 |
+
"learning_rate": 9.250965250965252e-05,
|
| 429 |
+
"loss": 1.0076140403747558,
|
| 430 |
+
"step": 600
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.047072441400598054,
|
| 434 |
+
"grad_norm": 0.1781102418899536,
|
| 435 |
+
"learning_rate": 9.405405405405407e-05,
|
| 436 |
+
"loss": 0.9680351257324219,
|
| 437 |
+
"step": 610
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.04784412076782097,
|
| 441 |
+
"grad_norm": 0.16192109882831573,
|
| 442 |
+
"learning_rate": 9.559845559845561e-05,
|
| 443 |
+
"loss": 0.9431415557861328,
|
| 444 |
+
"step": 620
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.048615800135043886,
|
| 448 |
+
"grad_norm": 0.155950129032135,
|
| 449 |
+
"learning_rate": 9.714285714285715e-05,
|
| 450 |
+
"loss": 1.000882625579834,
|
| 451 |
+
"step": 630
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.04938747950226681,
|
| 455 |
+
"grad_norm": 0.16288375854492188,
|
| 456 |
+
"learning_rate": 9.868725868725869e-05,
|
| 457 |
+
"loss": 1.0334013938903808,
|
| 458 |
+
"step": 640
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.050159158869489726,
|
| 462 |
+
"grad_norm": 0.13413415849208832,
|
| 463 |
+
"learning_rate": 0.00010023166023166025,
|
| 464 |
+
"loss": 1.011709499359131,
|
| 465 |
+
"step": 650
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.05093083823671265,
|
| 469 |
+
"grad_norm": 0.13729217648506165,
|
| 470 |
+
"learning_rate": 0.00010177606177606179,
|
| 471 |
+
"loss": 0.9930562973022461,
|
| 472 |
+
"step": 660
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.051702517603935565,
|
| 476 |
+
"grad_norm": 0.14648699760437012,
|
| 477 |
+
"learning_rate": 0.00010332046332046333,
|
| 478 |
+
"loss": 1.0485844612121582,
|
| 479 |
+
"step": 670
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.05247419697115848,
|
| 483 |
+
"grad_norm": 0.15611329674720764,
|
| 484 |
+
"learning_rate": 0.00010486486486486487,
|
| 485 |
+
"loss": 0.9434291839599609,
|
| 486 |
+
"step": 680
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.053245876338381404,
|
| 490 |
+
"grad_norm": 0.13057349622249603,
|
| 491 |
+
"learning_rate": 0.00010640926640926641,
|
| 492 |
+
"loss": 0.8720365524291992,
|
| 493 |
+
"step": 690
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.05401755570560432,
|
| 497 |
+
"grad_norm": 0.38071855902671814,
|
| 498 |
+
"learning_rate": 0.00010795366795366796,
|
| 499 |
+
"loss": 0.9360018730163574,
|
| 500 |
+
"step": 700
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.05478923507282724,
|
| 504 |
+
"grad_norm": 0.1299811750650406,
|
| 505 |
+
"learning_rate": 0.0001094980694980695,
|
| 506 |
+
"loss": 0.9274260520935058,
|
| 507 |
+
"step": 710
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.05556091444005016,
|
| 511 |
+
"grad_norm": 0.14164002239704132,
|
| 512 |
+
"learning_rate": 0.00011104247104247106,
|
| 513 |
+
"loss": 0.9184993743896485,
|
| 514 |
+
"step": 720
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.056332593807273075,
|
| 518 |
+
"grad_norm": 0.15521082282066345,
|
| 519 |
+
"learning_rate": 0.0001125868725868726,
|
| 520 |
+
"loss": 1.0110851287841798,
|
| 521 |
+
"step": 730
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.057104273174496,
|
| 525 |
+
"grad_norm": 0.17111285030841827,
|
| 526 |
+
"learning_rate": 0.00011413127413127414,
|
| 527 |
+
"loss": 0.9625322341918945,
|
| 528 |
+
"step": 740
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.057875952541718914,
|
| 532 |
+
"grad_norm": 0.13952504098415375,
|
| 533 |
+
"learning_rate": 0.00011567567567567568,
|
| 534 |
+
"loss": 0.8918585777282715,
|
| 535 |
+
"step": 750
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.05864763190894184,
|
| 539 |
+
"grad_norm": 0.1711304485797882,
|
| 540 |
+
"learning_rate": 0.00011722007722007722,
|
| 541 |
+
"loss": 1.013539981842041,
|
| 542 |
+
"step": 760
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.05941931127616475,
|
| 546 |
+
"grad_norm": 0.1418197751045227,
|
| 547 |
+
"learning_rate": 0.00011876447876447876,
|
| 548 |
+
"loss": 0.9296130180358887,
|
| 549 |
+
"step": 770
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.06019099064338767,
|
| 553 |
+
"grad_norm": 0.15530534088611603,
|
| 554 |
+
"learning_rate": 0.00012030888030888032,
|
| 555 |
+
"loss": 0.9378318786621094,
|
| 556 |
+
"step": 780
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.06096267001061059,
|
| 560 |
+
"grad_norm": 0.13504521548748016,
|
| 561 |
+
"learning_rate": 0.00012185328185328187,
|
| 562 |
+
"loss": 0.9477480888366699,
|
| 563 |
+
"step": 790
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.06173434937783351,
|
| 567 |
+
"grad_norm": 0.1602628529071808,
|
| 568 |
+
"learning_rate": 0.0001233976833976834,
|
| 569 |
+
"loss": 1.0176645278930665,
|
| 570 |
+
"step": 800
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.06250602874505642,
|
| 574 |
+
"grad_norm": 0.13999249041080475,
|
| 575 |
+
"learning_rate": 0.00012494208494208495,
|
| 576 |
+
"loss": 0.9362374305725097,
|
| 577 |
+
"step": 810
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.06327770811227935,
|
| 581 |
+
"grad_norm": 0.15388326346874237,
|
| 582 |
+
"learning_rate": 0.0001264864864864865,
|
| 583 |
+
"loss": 0.9121697425842286,
|
| 584 |
+
"step": 820
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.06404938747950227,
|
| 588 |
+
"grad_norm": 0.14896224439144135,
|
| 589 |
+
"learning_rate": 0.00012803088803088803,
|
| 590 |
+
"loss": 0.9638944625854492,
|
| 591 |
+
"step": 830
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.06482106684672519,
|
| 595 |
+
"grad_norm": 0.14142225682735443,
|
| 596 |
+
"learning_rate": 0.00012957528957528957,
|
| 597 |
+
"loss": 0.907442855834961,
|
| 598 |
+
"step": 840
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.0655927462139481,
|
| 602 |
+
"grad_norm": 0.13392828404903412,
|
| 603 |
+
"learning_rate": 0.00013111969111969114,
|
| 604 |
+
"loss": 0.9532367706298828,
|
| 605 |
+
"step": 850
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.06636442558117102,
|
| 609 |
+
"grad_norm": 0.14815282821655273,
|
| 610 |
+
"learning_rate": 0.00013266409266409268,
|
| 611 |
+
"loss": 0.9036151885986328,
|
| 612 |
+
"step": 860
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.06713610494839395,
|
| 616 |
+
"grad_norm": 0.17789602279663086,
|
| 617 |
+
"learning_rate": 0.00013420849420849422,
|
| 618 |
+
"loss": 0.9164458274841308,
|
| 619 |
+
"step": 870
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.06790778431561686,
|
| 623 |
+
"grad_norm": 0.17448553442955017,
|
| 624 |
+
"learning_rate": 0.00013575289575289576,
|
| 625 |
+
"loss": 0.9297392845153809,
|
| 626 |
+
"step": 880
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.06867946368283978,
|
| 630 |
+
"grad_norm": 0.14892329275608063,
|
| 631 |
+
"learning_rate": 0.0001372972972972973,
|
| 632 |
+
"loss": 0.9415802955627441,
|
| 633 |
+
"step": 890
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.0694511430500627,
|
| 637 |
+
"grad_norm": 0.18727394938468933,
|
| 638 |
+
"learning_rate": 0.00013884169884169885,
|
| 639 |
+
"loss": 0.887691879272461,
|
| 640 |
+
"step": 900
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.07022282241728561,
|
| 644 |
+
"grad_norm": 0.1246710792183876,
|
| 645 |
+
"learning_rate": 0.0001403861003861004,
|
| 646 |
+
"loss": 0.8601170539855957,
|
| 647 |
+
"step": 910
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.07099450178450854,
|
| 651 |
+
"grad_norm": 0.15692849457263947,
|
| 652 |
+
"learning_rate": 0.00014193050193050195,
|
| 653 |
+
"loss": 0.9606046676635742,
|
| 654 |
+
"step": 920
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.07176618115173146,
|
| 658 |
+
"grad_norm": 0.17853842675685883,
|
| 659 |
+
"learning_rate": 0.0001434749034749035,
|
| 660 |
+
"loss": 0.938359260559082,
|
| 661 |
+
"step": 930
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.07253786051895438,
|
| 665 |
+
"grad_norm": 0.14882907271385193,
|
| 666 |
+
"learning_rate": 0.00014501930501930504,
|
| 667 |
+
"loss": 0.9875331878662109,
|
| 668 |
+
"step": 940
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.07330953988617729,
|
| 672 |
+
"grad_norm": 0.13406018912792206,
|
| 673 |
+
"learning_rate": 0.00014656370656370658,
|
| 674 |
+
"loss": 0.9117307662963867,
|
| 675 |
+
"step": 950
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.07408121925340021,
|
| 679 |
+
"grad_norm": 0.12386741489171982,
|
| 680 |
+
"learning_rate": 0.00014810810810810812,
|
| 681 |
+
"loss": 0.9069728851318359,
|
| 682 |
+
"step": 960
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.07485289862062314,
|
| 686 |
+
"grad_norm": 0.15084366500377655,
|
| 687 |
+
"learning_rate": 0.00014965250965250966,
|
| 688 |
+
"loss": 0.9486578941345215,
|
| 689 |
+
"step": 970
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.07562457798784605,
|
| 693 |
+
"grad_norm": 0.13196571171283722,
|
| 694 |
+
"learning_rate": 0.0001511969111969112,
|
| 695 |
+
"loss": 0.9376090049743653,
|
| 696 |
+
"step": 980
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.07639625735506897,
|
| 700 |
+
"grad_norm": 0.11976128071546555,
|
| 701 |
+
"learning_rate": 0.00015274131274131277,
|
| 702 |
+
"loss": 0.9725616455078125,
|
| 703 |
+
"step": 990
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.07716793672229189,
|
| 707 |
+
"grad_norm": 0.13437485694885254,
|
| 708 |
+
"learning_rate": 0.0001542857142857143,
|
| 709 |
+
"loss": 0.9574755668640137,
|
| 710 |
+
"step": 1000
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.0779396160895148,
|
| 714 |
+
"grad_norm": 0.13558916747570038,
|
| 715 |
+
"learning_rate": 0.00015583011583011585,
|
| 716 |
+
"loss": 0.9154973983764648,
|
| 717 |
+
"step": 1010
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.07871129545673773,
|
| 721 |
+
"grad_norm": 0.1680697351694107,
|
| 722 |
+
"learning_rate": 0.0001573745173745174,
|
| 723 |
+
"loss": 1.0692084312438965,
|
| 724 |
+
"step": 1020
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.07948297482396065,
|
| 728 |
+
"grad_norm": 0.14069008827209473,
|
| 729 |
+
"learning_rate": 0.00015891891891891893,
|
| 730 |
+
"loss": 0.9002031326293946,
|
| 731 |
+
"step": 1030
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 0.08025465419118356,
|
| 735 |
+
"grad_norm": 0.12237665057182312,
|
| 736 |
+
"learning_rate": 0.00016046332046332047,
|
| 737 |
+
"loss": 0.8829663276672364,
|
| 738 |
+
"step": 1040
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.08102633355840648,
|
| 742 |
+
"grad_norm": 0.14210717380046844,
|
| 743 |
+
"learning_rate": 0.000162007722007722,
|
| 744 |
+
"loss": 0.9502348899841309,
|
| 745 |
+
"step": 1050
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.0817980129256294,
|
| 749 |
+
"grad_norm": 0.12595845758914948,
|
| 750 |
+
"learning_rate": 0.00016355212355212358,
|
| 751 |
+
"loss": 0.8802145957946778,
|
| 752 |
+
"step": 1060
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.08256969229285233,
|
| 756 |
+
"grad_norm": 0.14671702682971954,
|
| 757 |
+
"learning_rate": 0.00016509652509652512,
|
| 758 |
+
"loss": 0.950124454498291,
|
| 759 |
+
"step": 1070
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.08334137166007524,
|
| 763 |
+
"grad_norm": 0.1262345314025879,
|
| 764 |
+
"learning_rate": 0.00016664092664092666,
|
| 765 |
+
"loss": 0.9178938865661621,
|
| 766 |
+
"step": 1080
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 0.08411305102729816,
|
| 770 |
+
"grad_norm": 0.14854216575622559,
|
| 771 |
+
"learning_rate": 0.0001681853281853282,
|
| 772 |
+
"loss": 0.9059360504150391,
|
| 773 |
+
"step": 1090
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.08488473039452107,
|
| 777 |
+
"grad_norm": 0.13612130284309387,
|
| 778 |
+
"learning_rate": 0.00016972972972972974,
|
| 779 |
+
"loss": 0.883179759979248,
|
| 780 |
+
"step": 1100
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 0.08565640976174399,
|
| 784 |
+
"grad_norm": 0.195224329829216,
|
| 785 |
+
"learning_rate": 0.00017127413127413128,
|
| 786 |
+
"loss": 0.9765983581542969,
|
| 787 |
+
"step": 1110
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 0.08642808912896692,
|
| 791 |
+
"grad_norm": 0.16128239035606384,
|
| 792 |
+
"learning_rate": 0.00017281853281853282,
|
| 793 |
+
"loss": 0.9481371879577637,
|
| 794 |
+
"step": 1120
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.08719976849618984,
|
| 798 |
+
"grad_norm": 0.1204826682806015,
|
| 799 |
+
"learning_rate": 0.00017436293436293436,
|
| 800 |
+
"loss": 0.9438440322875976,
|
| 801 |
+
"step": 1130
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.08797144786341275,
|
| 805 |
+
"grad_norm": 0.13581594824790955,
|
| 806 |
+
"learning_rate": 0.00017590733590733593,
|
| 807 |
+
"loss": 0.9164579391479493,
|
| 808 |
+
"step": 1140
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 0.08874312723063567,
|
| 812 |
+
"grad_norm": 0.14480997622013092,
|
| 813 |
+
"learning_rate": 0.00017745173745173747,
|
| 814 |
+
"loss": 0.8554980278015136,
|
| 815 |
+
"step": 1150
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 0.08951480659785858,
|
| 819 |
+
"grad_norm": 0.1339653730392456,
|
| 820 |
+
"learning_rate": 0.000178996138996139,
|
| 821 |
+
"loss": 0.9386772155761719,
|
| 822 |
+
"step": 1160
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 0.09028648596508151,
|
| 826 |
+
"grad_norm": 0.13732171058654785,
|
| 827 |
+
"learning_rate": 0.00018054054054054055,
|
| 828 |
+
"loss": 0.960637378692627,
|
| 829 |
+
"step": 1170
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 0.09105816533230443,
|
| 833 |
+
"grad_norm": 0.14760258793830872,
|
| 834 |
+
"learning_rate": 0.0001820849420849421,
|
| 835 |
+
"loss": 0.9496297836303711,
|
| 836 |
+
"step": 1180
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 0.09182984469952735,
|
| 840 |
+
"grad_norm": 0.13694636523723602,
|
| 841 |
+
"learning_rate": 0.00018362934362934363,
|
| 842 |
+
"loss": 0.9301774024963378,
|
| 843 |
+
"step": 1190
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.09260152406675026,
|
| 847 |
+
"grad_norm": 0.16521573066711426,
|
| 848 |
+
"learning_rate": 0.00018517374517374518,
|
| 849 |
+
"loss": 0.9696132659912109,
|
| 850 |
+
"step": 1200
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 0.09337320343397318,
|
| 854 |
+
"grad_norm": 0.13662070035934448,
|
| 855 |
+
"learning_rate": 0.00018671814671814674,
|
| 856 |
+
"loss": 0.9592963218688965,
|
| 857 |
+
"step": 1210
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.09414488280119611,
|
| 861 |
+
"grad_norm": 0.12738122045993805,
|
| 862 |
+
"learning_rate": 0.00018826254826254828,
|
| 863 |
+
"loss": 0.9708365440368653,
|
| 864 |
+
"step": 1220
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.09491656216841902,
|
| 868 |
+
"grad_norm": 0.14669036865234375,
|
| 869 |
+
"learning_rate": 0.00018980694980694982,
|
| 870 |
+
"loss": 0.8764440536499023,
|
| 871 |
+
"step": 1230
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 0.09568824153564194,
|
| 875 |
+
"grad_norm": 0.12573756277561188,
|
| 876 |
+
"learning_rate": 0.00019135135135135137,
|
| 877 |
+
"loss": 0.8464407920837402,
|
| 878 |
+
"step": 1240
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.09645992090286486,
|
| 882 |
+
"grad_norm": 0.14189030230045319,
|
| 883 |
+
"learning_rate": 0.0001928957528957529,
|
| 884 |
+
"loss": 0.950318717956543,
|
| 885 |
+
"step": 1250
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.09723160027008777,
|
| 889 |
+
"grad_norm": 0.2636380195617676,
|
| 890 |
+
"learning_rate": 0.00019444015444015445,
|
| 891 |
+
"loss": 0.9141375541687011,
|
| 892 |
+
"step": 1260
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 0.0980032796373107,
|
| 896 |
+
"grad_norm": 0.15273556113243103,
|
| 897 |
+
"learning_rate": 0.000195984555984556,
|
| 898 |
+
"loss": 1.0023685455322267,
|
| 899 |
+
"step": 1270
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 0.09877495900453362,
|
| 903 |
+
"grad_norm": 0.2087467461824417,
|
| 904 |
+
"learning_rate": 0.00019752895752895756,
|
| 905 |
+
"loss": 0.9461590766906738,
|
| 906 |
+
"step": 1280
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.09954663837175654,
|
| 910 |
+
"grad_norm": 0.14373677968978882,
|
| 911 |
+
"learning_rate": 0.0001990733590733591,
|
| 912 |
+
"loss": 0.8914681434631347,
|
| 913 |
+
"step": 1290
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 0.10031831773897945,
|
| 917 |
+
"grad_norm": 0.13711115717887878,
|
| 918 |
+
"learning_rate": 0.00019993141289437587,
|
| 919 |
+
"loss": 0.9707538604736328,
|
| 920 |
+
"step": 1300
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 0.10108999710620237,
|
| 924 |
+
"grad_norm": 0.13779997825622559,
|
| 925 |
+
"learning_rate": 0.00019975994513031552,
|
| 926 |
+
"loss": 0.9407063484191894,
|
| 927 |
+
"step": 1310
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.1018616764734253,
|
| 931 |
+
"grad_norm": 0.1424177885055542,
|
| 932 |
+
"learning_rate": 0.00019958847736625514,
|
| 933 |
+
"loss": 0.944306755065918,
|
| 934 |
+
"step": 1320
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 0.10263335584064821,
|
| 938 |
+
"grad_norm": 0.15074807405471802,
|
| 939 |
+
"learning_rate": 0.00019941700960219482,
|
| 940 |
+
"loss": 0.9324775695800781,
|
| 941 |
+
"step": 1330
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 0.10340503520787113,
|
| 945 |
+
"grad_norm": 0.15965643525123596,
|
| 946 |
+
"learning_rate": 0.00019924554183813444,
|
| 947 |
+
"loss": 0.9168493270874023,
|
| 948 |
+
"step": 1340
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 0.10417671457509405,
|
| 952 |
+
"grad_norm": 0.12655006349086761,
|
| 953 |
+
"learning_rate": 0.0001990740740740741,
|
| 954 |
+
"loss": 0.918604850769043,
|
| 955 |
+
"step": 1350
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 0.10494839394231696,
|
| 959 |
+
"grad_norm": 0.11994543671607971,
|
| 960 |
+
"learning_rate": 0.0001989026063100137,
|
| 961 |
+
"loss": 0.8942041397094727,
|
| 962 |
+
"step": 1360
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.10572007330953989,
|
| 966 |
+
"grad_norm": 0.1397182047367096,
|
| 967 |
+
"learning_rate": 0.0001987311385459534,
|
| 968 |
+
"loss": 0.8999843597412109,
|
| 969 |
+
"step": 1370
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.10649175267676281,
|
| 973 |
+
"grad_norm": 0.20514515042304993,
|
| 974 |
+
"learning_rate": 0.000198559670781893,
|
| 975 |
+
"loss": 0.9744900703430176,
|
| 976 |
+
"step": 1380
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 0.10726343204398572,
|
| 980 |
+
"grad_norm": 0.15667827427387238,
|
| 981 |
+
"learning_rate": 0.00019838820301783266,
|
| 982 |
+
"loss": 0.8710949897766114,
|
| 983 |
+
"step": 1390
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 0.10803511141120864,
|
| 987 |
+
"grad_norm": 0.1237126812338829,
|
| 988 |
+
"learning_rate": 0.00019821673525377228,
|
| 989 |
+
"loss": 0.8532806396484375,
|
| 990 |
+
"step": 1400
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 0.10880679077843156,
|
| 994 |
+
"grad_norm": 0.1715669184923172,
|
| 995 |
+
"learning_rate": 0.00019804526748971196,
|
| 996 |
+
"loss": 0.9749599456787109,
|
| 997 |
+
"step": 1410
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 0.10957847014565449,
|
| 1001 |
+
"grad_norm": 0.13979029655456543,
|
| 1002 |
+
"learning_rate": 0.00019787379972565158,
|
| 1003 |
+
"loss": 0.9612955093383789,
|
| 1004 |
+
"step": 1420
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 0.1103501495128774,
|
| 1008 |
+
"grad_norm": 0.13627590239048004,
|
| 1009 |
+
"learning_rate": 0.00019770233196159123,
|
| 1010 |
+
"loss": 0.8780692100524903,
|
| 1011 |
+
"step": 1430
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 0.11112182888010032,
|
| 1015 |
+
"grad_norm": 0.1600399911403656,
|
| 1016 |
+
"learning_rate": 0.00019753086419753085,
|
| 1017 |
+
"loss": 0.8817881584167481,
|
| 1018 |
+
"step": 1440
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 0.11189350824732323,
|
| 1022 |
+
"grad_norm": 0.1146964505314827,
|
| 1023 |
+
"learning_rate": 0.00019735939643347053,
|
| 1024 |
+
"loss": 0.9072661399841309,
|
| 1025 |
+
"step": 1450
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 0.11266518761454615,
|
| 1029 |
+
"grad_norm": 0.14121341705322266,
|
| 1030 |
+
"learning_rate": 0.00019718792866941015,
|
| 1031 |
+
"loss": 0.8885805130004882,
|
| 1032 |
+
"step": 1460
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 0.11343686698176908,
|
| 1036 |
+
"grad_norm": 0.1582922786474228,
|
| 1037 |
+
"learning_rate": 0.0001970164609053498,
|
| 1038 |
+
"loss": 0.9153773307800293,
|
| 1039 |
+
"step": 1470
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 0.114208546348992,
|
| 1043 |
+
"grad_norm": 0.14982298016548157,
|
| 1044 |
+
"learning_rate": 0.00019684499314128945,
|
| 1045 |
+
"loss": 0.9298340797424316,
|
| 1046 |
+
"step": 1480
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 0.11498022571621491,
|
| 1050 |
+
"grad_norm": 0.11531206965446472,
|
| 1051 |
+
"learning_rate": 0.0001966735253772291,
|
| 1052 |
+
"loss": 0.9395890235900879,
|
| 1053 |
+
"step": 1490
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 0.11575190508343783,
|
| 1057 |
+
"grad_norm": 0.14209498465061188,
|
| 1058 |
+
"learning_rate": 0.00019650205761316872,
|
| 1059 |
+
"loss": 0.8390321731567383,
|
| 1060 |
+
"step": 1500
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 0.11652358445066074,
|
| 1064 |
+
"grad_norm": 0.11906258016824722,
|
| 1065 |
+
"learning_rate": 0.00019633058984910837,
|
| 1066 |
+
"loss": 0.909323787689209,
|
| 1067 |
+
"step": 1510
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 0.11729526381788367,
|
| 1071 |
+
"grad_norm": 0.12579163908958435,
|
| 1072 |
+
"learning_rate": 0.00019615912208504802,
|
| 1073 |
+
"loss": 0.9562045097351074,
|
| 1074 |
+
"step": 1520
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 0.11806694318510659,
|
| 1078 |
+
"grad_norm": 0.1287720799446106,
|
| 1079 |
+
"learning_rate": 0.00019598765432098767,
|
| 1080 |
+
"loss": 0.9209161758422851,
|
| 1081 |
+
"step": 1530
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 0.1188386225523295,
|
| 1085 |
+
"grad_norm": 0.13776282966136932,
|
| 1086 |
+
"learning_rate": 0.0001958161865569273,
|
| 1087 |
+
"loss": 0.9366206169128418,
|
| 1088 |
+
"step": 1540
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 0.11961030191955242,
|
| 1092 |
+
"grad_norm": 0.1586165428161621,
|
| 1093 |
+
"learning_rate": 0.00019564471879286694,
|
| 1094 |
+
"loss": 0.9056665420532226,
|
| 1095 |
+
"step": 1550
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 0.12038198128677534,
|
| 1099 |
+
"grad_norm": 0.15723218023777008,
|
| 1100 |
+
"learning_rate": 0.0001954732510288066,
|
| 1101 |
+
"loss": 0.8944165229797363,
|
| 1102 |
+
"step": 1560
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 0.12115366065399827,
|
| 1106 |
+
"grad_norm": 0.15735211968421936,
|
| 1107 |
+
"learning_rate": 0.00019530178326474624,
|
| 1108 |
+
"loss": 0.8650986671447753,
|
| 1109 |
+
"step": 1570
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 0.12192534002122118,
|
| 1113 |
+
"grad_norm": 0.15295566618442535,
|
| 1114 |
+
"learning_rate": 0.0001951303155006859,
|
| 1115 |
+
"loss": 0.9541757583618165,
|
| 1116 |
+
"step": 1580
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 0.1226970193884441,
|
| 1120 |
+
"grad_norm": 0.16210581362247467,
|
| 1121 |
+
"learning_rate": 0.0001949588477366255,
|
| 1122 |
+
"loss": 0.8924543380737304,
|
| 1123 |
+
"step": 1590
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 0.12346869875566702,
|
| 1127 |
+
"grad_norm": 0.15451756119728088,
|
| 1128 |
+
"learning_rate": 0.0001947873799725652,
|
| 1129 |
+
"loss": 0.8653304100036621,
|
| 1130 |
+
"step": 1600
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 0.12424037812288993,
|
| 1134 |
+
"grad_norm": 0.12462305277585983,
|
| 1135 |
+
"learning_rate": 0.0001946159122085048,
|
| 1136 |
+
"loss": 0.9189548492431641,
|
| 1137 |
+
"step": 1610
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 0.12501205749011285,
|
| 1141 |
+
"grad_norm": 0.10922125726938248,
|
| 1142 |
+
"learning_rate": 0.00019444444444444446,
|
| 1143 |
+
"loss": 0.8601775169372559,
|
| 1144 |
+
"step": 1620
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 0.12578373685733577,
|
| 1148 |
+
"grad_norm": 0.1442819982767105,
|
| 1149 |
+
"learning_rate": 0.00019427297668038408,
|
| 1150 |
+
"loss": 0.883521556854248,
|
| 1151 |
+
"step": 1630
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 0.1265554162245587,
|
| 1155 |
+
"grad_norm": 0.1921447366476059,
|
| 1156 |
+
"learning_rate": 0.00019410150891632376,
|
| 1157 |
+
"loss": 0.9088053703308105,
|
| 1158 |
+
"step": 1640
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 0.12732709559178162,
|
| 1162 |
+
"grad_norm": 0.13579413294792175,
|
| 1163 |
+
"learning_rate": 0.00019393004115226338,
|
| 1164 |
+
"loss": 0.9177509307861328,
|
| 1165 |
+
"step": 1650
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 0.12809877495900454,
|
| 1169 |
+
"grad_norm": 0.12798288464546204,
|
| 1170 |
+
"learning_rate": 0.00019375857338820303,
|
| 1171 |
+
"loss": 0.9359799385070801,
|
| 1172 |
+
"step": 1660
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 0.12887045432622746,
|
| 1176 |
+
"grad_norm": 0.12642040848731995,
|
| 1177 |
+
"learning_rate": 0.00019358710562414265,
|
| 1178 |
+
"loss": 0.876513671875,
|
| 1179 |
+
"step": 1670
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 0.12964213369345037,
|
| 1183 |
+
"grad_norm": 0.12268314510583878,
|
| 1184 |
+
"learning_rate": 0.00019341563786008233,
|
| 1185 |
+
"loss": 0.878510570526123,
|
| 1186 |
+
"step": 1680
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 0.1304138130606733,
|
| 1190 |
+
"grad_norm": 0.1510227620601654,
|
| 1191 |
+
"learning_rate": 0.00019324417009602195,
|
| 1192 |
+
"loss": 0.9135002136230469,
|
| 1193 |
+
"step": 1690
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 0.1311854924278962,
|
| 1197 |
+
"grad_norm": 0.16413401067256927,
|
| 1198 |
+
"learning_rate": 0.0001930727023319616,
|
| 1199 |
+
"loss": 0.8695366859436036,
|
| 1200 |
+
"step": 1700
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 0.13195717179511912,
|
| 1204 |
+
"grad_norm": 0.14487908780574799,
|
| 1205 |
+
"learning_rate": 0.00019290123456790122,
|
| 1206 |
+
"loss": 0.9284669876098632,
|
| 1207 |
+
"step": 1710
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 0.13272885116234204,
|
| 1211 |
+
"grad_norm": 0.1303521990776062,
|
| 1212 |
+
"learning_rate": 0.0001927297668038409,
|
| 1213 |
+
"loss": 0.8737581253051758,
|
| 1214 |
+
"step": 1720
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 0.13350053052956495,
|
| 1218 |
+
"grad_norm": 0.14090701937675476,
|
| 1219 |
+
"learning_rate": 0.00019255829903978052,
|
| 1220 |
+
"loss": 0.8595477104187011,
|
| 1221 |
+
"step": 1730
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 0.1342722098967879,
|
| 1225 |
+
"grad_norm": 0.1355149745941162,
|
| 1226 |
+
"learning_rate": 0.00019238683127572017,
|
| 1227 |
+
"loss": 0.8475465774536133,
|
| 1228 |
+
"step": 1740
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 0.1350438892640108,
|
| 1232 |
+
"grad_norm": 0.14047279953956604,
|
| 1233 |
+
"learning_rate": 0.0001922153635116598,
|
| 1234 |
+
"loss": 0.9217391967773437,
|
| 1235 |
+
"step": 1750
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 0.13581556863123373,
|
| 1239 |
+
"grad_norm": 0.14659123122692108,
|
| 1240 |
+
"learning_rate": 0.00019204389574759947,
|
| 1241 |
+
"loss": 0.9316446304321289,
|
| 1242 |
+
"step": 1760
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 0.13658724799845665,
|
| 1246 |
+
"grad_norm": 0.1811600923538208,
|
| 1247 |
+
"learning_rate": 0.0001918724279835391,
|
| 1248 |
+
"loss": 0.9173222541809082,
|
| 1249 |
+
"step": 1770
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 0.13735892736567956,
|
| 1253 |
+
"grad_norm": 0.12042385339736938,
|
| 1254 |
+
"learning_rate": 0.00019170096021947874,
|
| 1255 |
+
"loss": 0.907382869720459,
|
| 1256 |
+
"step": 1780
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 0.13813060673290248,
|
| 1260 |
+
"grad_norm": 0.15939505398273468,
|
| 1261 |
+
"learning_rate": 0.0001915294924554184,
|
| 1262 |
+
"loss": 0.964719009399414,
|
| 1263 |
+
"step": 1790
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 0.1389022861001254,
|
| 1267 |
+
"grad_norm": 0.14139987528324127,
|
| 1268 |
+
"learning_rate": 0.00019135802469135804,
|
| 1269 |
+
"loss": 0.8954049110412597,
|
| 1270 |
+
"step": 1800
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 0.1396739654673483,
|
| 1274 |
+
"grad_norm": 0.15884581208229065,
|
| 1275 |
+
"learning_rate": 0.0001911865569272977,
|
| 1276 |
+
"loss": 0.9414543151855469,
|
| 1277 |
+
"step": 1810
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 0.14044564483457123,
|
| 1281 |
+
"grad_norm": 0.1332668662071228,
|
| 1282 |
+
"learning_rate": 0.0001910150891632373,
|
| 1283 |
+
"loss": 0.8585048675537109,
|
| 1284 |
+
"step": 1820
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 0.14121732420179414,
|
| 1288 |
+
"grad_norm": 0.1384868174791336,
|
| 1289 |
+
"learning_rate": 0.00019084362139917696,
|
| 1290 |
+
"loss": 0.8052179336547851,
|
| 1291 |
+
"step": 1830
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 0.14198900356901709,
|
| 1295 |
+
"grad_norm": 0.1241953894495964,
|
| 1296 |
+
"learning_rate": 0.0001906721536351166,
|
| 1297 |
+
"loss": 0.9241853713989258,
|
| 1298 |
+
"step": 1840
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 0.14276068293624,
|
| 1302 |
+
"grad_norm": 0.13251616060733795,
|
| 1303 |
+
"learning_rate": 0.00019050068587105626,
|
| 1304 |
+
"loss": 0.8902045249938965,
|
| 1305 |
+
"step": 1850
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 0.14353236230346292,
|
| 1309 |
+
"grad_norm": 0.13486811518669128,
|
| 1310 |
+
"learning_rate": 0.00019032921810699588,
|
| 1311 |
+
"loss": 0.8438145637512207,
|
| 1312 |
+
"step": 1860
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 0.14430404167068583,
|
| 1316 |
+
"grad_norm": 0.14527903497219086,
|
| 1317 |
+
"learning_rate": 0.00019015775034293556,
|
| 1318 |
+
"loss": 0.932585334777832,
|
| 1319 |
+
"step": 1870
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 0.14507572103790875,
|
| 1323 |
+
"grad_norm": 0.15183964371681213,
|
| 1324 |
+
"learning_rate": 0.00018998628257887518,
|
| 1325 |
+
"loss": 0.9338572502136231,
|
| 1326 |
+
"step": 1880
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 0.14584740040513167,
|
| 1330 |
+
"grad_norm": 0.1227315217256546,
|
| 1331 |
+
"learning_rate": 0.00018981481481481483,
|
| 1332 |
+
"loss": 0.8647249221801758,
|
| 1333 |
+
"step": 1890
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 0.14661907977235458,
|
| 1337 |
+
"grad_norm": 0.14465254545211792,
|
| 1338 |
+
"learning_rate": 0.00018964334705075445,
|
| 1339 |
+
"loss": 0.887813663482666,
|
| 1340 |
+
"step": 1900
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 0.1473907591395775,
|
| 1344 |
+
"grad_norm": 0.11031103879213333,
|
| 1345 |
+
"learning_rate": 0.00018947187928669413,
|
| 1346 |
+
"loss": 0.8783070564270019,
|
| 1347 |
+
"step": 1910
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 0.14816243850680041,
|
| 1351 |
+
"grad_norm": 0.13811931014060974,
|
| 1352 |
+
"learning_rate": 0.00018930041152263375,
|
| 1353 |
+
"loss": 0.90804443359375,
|
| 1354 |
+
"step": 1920
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 0.14893411787402333,
|
| 1358 |
+
"grad_norm": 0.25385376811027527,
|
| 1359 |
+
"learning_rate": 0.0001891289437585734,
|
| 1360 |
+
"loss": 0.888271427154541,
|
| 1361 |
+
"step": 1930
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 0.14970579724124627,
|
| 1365 |
+
"grad_norm": 0.14109653234481812,
|
| 1366 |
+
"learning_rate": 0.00018895747599451302,
|
| 1367 |
+
"loss": 0.8717686653137207,
|
| 1368 |
+
"step": 1940
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 0.1504774766084692,
|
| 1372 |
+
"grad_norm": 0.10888762027025223,
|
| 1373 |
+
"learning_rate": 0.0001887860082304527,
|
| 1374 |
+
"loss": 0.8756811141967773,
|
| 1375 |
+
"step": 1950
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 0.1512491559756921,
|
| 1379 |
+
"grad_norm": 0.1465354561805725,
|
| 1380 |
+
"learning_rate": 0.00018861454046639232,
|
| 1381 |
+
"loss": 0.9119040489196777,
|
| 1382 |
+
"step": 1960
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 0.15202083534291502,
|
| 1386 |
+
"grad_norm": 0.13660100102424622,
|
| 1387 |
+
"learning_rate": 0.00018844307270233197,
|
| 1388 |
+
"loss": 0.8416598320007325,
|
| 1389 |
+
"step": 1970
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 0.15279251471013794,
|
| 1393 |
+
"grad_norm": 0.12262725085020065,
|
| 1394 |
+
"learning_rate": 0.0001882716049382716,
|
| 1395 |
+
"loss": 0.8306491851806641,
|
| 1396 |
+
"step": 1980
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 0.15356419407736085,
|
| 1400 |
+
"grad_norm": 0.18066026270389557,
|
| 1401 |
+
"learning_rate": 0.00018810013717421127,
|
| 1402 |
+
"loss": 0.8606444358825683,
|
| 1403 |
+
"step": 1990
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 0.15433587344458377,
|
| 1407 |
+
"grad_norm": 0.1607869267463684,
|
| 1408 |
+
"learning_rate": 0.0001879286694101509,
|
| 1409 |
+
"loss": 0.9605829238891601,
|
| 1410 |
+
"step": 2000
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 0.1551075528118067,
|
| 1414 |
+
"grad_norm": 0.1732511818408966,
|
| 1415 |
+
"learning_rate": 0.00018775720164609054,
|
| 1416 |
+
"loss": 0.9208683013916016,
|
| 1417 |
+
"step": 2010
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 0.1558792321790296,
|
| 1421 |
+
"grad_norm": 0.1554340124130249,
|
| 1422 |
+
"learning_rate": 0.00018758573388203017,
|
| 1423 |
+
"loss": 0.9016365051269531,
|
| 1424 |
+
"step": 2020
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 0.15665091154625252,
|
| 1428 |
+
"grad_norm": 0.1407565027475357,
|
| 1429 |
+
"learning_rate": 0.00018741426611796984,
|
| 1430 |
+
"loss": 0.9112971305847168,
|
| 1431 |
+
"step": 2030
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 0.15742259091347546,
|
| 1435 |
+
"grad_norm": 0.10590255260467529,
|
| 1436 |
+
"learning_rate": 0.00018724279835390946,
|
| 1437 |
+
"loss": 0.8664677619934082,
|
| 1438 |
+
"step": 2040
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 0.15819427028069838,
|
| 1442 |
+
"grad_norm": 0.13333319127559662,
|
| 1443 |
+
"learning_rate": 0.00018707133058984911,
|
| 1444 |
+
"loss": 0.9705114364624023,
|
| 1445 |
+
"step": 2050
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 0.1589659496479213,
|
| 1449 |
+
"grad_norm": 0.16020020842552185,
|
| 1450 |
+
"learning_rate": 0.00018689986282578876,
|
| 1451 |
+
"loss": 0.9187061309814453,
|
| 1452 |
+
"step": 2060
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 0.1597376290151442,
|
| 1456 |
+
"grad_norm": 0.1456824541091919,
|
| 1457 |
+
"learning_rate": 0.0001867283950617284,
|
| 1458 |
+
"loss": 0.8844801902770996,
|
| 1459 |
+
"step": 2070
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 0.16050930838236713,
|
| 1463 |
+
"grad_norm": 0.13203363120555878,
|
| 1464 |
+
"learning_rate": 0.00018655692729766806,
|
| 1465 |
+
"loss": 0.9111983299255371,
|
| 1466 |
+
"step": 2080
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 0.16128098774959004,
|
| 1470 |
+
"grad_norm": 0.10979647189378738,
|
| 1471 |
+
"learning_rate": 0.00018638545953360768,
|
| 1472 |
+
"loss": 0.9126319885253906,
|
| 1473 |
+
"step": 2090
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 0.16205266711681296,
|
| 1477 |
+
"grad_norm": 0.12909536063671112,
|
| 1478 |
+
"learning_rate": 0.00018621399176954733,
|
| 1479 |
+
"loss": 0.8958646774291992,
|
| 1480 |
+
"step": 2100
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 0.16282434648403588,
|
| 1484 |
+
"grad_norm": 0.15361259877681732,
|
| 1485 |
+
"learning_rate": 0.00018604252400548698,
|
| 1486 |
+
"loss": 0.8408657073974609,
|
| 1487 |
+
"step": 2110
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 0.1635960258512588,
|
| 1491 |
+
"grad_norm": 0.11375487595796585,
|
| 1492 |
+
"learning_rate": 0.00018587105624142663,
|
| 1493 |
+
"loss": 0.9133548736572266,
|
| 1494 |
+
"step": 2120
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 0.1643677052184817,
|
| 1498 |
+
"grad_norm": 0.1553937792778015,
|
| 1499 |
+
"learning_rate": 0.00018569958847736625,
|
| 1500 |
+
"loss": 0.8190338134765625,
|
| 1501 |
+
"step": 2130
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 0.16513938458570465,
|
| 1505 |
+
"grad_norm": 0.14899234473705292,
|
| 1506 |
+
"learning_rate": 0.0001855281207133059,
|
| 1507 |
+
"loss": 0.8054628372192383,
|
| 1508 |
+
"step": 2140
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 0.16591106395292757,
|
| 1512 |
+
"grad_norm": 0.11932719498872757,
|
| 1513 |
+
"learning_rate": 0.00018535665294924555,
|
| 1514 |
+
"loss": 0.8314993858337403,
|
| 1515 |
+
"step": 2150
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 0.16668274332015048,
|
| 1519 |
+
"grad_norm": 0.15255865454673767,
|
| 1520 |
+
"learning_rate": 0.0001851851851851852,
|
| 1521 |
+
"loss": 0.9741696357727051,
|
| 1522 |
+
"step": 2160
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 0.1674544226873734,
|
| 1526 |
+
"grad_norm": 0.1365659087896347,
|
| 1527 |
+
"learning_rate": 0.00018501371742112483,
|
| 1528 |
+
"loss": 0.7812792778015136,
|
| 1529 |
+
"step": 2170
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 0.16822610205459632,
|
| 1533 |
+
"grad_norm": 0.1468389928340912,
|
| 1534 |
+
"learning_rate": 0.00018484224965706447,
|
| 1535 |
+
"loss": 0.8438286781311035,
|
| 1536 |
+
"step": 2180
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 0.16899778142181923,
|
| 1540 |
+
"grad_norm": 0.1342012882232666,
|
| 1541 |
+
"learning_rate": 0.00018467078189300412,
|
| 1542 |
+
"loss": 0.8273720741271973,
|
| 1543 |
+
"step": 2190
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 0.16976946078904215,
|
| 1547 |
+
"grad_norm": 0.14852559566497803,
|
| 1548 |
+
"learning_rate": 0.00018449931412894377,
|
| 1549 |
+
"loss": 0.8302847862243652,
|
| 1550 |
+
"step": 2200
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 0.17054114015626506,
|
| 1554 |
+
"grad_norm": 0.17884424328804016,
|
| 1555 |
+
"learning_rate": 0.0001843278463648834,
|
| 1556 |
+
"loss": 0.9065903663635254,
|
| 1557 |
+
"step": 2210
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 0.17131281952348798,
|
| 1561 |
+
"grad_norm": 0.1340647041797638,
|
| 1562 |
+
"learning_rate": 0.00018415637860082307,
|
| 1563 |
+
"loss": 0.8122591018676758,
|
| 1564 |
+
"step": 2220
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 0.1720844988907109,
|
| 1568 |
+
"grad_norm": 0.17012424767017365,
|
| 1569 |
+
"learning_rate": 0.0001839849108367627,
|
| 1570 |
+
"loss": 0.8936735153198242,
|
| 1571 |
+
"step": 2230
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 0.17285617825793384,
|
| 1575 |
+
"grad_norm": 0.11823276430368423,
|
| 1576 |
+
"learning_rate": 0.00018381344307270234,
|
| 1577 |
+
"loss": 0.88836669921875,
|
| 1578 |
+
"step": 2240
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 0.17362785762515676,
|
| 1582 |
+
"grad_norm": 0.12694299221038818,
|
| 1583 |
+
"learning_rate": 0.00018364197530864197,
|
| 1584 |
+
"loss": 0.906658935546875,
|
| 1585 |
+
"step": 2250
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 0.17439953699237967,
|
| 1589 |
+
"grad_norm": 0.14491288363933563,
|
| 1590 |
+
"learning_rate": 0.00018347050754458164,
|
| 1591 |
+
"loss": 0.8715028762817383,
|
| 1592 |
+
"step": 2260
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 0.1751712163596026,
|
| 1596 |
+
"grad_norm": 0.1279899775981903,
|
| 1597 |
+
"learning_rate": 0.00018329903978052127,
|
| 1598 |
+
"loss": 0.8870208740234375,
|
| 1599 |
+
"step": 2270
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 0.1759428957268255,
|
| 1603 |
+
"grad_norm": 0.14201810956001282,
|
| 1604 |
+
"learning_rate": 0.00018312757201646091,
|
| 1605 |
+
"loss": 0.9046253204345703,
|
| 1606 |
+
"step": 2280
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 0.17671457509404842,
|
| 1610 |
+
"grad_norm": 0.12473177909851074,
|
| 1611 |
+
"learning_rate": 0.00018295610425240056,
|
| 1612 |
+
"loss": 0.8702874183654785,
|
| 1613 |
+
"step": 2290
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 0.17748625446127134,
|
| 1617 |
+
"grad_norm": 0.12428930401802063,
|
| 1618 |
+
"learning_rate": 0.0001827846364883402,
|
| 1619 |
+
"loss": 0.8405272483825683,
|
| 1620 |
+
"step": 2300
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 0.17825793382849425,
|
| 1624 |
+
"grad_norm": 0.13424119353294373,
|
| 1625 |
+
"learning_rate": 0.00018261316872427984,
|
| 1626 |
+
"loss": 0.8849527359008789,
|
| 1627 |
+
"step": 2310
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 0.17902961319571717,
|
| 1631 |
+
"grad_norm": 0.12349385023117065,
|
| 1632 |
+
"learning_rate": 0.00018244170096021949,
|
| 1633 |
+
"loss": 0.8746221542358399,
|
| 1634 |
+
"step": 2320
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 0.17980129256294008,
|
| 1638 |
+
"grad_norm": 0.11935239285230637,
|
| 1639 |
+
"learning_rate": 0.00018227023319615913,
|
| 1640 |
+
"loss": 0.8474451065063476,
|
| 1641 |
+
"step": 2330
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 0.18057297193016303,
|
| 1645 |
+
"grad_norm": 0.13540779054164886,
|
| 1646 |
+
"learning_rate": 0.00018209876543209878,
|
| 1647 |
+
"loss": 0.8805816650390625,
|
| 1648 |
+
"step": 2340
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 0.18134465129738594,
|
| 1652 |
+
"grad_norm": 0.1339704990386963,
|
| 1653 |
+
"learning_rate": 0.00018192729766803843,
|
| 1654 |
+
"loss": 0.9093109130859375,
|
| 1655 |
+
"step": 2350
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 0.18211633066460886,
|
| 1659 |
+
"grad_norm": 0.14474879205226898,
|
| 1660 |
+
"learning_rate": 0.00018175582990397806,
|
| 1661 |
+
"loss": 0.8396927833557128,
|
| 1662 |
+
"step": 2360
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 0.18288801003183178,
|
| 1666 |
+
"grad_norm": 0.11800862848758698,
|
| 1667 |
+
"learning_rate": 0.0001815843621399177,
|
| 1668 |
+
"loss": 0.8718694686889649,
|
| 1669 |
+
"step": 2370
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 0.1836596893990547,
|
| 1673 |
+
"grad_norm": 0.14035063982009888,
|
| 1674 |
+
"learning_rate": 0.00018141289437585735,
|
| 1675 |
+
"loss": 0.969059944152832,
|
| 1676 |
+
"step": 2380
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 0.1844313687662776,
|
| 1680 |
+
"grad_norm": 0.1354781836271286,
|
| 1681 |
+
"learning_rate": 0.000181241426611797,
|
| 1682 |
+
"loss": 0.9034146308898926,
|
| 1683 |
+
"step": 2390
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 0.18520304813350053,
|
| 1687 |
+
"grad_norm": 0.15591464936733246,
|
| 1688 |
+
"learning_rate": 0.00018106995884773663,
|
| 1689 |
+
"loss": 0.805502986907959,
|
| 1690 |
+
"step": 2400
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 0.18597472750072344,
|
| 1694 |
+
"grad_norm": 0.17329534888267517,
|
| 1695 |
+
"learning_rate": 0.00018089849108367628,
|
| 1696 |
+
"loss": 0.9025980949401855,
|
| 1697 |
+
"step": 2410
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 0.18674640686794636,
|
| 1701 |
+
"grad_norm": 0.35040536522865295,
|
| 1702 |
+
"learning_rate": 0.00018072702331961592,
|
| 1703 |
+
"loss": 0.821717357635498,
|
| 1704 |
+
"step": 2420
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 0.18751808623516927,
|
| 1708 |
+
"grad_norm": 0.13618957996368408,
|
| 1709 |
+
"learning_rate": 0.00018055555555555557,
|
| 1710 |
+
"loss": 0.8431755065917969,
|
| 1711 |
+
"step": 2430
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 0.18828976560239222,
|
| 1715 |
+
"grad_norm": 0.16440042853355408,
|
| 1716 |
+
"learning_rate": 0.0001803840877914952,
|
| 1717 |
+
"loss": 0.9136919975280762,
|
| 1718 |
+
"step": 2440
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 0.18906144496961513,
|
| 1722 |
+
"grad_norm": 0.18514175713062286,
|
| 1723 |
+
"learning_rate": 0.00018021262002743485,
|
| 1724 |
+
"loss": 0.8714737892150879,
|
| 1725 |
+
"step": 2450
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 0.18983312433683805,
|
| 1729 |
+
"grad_norm": 0.16719800233840942,
|
| 1730 |
+
"learning_rate": 0.0001800411522633745,
|
| 1731 |
+
"loss": 0.9059031486511231,
|
| 1732 |
+
"step": 2460
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 0.19060480370406097,
|
| 1736 |
+
"grad_norm": 0.1346147507429123,
|
| 1737 |
+
"learning_rate": 0.00017986968449931414,
|
| 1738 |
+
"loss": 0.7939674377441406,
|
| 1739 |
+
"step": 2470
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 0.19137648307128388,
|
| 1743 |
+
"grad_norm": 0.16486112773418427,
|
| 1744 |
+
"learning_rate": 0.00017969821673525377,
|
| 1745 |
+
"loss": 0.904393196105957,
|
| 1746 |
+
"step": 2480
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 0.1921481624385068,
|
| 1750 |
+
"grad_norm": 0.12318016588687897,
|
| 1751 |
+
"learning_rate": 0.00017952674897119342,
|
| 1752 |
+
"loss": 0.8810678482055664,
|
| 1753 |
+
"step": 2490
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 0.1929198418057297,
|
| 1757 |
+
"grad_norm": 0.1480247527360916,
|
| 1758 |
+
"learning_rate": 0.00017935528120713307,
|
| 1759 |
+
"loss": 0.7764781475067138,
|
| 1760 |
+
"step": 2500
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 0.19369152117295263,
|
| 1764 |
+
"grad_norm": 0.1327567845582962,
|
| 1765 |
+
"learning_rate": 0.00017918381344307272,
|
| 1766 |
+
"loss": 0.8767733573913574,
|
| 1767 |
+
"step": 2510
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 0.19446320054017555,
|
| 1771 |
+
"grad_norm": 0.16582264006137848,
|
| 1772 |
+
"learning_rate": 0.00017901234567901234,
|
| 1773 |
+
"loss": 0.884821605682373,
|
| 1774 |
+
"step": 2520
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 0.1952348799073985,
|
| 1778 |
+
"grad_norm": 0.14093245565891266,
|
| 1779 |
+
"learning_rate": 0.000178840877914952,
|
| 1780 |
+
"loss": 0.8281044006347656,
|
| 1781 |
+
"step": 2530
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 0.1960065592746214,
|
| 1785 |
+
"grad_norm": 0.1372932493686676,
|
| 1786 |
+
"learning_rate": 0.00017866941015089164,
|
| 1787 |
+
"loss": 0.9036026954650879,
|
| 1788 |
+
"step": 2540
|
| 1789 |
+
},
|
| 1790 |
+
{
|
| 1791 |
+
"epoch": 0.19677823864184432,
|
| 1792 |
+
"grad_norm": 0.15799172222614288,
|
| 1793 |
+
"learning_rate": 0.00017849794238683129,
|
| 1794 |
+
"loss": 0.8834423065185547,
|
| 1795 |
+
"step": 2550
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 0.19754991800906724,
|
| 1799 |
+
"grad_norm": 0.13300693035125732,
|
| 1800 |
+
"learning_rate": 0.00017832647462277094,
|
| 1801 |
+
"loss": 0.8410321235656738,
|
| 1802 |
+
"step": 2560
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 0.19832159737629015,
|
| 1806 |
+
"grad_norm": 0.11820129305124283,
|
| 1807 |
+
"learning_rate": 0.00017815500685871056,
|
| 1808 |
+
"loss": 0.8374045372009278,
|
| 1809 |
+
"step": 2570
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 0.19909327674351307,
|
| 1813 |
+
"grad_norm": 0.1374407708644867,
|
| 1814 |
+
"learning_rate": 0.0001779835390946502,
|
| 1815 |
+
"loss": 0.7897539138793945,
|
| 1816 |
+
"step": 2580
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 0.199864956110736,
|
| 1820 |
+
"grad_norm": 0.13014692068099976,
|
| 1821 |
+
"learning_rate": 0.00017781207133058986,
|
| 1822 |
+
"loss": 0.856849193572998,
|
| 1823 |
+
"step": 2590
|
| 1824 |
+
},
|
| 1825 |
+
{
|
| 1826 |
+
"epoch": 0.2006366354779589,
|
| 1827 |
+
"grad_norm": 0.13736820220947266,
|
| 1828 |
+
"learning_rate": 0.0001776406035665295,
|
| 1829 |
+
"loss": 0.8098331451416015,
|
| 1830 |
+
"step": 2600
|
| 1831 |
+
},
|
| 1832 |
+
{
|
| 1833 |
+
"epoch": 0.20140831484518182,
|
| 1834 |
+
"grad_norm": 0.13417045772075653,
|
| 1835 |
+
"learning_rate": 0.00017746913580246916,
|
| 1836 |
+
"loss": 0.8112906455993653,
|
| 1837 |
+
"step": 2610
|
| 1838 |
+
},
|
| 1839 |
+
{
|
| 1840 |
+
"epoch": 0.20217999421240473,
|
| 1841 |
+
"grad_norm": 0.12335588037967682,
|
| 1842 |
+
"learning_rate": 0.0001772976680384088,
|
| 1843 |
+
"loss": 0.8197178840637207,
|
| 1844 |
+
"step": 2620
|
| 1845 |
+
},
|
| 1846 |
+
{
|
| 1847 |
+
"epoch": 0.20295167357962768,
|
| 1848 |
+
"grad_norm": 0.12072271853685379,
|
| 1849 |
+
"learning_rate": 0.00017712620027434843,
|
| 1850 |
+
"loss": 0.8148613929748535,
|
| 1851 |
+
"step": 2630
|
| 1852 |
+
},
|
| 1853 |
+
{
|
| 1854 |
+
"epoch": 0.2037233529468506,
|
| 1855 |
+
"grad_norm": 0.12888556718826294,
|
| 1856 |
+
"learning_rate": 0.00017695473251028808,
|
| 1857 |
+
"loss": 0.8378517150878906,
|
| 1858 |
+
"step": 2640
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 0.2044950323140735,
|
| 1862 |
+
"grad_norm": 0.11225631088018417,
|
| 1863 |
+
"learning_rate": 0.00017678326474622773,
|
| 1864 |
+
"loss": 0.8098993301391602,
|
| 1865 |
+
"step": 2650
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 0.20526671168129643,
|
| 1869 |
+
"grad_norm": 0.1396367847919464,
|
| 1870 |
+
"learning_rate": 0.00017661179698216738,
|
| 1871 |
+
"loss": 0.7926461696624756,
|
| 1872 |
+
"step": 2660
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 0.20603839104851934,
|
| 1876 |
+
"grad_norm": 0.12182660400867462,
|
| 1877 |
+
"learning_rate": 0.000176440329218107,
|
| 1878 |
+
"loss": 0.8657416343688965,
|
| 1879 |
+
"step": 2670
|
| 1880 |
+
},
|
| 1881 |
+
{
|
| 1882 |
+
"epoch": 0.20681007041574226,
|
| 1883 |
+
"grad_norm": 0.12498902529478073,
|
| 1884 |
+
"learning_rate": 0.00017626886145404665,
|
| 1885 |
+
"loss": 0.8974786758422851,
|
| 1886 |
+
"step": 2680
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 0.20758174978296517,
|
| 1890 |
+
"grad_norm": 0.1641893833875656,
|
| 1891 |
+
"learning_rate": 0.0001760973936899863,
|
| 1892 |
+
"loss": 0.7702033042907714,
|
| 1893 |
+
"step": 2690
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 0.2083534291501881,
|
| 1897 |
+
"grad_norm": 0.14216631650924683,
|
| 1898 |
+
"learning_rate": 0.00017592592592592595,
|
| 1899 |
+
"loss": 0.8128464698791504,
|
| 1900 |
+
"step": 2700
|
| 1901 |
+
},
|
| 1902 |
+
{
|
| 1903 |
+
"epoch": 0.209125108517411,
|
| 1904 |
+
"grad_norm": 0.12807051837444305,
|
| 1905 |
+
"learning_rate": 0.00017575445816186557,
|
| 1906 |
+
"loss": 0.8731807708740235,
|
| 1907 |
+
"step": 2710
|
| 1908 |
+
},
|
| 1909 |
+
{
|
| 1910 |
+
"epoch": 0.20989678788463392,
|
| 1911 |
+
"grad_norm": 0.12057145684957504,
|
| 1912 |
+
"learning_rate": 0.00017558299039780522,
|
| 1913 |
+
"loss": 0.8347474098205566,
|
| 1914 |
+
"step": 2720
|
| 1915 |
+
},
|
| 1916 |
+
{
|
| 1917 |
+
"epoch": 0.21066846725185687,
|
| 1918 |
+
"grad_norm": 0.1331891119480133,
|
| 1919 |
+
"learning_rate": 0.00017541152263374487,
|
| 1920 |
+
"loss": 0.7946592330932617,
|
| 1921 |
+
"step": 2730
|
| 1922 |
+
},
|
| 1923 |
+
{
|
| 1924 |
+
"epoch": 0.21144014661907978,
|
| 1925 |
+
"grad_norm": 0.13952475786209106,
|
| 1926 |
+
"learning_rate": 0.00017524005486968452,
|
| 1927 |
+
"loss": 0.850405216217041,
|
| 1928 |
+
"step": 2740
|
| 1929 |
+
},
|
| 1930 |
+
{
|
| 1931 |
+
"epoch": 0.2122118259863027,
|
| 1932 |
+
"grad_norm": 0.12533603608608246,
|
| 1933 |
+
"learning_rate": 0.00017506858710562414,
|
| 1934 |
+
"loss": 0.8693943977355957,
|
| 1935 |
+
"step": 2750
|
| 1936 |
+
},
|
| 1937 |
+
{
|
| 1938 |
+
"epoch": 0.21298350535352562,
|
| 1939 |
+
"grad_norm": 0.134017214179039,
|
| 1940 |
+
"learning_rate": 0.0001748971193415638,
|
| 1941 |
+
"loss": 0.9226296424865723,
|
| 1942 |
+
"step": 2760
|
| 1943 |
+
},
|
| 1944 |
+
{
|
| 1945 |
+
"epoch": 0.21375518472074853,
|
| 1946 |
+
"grad_norm": 0.12564072012901306,
|
| 1947 |
+
"learning_rate": 0.00017472565157750344,
|
| 1948 |
+
"loss": 0.8781246185302735,
|
| 1949 |
+
"step": 2770
|
| 1950 |
+
},
|
| 1951 |
+
{
|
| 1952 |
+
"epoch": 0.21452686408797145,
|
| 1953 |
+
"grad_norm": 0.12992620468139648,
|
| 1954 |
+
"learning_rate": 0.0001745541838134431,
|
| 1955 |
+
"loss": 0.8699252128601074,
|
| 1956 |
+
"step": 2780
|
| 1957 |
+
},
|
| 1958 |
+
{
|
| 1959 |
+
"epoch": 0.21529854345519436,
|
| 1960 |
+
"grad_norm": 0.11067423224449158,
|
| 1961 |
+
"learning_rate": 0.0001743827160493827,
|
| 1962 |
+
"loss": 0.8009305000305176,
|
| 1963 |
+
"step": 2790
|
| 1964 |
+
},
|
| 1965 |
+
{
|
| 1966 |
+
"epoch": 0.21607022282241728,
|
| 1967 |
+
"grad_norm": 0.13229770958423615,
|
| 1968 |
+
"learning_rate": 0.00017421124828532236,
|
| 1969 |
+
"loss": 0.92990140914917,
|
| 1970 |
+
"step": 2800
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"epoch": 0.2168419021896402,
|
| 1974 |
+
"grad_norm": 0.13477829098701477,
|
| 1975 |
+
"learning_rate": 0.000174039780521262,
|
| 1976 |
+
"loss": 0.8522166252136231,
|
| 1977 |
+
"step": 2810
|
| 1978 |
+
},
|
| 1979 |
+
{
|
| 1980 |
+
"epoch": 0.2176135815568631,
|
| 1981 |
+
"grad_norm": 0.1265680193901062,
|
| 1982 |
+
"learning_rate": 0.00017386831275720166,
|
| 1983 |
+
"loss": 0.8684545516967773,
|
| 1984 |
+
"step": 2820
|
| 1985 |
+
},
|
| 1986 |
+
{
|
| 1987 |
+
"epoch": 0.21838526092408606,
|
| 1988 |
+
"grad_norm": 0.11227365583181381,
|
| 1989 |
+
"learning_rate": 0.0001736968449931413,
|
| 1990 |
+
"loss": 0.821353816986084,
|
| 1991 |
+
"step": 2830
|
| 1992 |
+
},
|
| 1993 |
+
{
|
| 1994 |
+
"epoch": 0.21915694029130897,
|
| 1995 |
+
"grad_norm": 0.11255034059286118,
|
| 1996 |
+
"learning_rate": 0.00017352537722908093,
|
| 1997 |
+
"loss": 0.8419916152954101,
|
| 1998 |
+
"step": 2840
|
| 1999 |
+
},
|
| 2000 |
+
{
|
| 2001 |
+
"epoch": 0.2199286196585319,
|
| 2002 |
+
"grad_norm": 0.12512286007404327,
|
| 2003 |
+
"learning_rate": 0.0001733539094650206,
|
| 2004 |
+
"loss": 0.8188055992126465,
|
| 2005 |
+
"step": 2850
|
| 2006 |
+
},
|
| 2007 |
+
{
|
| 2008 |
+
"epoch": 0.2207002990257548,
|
| 2009 |
+
"grad_norm": 0.13817989826202393,
|
| 2010 |
+
"learning_rate": 0.00017318244170096023,
|
| 2011 |
+
"loss": 0.9547490119934082,
|
| 2012 |
+
"step": 2860
|
| 2013 |
+
},
|
| 2014 |
+
{
|
| 2015 |
+
"epoch": 0.22147197839297772,
|
| 2016 |
+
"grad_norm": 0.14506305754184723,
|
| 2017 |
+
"learning_rate": 0.00017301097393689988,
|
| 2018 |
+
"loss": 0.8111377716064453,
|
| 2019 |
+
"step": 2870
|
| 2020 |
+
},
|
| 2021 |
+
{
|
| 2022 |
+
"epoch": 0.22224365776020064,
|
| 2023 |
+
"grad_norm": 0.14242449402809143,
|
| 2024 |
+
"learning_rate": 0.0001728395061728395,
|
| 2025 |
+
"loss": 0.7653944015502929,
|
| 2026 |
+
"step": 2880
|
| 2027 |
+
},
|
| 2028 |
+
{
|
| 2029 |
+
"epoch": 0.22301533712742355,
|
| 2030 |
+
"grad_norm": 0.1414581537246704,
|
| 2031 |
+
"learning_rate": 0.00017266803840877918,
|
| 2032 |
+
"loss": 0.8571985244750977,
|
| 2033 |
+
"step": 2890
|
| 2034 |
+
},
|
| 2035 |
+
{
|
| 2036 |
+
"epoch": 0.22378701649464647,
|
| 2037 |
+
"grad_norm": 0.13643725216388702,
|
| 2038 |
+
"learning_rate": 0.0001724965706447188,
|
| 2039 |
+
"loss": 0.8333075523376465,
|
| 2040 |
+
"step": 2900
|
| 2041 |
+
},
|
| 2042 |
+
{
|
| 2043 |
+
"epoch": 0.22455869586186938,
|
| 2044 |
+
"grad_norm": 0.17245373129844666,
|
| 2045 |
+
"learning_rate": 0.00017232510288065845,
|
| 2046 |
+
"loss": 0.8401066780090332,
|
| 2047 |
+
"step": 2910
|
| 2048 |
+
},
|
| 2049 |
+
{
|
| 2050 |
+
"epoch": 0.2253303752290923,
|
| 2051 |
+
"grad_norm": 0.12681716680526733,
|
| 2052 |
+
"learning_rate": 0.00017215363511659807,
|
| 2053 |
+
"loss": 0.8211629867553711,
|
| 2054 |
+
"step": 2920
|
| 2055 |
+
},
|
| 2056 |
+
{
|
| 2057 |
+
"epoch": 0.22610205459631524,
|
| 2058 |
+
"grad_norm": 0.09726311266422272,
|
| 2059 |
+
"learning_rate": 0.00017198216735253775,
|
| 2060 |
+
"loss": 0.8029566764831543,
|
| 2061 |
+
"step": 2930
|
| 2062 |
+
},
|
| 2063 |
+
{
|
| 2064 |
+
"epoch": 0.22687373396353816,
|
| 2065 |
+
"grad_norm": 0.13840550184249878,
|
| 2066 |
+
"learning_rate": 0.00017181069958847737,
|
| 2067 |
+
"loss": 0.8934766769409179,
|
| 2068 |
+
"step": 2940
|
| 2069 |
+
},
|
| 2070 |
+
{
|
| 2071 |
+
"epoch": 0.22764541333076108,
|
| 2072 |
+
"grad_norm": 0.12750297784805298,
|
| 2073 |
+
"learning_rate": 0.00017163923182441702,
|
| 2074 |
+
"loss": 0.8754122734069825,
|
| 2075 |
+
"step": 2950
|
| 2076 |
+
},
|
| 2077 |
+
{
|
| 2078 |
+
"epoch": 0.228417092697984,
|
| 2079 |
+
"grad_norm": 0.10405158251523972,
|
| 2080 |
+
"learning_rate": 0.00017146776406035664,
|
| 2081 |
+
"loss": 0.7468550682067872,
|
| 2082 |
+
"step": 2960
|
| 2083 |
+
},
|
| 2084 |
+
{
|
| 2085 |
+
"epoch": 0.2291887720652069,
|
| 2086 |
+
"grad_norm": 0.14371293783187866,
|
| 2087 |
+
"learning_rate": 0.00017129629629629632,
|
| 2088 |
+
"loss": 0.8387319564819335,
|
| 2089 |
+
"step": 2970
|
| 2090 |
+
},
|
| 2091 |
+
{
|
| 2092 |
+
"epoch": 0.22996045143242982,
|
| 2093 |
+
"grad_norm": 0.13800597190856934,
|
| 2094 |
+
"learning_rate": 0.00017112482853223594,
|
| 2095 |
+
"loss": 0.8476024627685547,
|
| 2096 |
+
"step": 2980
|
| 2097 |
+
},
|
| 2098 |
+
{
|
| 2099 |
+
"epoch": 0.23073213079965274,
|
| 2100 |
+
"grad_norm": 0.11655699461698532,
|
| 2101 |
+
"learning_rate": 0.0001709533607681756,
|
| 2102 |
+
"loss": 0.786558723449707,
|
| 2103 |
+
"step": 2990
|
| 2104 |
+
},
|
| 2105 |
+
{
|
| 2106 |
+
"epoch": 0.23150381016687566,
|
| 2107 |
+
"grad_norm": 0.14017945528030396,
|
| 2108 |
+
"learning_rate": 0.00017078189300411524,
|
| 2109 |
+
"loss": 0.8820916175842285,
|
| 2110 |
+
"step": 3000
|
| 2111 |
+
},
|
| 2112 |
+
{
|
| 2113 |
+
"epoch": 0.23227548953409857,
|
| 2114 |
+
"grad_norm": 0.12487129867076874,
|
| 2115 |
+
"learning_rate": 0.0001706104252400549,
|
| 2116 |
+
"loss": 0.8847643852233886,
|
| 2117 |
+
"step": 3010
|
| 2118 |
+
},
|
| 2119 |
+
{
|
| 2120 |
+
"epoch": 0.2330471689013215,
|
| 2121 |
+
"grad_norm": 0.12297922372817993,
|
| 2122 |
+
"learning_rate": 0.0001704389574759945,
|
| 2123 |
+
"loss": 0.8033929824829101,
|
| 2124 |
+
"step": 3020
|
| 2125 |
+
},
|
| 2126 |
+
{
|
| 2127 |
+
"epoch": 0.23381884826854443,
|
| 2128 |
+
"grad_norm": 0.16417784988880157,
|
| 2129 |
+
"learning_rate": 0.00017026748971193416,
|
| 2130 |
+
"loss": 0.819823169708252,
|
| 2131 |
+
"step": 3030
|
| 2132 |
+
},
|
| 2133 |
+
{
|
| 2134 |
+
"epoch": 0.23459052763576735,
|
| 2135 |
+
"grad_norm": 0.1531011015176773,
|
| 2136 |
+
"learning_rate": 0.0001700960219478738,
|
| 2137 |
+
"loss": 0.8654590606689453,
|
| 2138 |
+
"step": 3040
|
| 2139 |
+
},
|
| 2140 |
+
{
|
| 2141 |
+
"epoch": 0.23536220700299026,
|
| 2142 |
+
"grad_norm": 0.13741746544837952,
|
| 2143 |
+
"learning_rate": 0.00016992455418381346,
|
| 2144 |
+
"loss": 0.8356669425964356,
|
| 2145 |
+
"step": 3050
|
| 2146 |
+
},
|
| 2147 |
+
{
|
| 2148 |
+
"epoch": 0.23613388637021318,
|
| 2149 |
+
"grad_norm": 0.12235406786203384,
|
| 2150 |
+
"learning_rate": 0.00016975308641975308,
|
| 2151 |
+
"loss": 0.7874931335449219,
|
| 2152 |
+
"step": 3060
|
| 2153 |
+
},
|
| 2154 |
+
{
|
| 2155 |
+
"epoch": 0.2369055657374361,
|
| 2156 |
+
"grad_norm": 0.15917153656482697,
|
| 2157 |
+
"learning_rate": 0.00016958161865569273,
|
| 2158 |
+
"loss": 0.8752988815307617,
|
| 2159 |
+
"step": 3070
|
| 2160 |
+
},
|
| 2161 |
+
{
|
| 2162 |
+
"epoch": 0.237677245104659,
|
| 2163 |
+
"grad_norm": 0.13069361448287964,
|
| 2164 |
+
"learning_rate": 0.00016941015089163238,
|
| 2165 |
+
"loss": 0.877816104888916,
|
| 2166 |
+
"step": 3080
|
| 2167 |
+
},
|
| 2168 |
+
{
|
| 2169 |
+
"epoch": 0.23844892447188193,
|
| 2170 |
+
"grad_norm": 0.12786127626895905,
|
| 2171 |
+
"learning_rate": 0.00016923868312757203,
|
| 2172 |
+
"loss": 0.8660223960876465,
|
| 2173 |
+
"step": 3090
|
| 2174 |
+
},
|
| 2175 |
+
{
|
| 2176 |
+
"epoch": 0.23922060383910485,
|
| 2177 |
+
"grad_norm": 0.10427848249673843,
|
| 2178 |
+
"learning_rate": 0.00016906721536351168,
|
| 2179 |
+
"loss": 0.8196652412414551,
|
| 2180 |
+
"step": 3100
|
| 2181 |
+
},
|
| 2182 |
+
{
|
| 2183 |
+
"epoch": 0.23999228320632776,
|
| 2184 |
+
"grad_norm": 0.1204465851187706,
|
| 2185 |
+
"learning_rate": 0.0001688957475994513,
|
| 2186 |
+
"loss": 0.8015564918518067,
|
| 2187 |
+
"step": 3110
|
| 2188 |
+
},
|
| 2189 |
+
{
|
| 2190 |
+
"epoch": 0.24076396257355068,
|
| 2191 |
+
"grad_norm": 0.1356930285692215,
|
| 2192 |
+
"learning_rate": 0.00016872427983539098,
|
| 2193 |
+
"loss": 0.8163382530212402,
|
| 2194 |
+
"step": 3120
|
| 2195 |
+
},
|
| 2196 |
+
{
|
| 2197 |
+
"epoch": 0.24153564194077362,
|
| 2198 |
+
"grad_norm": 0.24513445794582367,
|
| 2199 |
+
"learning_rate": 0.0001685528120713306,
|
| 2200 |
+
"loss": 0.8484282493591309,
|
| 2201 |
+
"step": 3130
|
| 2202 |
+
},
|
| 2203 |
+
{
|
| 2204 |
+
"epoch": 0.24230732130799654,
|
| 2205 |
+
"grad_norm": 0.1258307546377182,
|
| 2206 |
+
"learning_rate": 0.00016838134430727025,
|
| 2207 |
+
"loss": 0.8763568878173829,
|
| 2208 |
+
"step": 3140
|
| 2209 |
+
},
|
| 2210 |
+
{
|
| 2211 |
+
"epoch": 0.24307900067521945,
|
| 2212 |
+
"grad_norm": 0.1511799544095993,
|
| 2213 |
+
"learning_rate": 0.00016820987654320987,
|
| 2214 |
+
"loss": 0.8349836349487305,
|
| 2215 |
+
"step": 3150
|
| 2216 |
+
},
|
| 2217 |
+
{
|
| 2218 |
+
"epoch": 0.24385068004244237,
|
| 2219 |
+
"grad_norm": 0.15442147850990295,
|
| 2220 |
+
"learning_rate": 0.00016803840877914955,
|
| 2221 |
+
"loss": 0.768619441986084,
|
| 2222 |
+
"step": 3160
|
| 2223 |
+
},
|
| 2224 |
+
{
|
| 2225 |
+
"epoch": 0.24462235940966529,
|
| 2226 |
+
"grad_norm": 0.14298409223556519,
|
| 2227 |
+
"learning_rate": 0.00016786694101508917,
|
| 2228 |
+
"loss": 0.8363221168518067,
|
| 2229 |
+
"step": 3170
|
| 2230 |
+
},
|
| 2231 |
+
{
|
| 2232 |
+
"epoch": 0.2453940387768882,
|
| 2233 |
+
"grad_norm": 0.11931406706571579,
|
| 2234 |
+
"learning_rate": 0.00016769547325102882,
|
| 2235 |
+
"loss": 0.8240514755249023,
|
| 2236 |
+
"step": 3180
|
| 2237 |
+
},
|
| 2238 |
+
{
|
| 2239 |
+
"epoch": 0.24616571814411112,
|
| 2240 |
+
"grad_norm": 0.18728391826152802,
|
| 2241 |
+
"learning_rate": 0.00016752400548696844,
|
| 2242 |
+
"loss": 0.8571996688842773,
|
| 2243 |
+
"step": 3190
|
| 2244 |
+
},
|
| 2245 |
+
{
|
| 2246 |
+
"epoch": 0.24693739751133403,
|
| 2247 |
+
"grad_norm": 0.12976998090744019,
|
| 2248 |
+
"learning_rate": 0.00016735253772290812,
|
| 2249 |
+
"loss": 0.7671982288360596,
|
| 2250 |
+
"step": 3200
|
| 2251 |
+
},
|
| 2252 |
+
{
|
| 2253 |
+
"epoch": 0.24770907687855695,
|
| 2254 |
+
"grad_norm": 0.12748423218727112,
|
| 2255 |
+
"learning_rate": 0.00016718106995884774,
|
| 2256 |
+
"loss": 0.7859314441680908,
|
| 2257 |
+
"step": 3210
|
| 2258 |
+
},
|
| 2259 |
+
{
|
| 2260 |
+
"epoch": 0.24848075624577987,
|
| 2261 |
+
"grad_norm": 0.14031143486499786,
|
| 2262 |
+
"learning_rate": 0.0001670096021947874,
|
| 2263 |
+
"loss": 0.8077226638793945,
|
| 2264 |
+
"step": 3220
|
| 2265 |
+
},
|
| 2266 |
+
{
|
| 2267 |
+
"epoch": 0.2492524356130028,
|
| 2268 |
+
"grad_norm": 0.12750263512134552,
|
| 2269 |
+
"learning_rate": 0.000166838134430727,
|
| 2270 |
+
"loss": 0.8905061721801758,
|
| 2271 |
+
"step": 3230
|
| 2272 |
+
},
|
| 2273 |
+
{
|
| 2274 |
+
"epoch": 0.2500241149802257,
|
| 2275 |
+
"grad_norm": 0.1253247708082199,
|
| 2276 |
+
"learning_rate": 0.0001666666666666667,
|
| 2277 |
+
"loss": 0.7827759265899659,
|
| 2278 |
+
"step": 3240
|
| 2279 |
+
},
|
| 2280 |
+
{
|
| 2281 |
+
"epoch": 0.25079579434744864,
|
| 2282 |
+
"grad_norm": 0.11356625705957413,
|
| 2283 |
+
"learning_rate": 0.0001664951989026063,
|
| 2284 |
+
"loss": 0.9060277938842773,
|
| 2285 |
+
"step": 3250
|
| 2286 |
+
},
|
| 2287 |
+
{
|
| 2288 |
+
"epoch": 0.25156747371467153,
|
| 2289 |
+
"grad_norm": 0.1360168755054474,
|
| 2290 |
+
"learning_rate": 0.00016632373113854596,
|
| 2291 |
+
"loss": 0.7898921966552734,
|
| 2292 |
+
"step": 3260
|
| 2293 |
+
},
|
| 2294 |
+
{
|
| 2295 |
+
"epoch": 0.2523391530818945,
|
| 2296 |
+
"grad_norm": 0.11251401156187057,
|
| 2297 |
+
"learning_rate": 0.00016615226337448558,
|
| 2298 |
+
"loss": 0.8594393730163574,
|
| 2299 |
+
"step": 3270
|
| 2300 |
+
},
|
| 2301 |
+
{
|
| 2302 |
+
"epoch": 0.2531108324491174,
|
| 2303 |
+
"grad_norm": 0.15321357548236847,
|
| 2304 |
+
"learning_rate": 0.00016598079561042526,
|
| 2305 |
+
"loss": 0.854586410522461,
|
| 2306 |
+
"step": 3280
|
| 2307 |
+
},
|
| 2308 |
+
{
|
| 2309 |
+
"epoch": 0.2538825118163403,
|
| 2310 |
+
"grad_norm": 0.14712406694889069,
|
| 2311 |
+
"learning_rate": 0.00016580932784636488,
|
| 2312 |
+
"loss": 0.8507588386535645,
|
| 2313 |
+
"step": 3290
|
| 2314 |
+
},
|
| 2315 |
+
{
|
| 2316 |
+
"epoch": 0.25465419118356325,
|
| 2317 |
+
"grad_norm": 0.11772070825099945,
|
| 2318 |
+
"learning_rate": 0.00016563786008230453,
|
| 2319 |
+
"loss": 0.9055712699890137,
|
| 2320 |
+
"step": 3300
|
| 2321 |
+
},
|
| 2322 |
+
{
|
| 2323 |
+
"epoch": 0.25542587055078614,
|
| 2324 |
+
"grad_norm": 0.14351730048656464,
|
| 2325 |
+
"learning_rate": 0.00016546639231824418,
|
| 2326 |
+
"loss": 0.8199276924133301,
|
| 2327 |
+
"step": 3310
|
| 2328 |
+
},
|
| 2329 |
+
{
|
| 2330 |
+
"epoch": 0.2561975499180091,
|
| 2331 |
+
"grad_norm": 0.1255323439836502,
|
| 2332 |
+
"learning_rate": 0.00016529492455418383,
|
| 2333 |
+
"loss": 0.8413225173950195,
|
| 2334 |
+
"step": 3320
|
| 2335 |
+
},
|
| 2336 |
+
{
|
| 2337 |
+
"epoch": 0.25696922928523197,
|
| 2338 |
+
"grad_norm": 0.12912032008171082,
|
| 2339 |
+
"learning_rate": 0.00016512345679012348,
|
| 2340 |
+
"loss": 0.8220077514648437,
|
| 2341 |
+
"step": 3330
|
| 2342 |
+
},
|
| 2343 |
+
{
|
| 2344 |
+
"epoch": 0.2577409086524549,
|
| 2345 |
+
"grad_norm": 0.12320882827043533,
|
| 2346 |
+
"learning_rate": 0.0001649519890260631,
|
| 2347 |
+
"loss": 0.8752640724182129,
|
| 2348 |
+
"step": 3340
|
| 2349 |
+
},
|
| 2350 |
+
{
|
| 2351 |
+
"epoch": 0.2585125880196778,
|
| 2352 |
+
"grad_norm": 0.2623811960220337,
|
| 2353 |
+
"learning_rate": 0.00016478052126200275,
|
| 2354 |
+
"loss": 0.8364349365234375,
|
| 2355 |
+
"step": 3350
|
| 2356 |
+
},
|
| 2357 |
+
{
|
| 2358 |
+
"epoch": 0.25928426738690075,
|
| 2359 |
+
"grad_norm": 0.132389634847641,
|
| 2360 |
+
"learning_rate": 0.0001646090534979424,
|
| 2361 |
+
"loss": 0.756529426574707,
|
| 2362 |
+
"step": 3360
|
| 2363 |
+
},
|
| 2364 |
+
{
|
| 2365 |
+
"epoch": 0.26005594675412363,
|
| 2366 |
+
"grad_norm": 0.12747901678085327,
|
| 2367 |
+
"learning_rate": 0.00016443758573388205,
|
| 2368 |
+
"loss": 0.8000151634216308,
|
| 2369 |
+
"step": 3370
|
| 2370 |
+
},
|
| 2371 |
+
{
|
| 2372 |
+
"epoch": 0.2608276261213466,
|
| 2373 |
+
"grad_norm": 0.1263447403907776,
|
| 2374 |
+
"learning_rate": 0.00016426611796982167,
|
| 2375 |
+
"loss": 0.7739401817321777,
|
| 2376 |
+
"step": 3380
|
| 2377 |
+
},
|
| 2378 |
+
{
|
| 2379 |
+
"epoch": 0.2615993054885695,
|
| 2380 |
+
"grad_norm": 0.11336930096149445,
|
| 2381 |
+
"learning_rate": 0.00016409465020576135,
|
| 2382 |
+
"loss": 0.8851364135742188,
|
| 2383 |
+
"step": 3390
|
| 2384 |
+
},
|
| 2385 |
+
{
|
| 2386 |
+
"epoch": 0.2623709848557924,
|
| 2387 |
+
"grad_norm": 0.14022980630397797,
|
| 2388 |
+
"learning_rate": 0.00016392318244170097,
|
| 2389 |
+
"loss": 0.8246338844299317,
|
| 2390 |
+
"step": 3400
|
| 2391 |
+
},
|
| 2392 |
+
{
|
| 2393 |
+
"epoch": 0.26314266422301535,
|
| 2394 |
+
"grad_norm": 0.1415836066007614,
|
| 2395 |
+
"learning_rate": 0.00016375171467764062,
|
| 2396 |
+
"loss": 0.8389305114746094,
|
| 2397 |
+
"step": 3410
|
| 2398 |
+
},
|
| 2399 |
+
{
|
| 2400 |
+
"epoch": 0.26391434359023824,
|
| 2401 |
+
"grad_norm": 0.1447453796863556,
|
| 2402 |
+
"learning_rate": 0.00016358024691358024,
|
| 2403 |
+
"loss": 0.8960967063903809,
|
| 2404 |
+
"step": 3420
|
| 2405 |
+
},
|
| 2406 |
+
{
|
| 2407 |
+
"epoch": 0.2646860229574612,
|
| 2408 |
+
"grad_norm": 0.14884066581726074,
|
| 2409 |
+
"learning_rate": 0.00016340877914951992,
|
| 2410 |
+
"loss": 0.7871220588684082,
|
| 2411 |
+
"step": 3430
|
| 2412 |
+
},
|
| 2413 |
+
{
|
| 2414 |
+
"epoch": 0.2654577023246841,
|
| 2415 |
+
"grad_norm": 0.13969279825687408,
|
| 2416 |
+
"learning_rate": 0.00016323731138545954,
|
| 2417 |
+
"loss": 0.837588119506836,
|
| 2418 |
+
"step": 3440
|
| 2419 |
+
},
|
| 2420 |
+
{
|
| 2421 |
+
"epoch": 0.266229381691907,
|
| 2422 |
+
"grad_norm": 0.1123804822564125,
|
| 2423 |
+
"learning_rate": 0.0001630658436213992,
|
| 2424 |
+
"loss": 0.7968134403228759,
|
| 2425 |
+
"step": 3450
|
| 2426 |
+
},
|
| 2427 |
+
{
|
| 2428 |
+
"epoch": 0.2670010610591299,
|
| 2429 |
+
"grad_norm": 0.1521446704864502,
|
| 2430 |
+
"learning_rate": 0.0001628943758573388,
|
| 2431 |
+
"loss": 0.7750689029693604,
|
| 2432 |
+
"step": 3460
|
| 2433 |
+
},
|
| 2434 |
+
{
|
| 2435 |
+
"epoch": 0.26777274042635285,
|
| 2436 |
+
"grad_norm": 0.14444394409656525,
|
| 2437 |
+
"learning_rate": 0.0001627229080932785,
|
| 2438 |
+
"loss": 0.8163520812988281,
|
| 2439 |
+
"step": 3470
|
| 2440 |
+
},
|
| 2441 |
+
{
|
| 2442 |
+
"epoch": 0.2685444197935758,
|
| 2443 |
+
"grad_norm": 0.13975541293621063,
|
| 2444 |
+
"learning_rate": 0.0001625514403292181,
|
| 2445 |
+
"loss": 0.8249734878540039,
|
| 2446 |
+
"step": 3480
|
| 2447 |
+
},
|
| 2448 |
+
{
|
| 2449 |
+
"epoch": 0.2693160991607987,
|
| 2450 |
+
"grad_norm": 0.13847948610782623,
|
| 2451 |
+
"learning_rate": 0.00016237997256515776,
|
| 2452 |
+
"loss": 0.7773365020751953,
|
| 2453 |
+
"step": 3490
|
| 2454 |
+
},
|
| 2455 |
+
{
|
| 2456 |
+
"epoch": 0.2700877785280216,
|
| 2457 |
+
"grad_norm": 0.13473714888095856,
|
| 2458 |
+
"learning_rate": 0.00016220850480109738,
|
| 2459 |
+
"loss": 0.819399070739746,
|
| 2460 |
+
"step": 3500
|
| 2461 |
+
},
|
| 2462 |
+
{
|
| 2463 |
+
"epoch": 0.2708594578952445,
|
| 2464 |
+
"grad_norm": 0.11676599830389023,
|
| 2465 |
+
"learning_rate": 0.00016203703703703706,
|
| 2466 |
+
"loss": 0.779163932800293,
|
| 2467 |
+
"step": 3510
|
| 2468 |
+
},
|
| 2469 |
+
{
|
| 2470 |
+
"epoch": 0.27163113726246746,
|
| 2471 |
+
"grad_norm": 0.12352027744054794,
|
| 2472 |
+
"learning_rate": 0.00016186556927297668,
|
| 2473 |
+
"loss": 0.804078197479248,
|
| 2474 |
+
"step": 3520
|
| 2475 |
+
},
|
| 2476 |
+
{
|
| 2477 |
+
"epoch": 0.27240281662969035,
|
| 2478 |
+
"grad_norm": 0.15879623591899872,
|
| 2479 |
+
"learning_rate": 0.00016169410150891633,
|
| 2480 |
+
"loss": 0.9352669715881348,
|
| 2481 |
+
"step": 3530
|
| 2482 |
+
},
|
| 2483 |
+
{
|
| 2484 |
+
"epoch": 0.2731744959969133,
|
| 2485 |
+
"grad_norm": 0.15267331898212433,
|
| 2486 |
+
"learning_rate": 0.00016152263374485595,
|
| 2487 |
+
"loss": 0.8269804954528809,
|
| 2488 |
+
"step": 3540
|
| 2489 |
+
},
|
| 2490 |
+
{
|
| 2491 |
+
"epoch": 0.2739461753641362,
|
| 2492 |
+
"grad_norm": 0.1624394804239273,
|
| 2493 |
+
"learning_rate": 0.00016135116598079563,
|
| 2494 |
+
"loss": 0.9027270317077637,
|
| 2495 |
+
"step": 3550
|
| 2496 |
+
},
|
| 2497 |
+
{
|
| 2498 |
+
"epoch": 0.2747178547313591,
|
| 2499 |
+
"grad_norm": 0.10725253075361252,
|
| 2500 |
+
"learning_rate": 0.00016117969821673525,
|
| 2501 |
+
"loss": 0.7687301158905029,
|
| 2502 |
+
"step": 3560
|
| 2503 |
+
},
|
| 2504 |
+
{
|
| 2505 |
+
"epoch": 0.275489534098582,
|
| 2506 |
+
"grad_norm": 0.13683226704597473,
|
| 2507 |
+
"learning_rate": 0.0001610082304526749,
|
| 2508 |
+
"loss": 0.8373688697814942,
|
| 2509 |
+
"step": 3570
|
| 2510 |
+
},
|
| 2511 |
+
{
|
| 2512 |
+
"epoch": 0.27626121346580496,
|
| 2513 |
+
"grad_norm": 0.15954583883285522,
|
| 2514 |
+
"learning_rate": 0.00016083676268861455,
|
| 2515 |
+
"loss": 0.7844015121459961,
|
| 2516 |
+
"step": 3580
|
| 2517 |
+
},
|
| 2518 |
+
{
|
| 2519 |
+
"epoch": 0.2770328928330279,
|
| 2520 |
+
"grad_norm": 0.14278897643089294,
|
| 2521 |
+
"learning_rate": 0.0001606652949245542,
|
| 2522 |
+
"loss": 0.8766173362731934,
|
| 2523 |
+
"step": 3590
|
| 2524 |
+
},
|
| 2525 |
+
{
|
| 2526 |
+
"epoch": 0.2778045722002508,
|
| 2527 |
+
"grad_norm": 0.10004450380802155,
|
| 2528 |
+
"learning_rate": 0.00016049382716049385,
|
| 2529 |
+
"loss": 0.7629057407379151,
|
| 2530 |
+
"step": 3600
|
| 2531 |
+
},
|
| 2532 |
+
{
|
| 2533 |
+
"epoch": 0.27857625156747373,
|
| 2534 |
+
"grad_norm": 0.12769654393196106,
|
| 2535 |
+
"learning_rate": 0.00016032235939643347,
|
| 2536 |
+
"loss": 0.8495834350585938,
|
| 2537 |
+
"step": 3610
|
| 2538 |
+
},
|
| 2539 |
+
{
|
| 2540 |
+
"epoch": 0.2793479309346966,
|
| 2541 |
+
"grad_norm": 0.14054711163043976,
|
| 2542 |
+
"learning_rate": 0.00016015089163237312,
|
| 2543 |
+
"loss": 0.8330297470092773,
|
| 2544 |
+
"step": 3620
|
| 2545 |
+
},
|
| 2546 |
+
{
|
| 2547 |
+
"epoch": 0.28011961030191956,
|
| 2548 |
+
"grad_norm": 0.16965901851654053,
|
| 2549 |
+
"learning_rate": 0.00015997942386831277,
|
| 2550 |
+
"loss": 0.8351662635803223,
|
| 2551 |
+
"step": 3630
|
| 2552 |
+
},
|
| 2553 |
+
{
|
| 2554 |
+
"epoch": 0.28089128966914245,
|
| 2555 |
+
"grad_norm": 0.12975865602493286,
|
| 2556 |
+
"learning_rate": 0.00015980795610425242,
|
| 2557 |
+
"loss": 0.893592357635498,
|
| 2558 |
+
"step": 3640
|
| 2559 |
+
},
|
| 2560 |
+
{
|
| 2561 |
+
"epoch": 0.2816629690363654,
|
| 2562 |
+
"grad_norm": 0.15801310539245605,
|
| 2563 |
+
"learning_rate": 0.00015963648834019204,
|
| 2564 |
+
"loss": 0.7849035263061523,
|
| 2565 |
+
"step": 3650
|
| 2566 |
+
},
|
| 2567 |
+
{
|
| 2568 |
+
"epoch": 0.2824346484035883,
|
| 2569 |
+
"grad_norm": 0.14637868106365204,
|
| 2570 |
+
"learning_rate": 0.0001594650205761317,
|
| 2571 |
+
"loss": 0.8064953804016113,
|
| 2572 |
+
"step": 3660
|
| 2573 |
+
},
|
| 2574 |
+
{
|
| 2575 |
+
"epoch": 0.28320632777081123,
|
| 2576 |
+
"grad_norm": 0.12257670611143112,
|
| 2577 |
+
"learning_rate": 0.00015929355281207134,
|
| 2578 |
+
"loss": 0.8076671600341797,
|
| 2579 |
+
"step": 3670
|
| 2580 |
+
},
|
| 2581 |
+
{
|
| 2582 |
+
"epoch": 0.28397800713803417,
|
| 2583 |
+
"grad_norm": 0.1313459724187851,
|
| 2584 |
+
"learning_rate": 0.000159122085048011,
|
| 2585 |
+
"loss": 0.8230973243713379,
|
| 2586 |
+
"step": 3680
|
| 2587 |
+
},
|
| 2588 |
+
{
|
| 2589 |
+
"epoch": 0.28474968650525706,
|
| 2590 |
+
"grad_norm": 0.14811420440673828,
|
| 2591 |
+
"learning_rate": 0.0001589506172839506,
|
| 2592 |
+
"loss": 0.8357210159301758,
|
| 2593 |
+
"step": 3690
|
| 2594 |
+
},
|
| 2595 |
+
{
|
| 2596 |
+
"epoch": 0.28552136587248,
|
| 2597 |
+
"grad_norm": 0.1593637764453888,
|
| 2598 |
+
"learning_rate": 0.00015877914951989026,
|
| 2599 |
+
"loss": 0.8747388839721679,
|
| 2600 |
+
"step": 3700
|
| 2601 |
+
},
|
| 2602 |
+
{
|
| 2603 |
+
"epoch": 0.2862930452397029,
|
| 2604 |
+
"grad_norm": 0.15067414939403534,
|
| 2605 |
+
"learning_rate": 0.0001586076817558299,
|
| 2606 |
+
"loss": 0.8474630355834961,
|
| 2607 |
+
"step": 3710
|
| 2608 |
+
},
|
| 2609 |
+
{
|
| 2610 |
+
"epoch": 0.28706472460692584,
|
| 2611 |
+
"grad_norm": 0.13254724442958832,
|
| 2612 |
+
"learning_rate": 0.00015843621399176956,
|
| 2613 |
+
"loss": 0.7940406322479248,
|
| 2614 |
+
"step": 3720
|
| 2615 |
+
},
|
| 2616 |
+
{
|
| 2617 |
+
"epoch": 0.2878364039741487,
|
| 2618 |
+
"grad_norm": 0.1223297193646431,
|
| 2619 |
+
"learning_rate": 0.00015826474622770918,
|
| 2620 |
+
"loss": 0.7828914165496826,
|
| 2621 |
+
"step": 3730
|
| 2622 |
+
},
|
| 2623 |
+
{
|
| 2624 |
+
"epoch": 0.28860808334137167,
|
| 2625 |
+
"grad_norm": 0.10676020383834839,
|
| 2626 |
+
"learning_rate": 0.00015809327846364883,
|
| 2627 |
+
"loss": 0.8743107795715332,
|
| 2628 |
+
"step": 3740
|
| 2629 |
+
},
|
| 2630 |
+
{
|
| 2631 |
+
"epoch": 0.28937976270859456,
|
| 2632 |
+
"grad_norm": 0.13496406376361847,
|
| 2633 |
+
"learning_rate": 0.00015792181069958848,
|
| 2634 |
+
"loss": 0.869862174987793,
|
| 2635 |
+
"step": 3750
|
| 2636 |
+
},
|
| 2637 |
+
{
|
| 2638 |
+
"epoch": 0.2901514420758175,
|
| 2639 |
+
"grad_norm": 0.17639778554439545,
|
| 2640 |
+
"learning_rate": 0.00015775034293552813,
|
| 2641 |
+
"loss": 0.830924129486084,
|
| 2642 |
+
"step": 3760
|
| 2643 |
+
},
|
| 2644 |
+
{
|
| 2645 |
+
"epoch": 0.29092312144304044,
|
| 2646 |
+
"grad_norm": 0.13989681005477905,
|
| 2647 |
+
"learning_rate": 0.00015757887517146775,
|
| 2648 |
+
"loss": 0.8048736572265625,
|
| 2649 |
+
"step": 3770
|
| 2650 |
+
},
|
| 2651 |
+
{
|
| 2652 |
+
"epoch": 0.29169480081026333,
|
| 2653 |
+
"grad_norm": 0.1636296808719635,
|
| 2654 |
+
"learning_rate": 0.00015740740740740743,
|
| 2655 |
+
"loss": 0.9431006431579589,
|
| 2656 |
+
"step": 3780
|
| 2657 |
+
},
|
| 2658 |
+
{
|
| 2659 |
+
"epoch": 0.2924664801774863,
|
| 2660 |
+
"grad_norm": 0.13841512799263,
|
| 2661 |
+
"learning_rate": 0.00015723593964334705,
|
| 2662 |
+
"loss": 0.8598175048828125,
|
| 2663 |
+
"step": 3790
|
| 2664 |
+
},
|
| 2665 |
+
{
|
| 2666 |
+
"epoch": 0.29323815954470916,
|
| 2667 |
+
"grad_norm": 0.15369687974452972,
|
| 2668 |
+
"learning_rate": 0.0001570644718792867,
|
| 2669 |
+
"loss": 0.8336953163146973,
|
| 2670 |
+
"step": 3800
|
| 2671 |
+
},
|
| 2672 |
+
{
|
| 2673 |
+
"epoch": 0.2940098389119321,
|
| 2674 |
+
"grad_norm": 0.10148610174655914,
|
| 2675 |
+
"learning_rate": 0.00015689300411522635,
|
| 2676 |
+
"loss": 0.867680835723877,
|
| 2677 |
+
"step": 3810
|
| 2678 |
+
},
|
| 2679 |
+
{
|
| 2680 |
+
"epoch": 0.294781518279155,
|
| 2681 |
+
"grad_norm": 0.18394576013088226,
|
| 2682 |
+
"learning_rate": 0.000156721536351166,
|
| 2683 |
+
"loss": 0.863736629486084,
|
| 2684 |
+
"step": 3820
|
| 2685 |
+
},
|
| 2686 |
+
{
|
| 2687 |
+
"epoch": 0.29555319764637794,
|
| 2688 |
+
"grad_norm": 0.13761882483959198,
|
| 2689 |
+
"learning_rate": 0.00015655006858710562,
|
| 2690 |
+
"loss": 0.8518194198608399,
|
| 2691 |
+
"step": 3830
|
| 2692 |
+
},
|
| 2693 |
+
{
|
| 2694 |
+
"epoch": 0.29632487701360083,
|
| 2695 |
+
"grad_norm": 0.14121606945991516,
|
| 2696 |
+
"learning_rate": 0.00015637860082304527,
|
| 2697 |
+
"loss": 0.8484822273254394,
|
| 2698 |
+
"step": 3840
|
| 2699 |
+
},
|
| 2700 |
+
{
|
| 2701 |
+
"epoch": 0.2970965563808238,
|
| 2702 |
+
"grad_norm": 0.1203160509467125,
|
| 2703 |
+
"learning_rate": 0.00015620713305898492,
|
| 2704 |
+
"loss": 0.818821907043457,
|
| 2705 |
+
"step": 3850
|
| 2706 |
+
},
|
| 2707 |
+
{
|
| 2708 |
+
"epoch": 0.29786823574804666,
|
| 2709 |
+
"grad_norm": 0.14057768881320953,
|
| 2710 |
+
"learning_rate": 0.00015603566529492457,
|
| 2711 |
+
"loss": 0.8779332160949707,
|
| 2712 |
+
"step": 3860
|
| 2713 |
+
},
|
| 2714 |
+
{
|
| 2715 |
+
"epoch": 0.2986399151152696,
|
| 2716 |
+
"grad_norm": 0.15813900530338287,
|
| 2717 |
+
"learning_rate": 0.00015586419753086422,
|
| 2718 |
+
"loss": 0.8108746528625488,
|
| 2719 |
+
"step": 3870
|
| 2720 |
+
},
|
| 2721 |
+
{
|
| 2722 |
+
"epoch": 0.29941159448249255,
|
| 2723 |
+
"grad_norm": 0.135147362947464,
|
| 2724 |
+
"learning_rate": 0.00015569272976680384,
|
| 2725 |
+
"loss": 0.7456881999969482,
|
| 2726 |
+
"step": 3880
|
| 2727 |
+
},
|
| 2728 |
+
{
|
| 2729 |
+
"epoch": 0.30018327384971544,
|
| 2730 |
+
"grad_norm": 0.13444091379642487,
|
| 2731 |
+
"learning_rate": 0.0001555212620027435,
|
| 2732 |
+
"loss": 0.7636943817138672,
|
| 2733 |
+
"step": 3890
|
| 2734 |
+
},
|
| 2735 |
+
{
|
| 2736 |
+
"epoch": 0.3009549532169384,
|
| 2737 |
+
"grad_norm": 0.13757798075675964,
|
| 2738 |
+
"learning_rate": 0.00015534979423868314,
|
| 2739 |
+
"loss": 0.8616155624389649,
|
| 2740 |
+
"step": 3900
|
| 2741 |
+
},
|
| 2742 |
+
{
|
| 2743 |
+
"epoch": 0.30172663258416127,
|
| 2744 |
+
"grad_norm": 0.10434421896934509,
|
| 2745 |
+
"learning_rate": 0.0001551783264746228,
|
| 2746 |
+
"loss": 0.7787850379943848,
|
| 2747 |
+
"step": 3910
|
| 2748 |
+
},
|
| 2749 |
+
{
|
| 2750 |
+
"epoch": 0.3024983119513842,
|
| 2751 |
+
"grad_norm": 0.12897703051567078,
|
| 2752 |
+
"learning_rate": 0.00015500685871056241,
|
| 2753 |
+
"loss": 0.753928279876709,
|
| 2754 |
+
"step": 3920
|
| 2755 |
+
},
|
| 2756 |
+
{
|
| 2757 |
+
"epoch": 0.3032699913186071,
|
| 2758 |
+
"grad_norm": 0.1417548656463623,
|
| 2759 |
+
"learning_rate": 0.00015483539094650206,
|
| 2760 |
+
"loss": 0.7543911933898926,
|
| 2761 |
+
"step": 3930
|
| 2762 |
+
},
|
| 2763 |
+
{
|
| 2764 |
+
"epoch": 0.30404167068583005,
|
| 2765 |
+
"grad_norm": 0.13236507773399353,
|
| 2766 |
+
"learning_rate": 0.0001546639231824417,
|
| 2767 |
+
"loss": 0.7871809959411621,
|
| 2768 |
+
"step": 3940
|
| 2769 |
+
},
|
| 2770 |
+
{
|
| 2771 |
+
"epoch": 0.30481335005305293,
|
| 2772 |
+
"grad_norm": 0.1445067822933197,
|
| 2773 |
+
"learning_rate": 0.00015449245541838136,
|
| 2774 |
+
"loss": 0.8031238555908203,
|
| 2775 |
+
"step": 3950
|
| 2776 |
+
},
|
| 2777 |
+
{
|
| 2778 |
+
"epoch": 0.3055850294202759,
|
| 2779 |
+
"grad_norm": 0.12821638584136963,
|
| 2780 |
+
"learning_rate": 0.00015432098765432098,
|
| 2781 |
+
"loss": 0.8052983283996582,
|
| 2782 |
+
"step": 3960
|
| 2783 |
+
},
|
| 2784 |
+
{
|
| 2785 |
+
"epoch": 0.3063567087874988,
|
| 2786 |
+
"grad_norm": 0.13501565158367157,
|
| 2787 |
+
"learning_rate": 0.00015414951989026063,
|
| 2788 |
+
"loss": 0.8471232414245605,
|
| 2789 |
+
"step": 3970
|
| 2790 |
+
},
|
| 2791 |
+
{
|
| 2792 |
+
"epoch": 0.3071283881547217,
|
| 2793 |
+
"grad_norm": 0.1196683943271637,
|
| 2794 |
+
"learning_rate": 0.00015397805212620028,
|
| 2795 |
+
"loss": 0.7595149517059326,
|
| 2796 |
+
"step": 3980
|
| 2797 |
+
},
|
| 2798 |
+
{
|
| 2799 |
+
"epoch": 0.30790006752194465,
|
| 2800 |
+
"grad_norm": 0.12833383679389954,
|
| 2801 |
+
"learning_rate": 0.00015380658436213993,
|
| 2802 |
+
"loss": 0.8490877151489258,
|
| 2803 |
+
"step": 3990
|
| 2804 |
+
},
|
| 2805 |
+
{
|
| 2806 |
+
"epoch": 0.30867174688916754,
|
| 2807 |
+
"grad_norm": 0.098176009953022,
|
| 2808 |
+
"learning_rate": 0.00015363511659807956,
|
| 2809 |
+
"loss": 0.8514268875122071,
|
| 2810 |
+
"step": 4000
|
| 2811 |
+
},
|
| 2812 |
+
{
|
| 2813 |
+
"epoch": 0.3094434262563905,
|
| 2814 |
+
"grad_norm": 0.12363216280937195,
|
| 2815 |
+
"learning_rate": 0.0001534636488340192,
|
| 2816 |
+
"loss": 0.7685100555419921,
|
| 2817 |
+
"step": 4010
|
| 2818 |
+
},
|
| 2819 |
+
{
|
| 2820 |
+
"epoch": 0.3102151056236134,
|
| 2821 |
+
"grad_norm": 0.12742134928703308,
|
| 2822 |
+
"learning_rate": 0.00015329218106995885,
|
| 2823 |
+
"loss": 0.8493739128112793,
|
| 2824 |
+
"step": 4020
|
| 2825 |
+
},
|
| 2826 |
+
{
|
| 2827 |
+
"epoch": 0.3109867849908363,
|
| 2828 |
+
"grad_norm": 0.13222931325435638,
|
| 2829 |
+
"learning_rate": 0.0001531207133058985,
|
| 2830 |
+
"loss": 0.8350587844848633,
|
| 2831 |
+
"step": 4030
|
| 2832 |
+
},
|
| 2833 |
+
{
|
| 2834 |
+
"epoch": 0.3117584643580592,
|
| 2835 |
+
"grad_norm": 0.12401147186756134,
|
| 2836 |
+
"learning_rate": 0.00015294924554183813,
|
| 2837 |
+
"loss": 0.7676318645477295,
|
| 2838 |
+
"step": 4040
|
| 2839 |
+
},
|
| 2840 |
+
{
|
| 2841 |
+
"epoch": 0.31253014372528215,
|
| 2842 |
+
"grad_norm": 0.1451227068901062,
|
| 2843 |
+
"learning_rate": 0.00015277777777777777,
|
| 2844 |
+
"loss": 0.857386302947998,
|
| 2845 |
+
"step": 4050
|
| 2846 |
+
},
|
| 2847 |
+
{
|
| 2848 |
+
"epoch": 0.31330182309250504,
|
| 2849 |
+
"grad_norm": 0.1386488378047943,
|
| 2850 |
+
"learning_rate": 0.00015260631001371742,
|
| 2851 |
+
"loss": 0.838217830657959,
|
| 2852 |
+
"step": 4060
|
| 2853 |
+
},
|
| 2854 |
+
{
|
| 2855 |
+
"epoch": 0.314073502459728,
|
| 2856 |
+
"grad_norm": 0.14964058995246887,
|
| 2857 |
+
"learning_rate": 0.00015243484224965707,
|
| 2858 |
+
"loss": 0.7892953872680664,
|
| 2859 |
+
"step": 4070
|
| 2860 |
+
},
|
| 2861 |
+
{
|
| 2862 |
+
"epoch": 0.3148451818269509,
|
| 2863 |
+
"grad_norm": 0.13118557631969452,
|
| 2864 |
+
"learning_rate": 0.00015226337448559672,
|
| 2865 |
+
"loss": 0.7844328880310059,
|
| 2866 |
+
"step": 4080
|
| 2867 |
+
},
|
| 2868 |
+
{
|
| 2869 |
+
"epoch": 0.3156168611941738,
|
| 2870 |
+
"grad_norm": 0.12486426532268524,
|
| 2871 |
+
"learning_rate": 0.00015209190672153635,
|
| 2872 |
+
"loss": 0.8688708305358886,
|
| 2873 |
+
"step": 4090
|
| 2874 |
+
},
|
| 2875 |
+
{
|
| 2876 |
+
"epoch": 0.31638854056139676,
|
| 2877 |
+
"grad_norm": 0.1207025870680809,
|
| 2878 |
+
"learning_rate": 0.000151920438957476,
|
| 2879 |
+
"loss": 0.7573784351348877,
|
| 2880 |
+
"step": 4100
|
| 2881 |
+
},
|
| 2882 |
+
{
|
| 2883 |
+
"epoch": 0.31716021992861965,
|
| 2884 |
+
"grad_norm": 0.12926630675792694,
|
| 2885 |
+
"learning_rate": 0.00015174897119341564,
|
| 2886 |
+
"loss": 0.796429967880249,
|
| 2887 |
+
"step": 4110
|
| 2888 |
+
},
|
| 2889 |
+
{
|
| 2890 |
+
"epoch": 0.3179318992958426,
|
| 2891 |
+
"grad_norm": 0.11644221097230911,
|
| 2892 |
+
"learning_rate": 0.0001515775034293553,
|
| 2893 |
+
"loss": 0.7781257629394531,
|
| 2894 |
+
"step": 4120
|
| 2895 |
+
},
|
| 2896 |
+
{
|
| 2897 |
+
"epoch": 0.3187035786630655,
|
| 2898 |
+
"grad_norm": 0.13467998802661896,
|
| 2899 |
+
"learning_rate": 0.00015140603566529492,
|
| 2900 |
+
"loss": 0.8052960395812988,
|
| 2901 |
+
"step": 4130
|
| 2902 |
+
},
|
| 2903 |
+
{
|
| 2904 |
+
"epoch": 0.3194752580302884,
|
| 2905 |
+
"grad_norm": 0.11296537518501282,
|
| 2906 |
+
"learning_rate": 0.0001512345679012346,
|
| 2907 |
+
"loss": 0.8008211135864258,
|
| 2908 |
+
"step": 4140
|
| 2909 |
+
},
|
| 2910 |
+
{
|
| 2911 |
+
"epoch": 0.3202469373975113,
|
| 2912 |
+
"grad_norm": 0.13329783082008362,
|
| 2913 |
+
"learning_rate": 0.00015106310013717421,
|
| 2914 |
+
"loss": 0.8355886459350585,
|
| 2915 |
+
"step": 4150
|
| 2916 |
+
},
|
| 2917 |
+
{
|
| 2918 |
+
"epoch": 0.32101861676473425,
|
| 2919 |
+
"grad_norm": 0.15643227100372314,
|
| 2920 |
+
"learning_rate": 0.00015089163237311386,
|
| 2921 |
+
"loss": 0.7765786647796631,
|
| 2922 |
+
"step": 4160
|
| 2923 |
+
},
|
| 2924 |
+
{
|
| 2925 |
+
"epoch": 0.3217902961319572,
|
| 2926 |
+
"grad_norm": 0.11483335494995117,
|
| 2927 |
+
"learning_rate": 0.00015072016460905351,
|
| 2928 |
+
"loss": 0.8904210090637207,
|
| 2929 |
+
"step": 4170
|
| 2930 |
+
},
|
| 2931 |
+
{
|
| 2932 |
+
"epoch": 0.3225619754991801,
|
| 2933 |
+
"grad_norm": 0.13604721426963806,
|
| 2934 |
+
"learning_rate": 0.00015054869684499316,
|
| 2935 |
+
"loss": 0.8202609062194824,
|
| 2936 |
+
"step": 4180
|
| 2937 |
+
},
|
| 2938 |
+
{
|
| 2939 |
+
"epoch": 0.32333365486640303,
|
| 2940 |
+
"grad_norm": 0.1352788507938385,
|
| 2941 |
+
"learning_rate": 0.00015037722908093279,
|
| 2942 |
+
"loss": 0.7799928665161133,
|
| 2943 |
+
"step": 4190
|
| 2944 |
+
},
|
| 2945 |
+
{
|
| 2946 |
+
"epoch": 0.3241053342336259,
|
| 2947 |
+
"grad_norm": 0.12347330898046494,
|
| 2948 |
+
"learning_rate": 0.00015020576131687243,
|
| 2949 |
+
"loss": 0.8344977378845215,
|
| 2950 |
+
"step": 4200
|
| 2951 |
+
},
|
| 2952 |
+
{
|
| 2953 |
+
"epoch": 0.32487701360084886,
|
| 2954 |
+
"grad_norm": 0.1332758665084839,
|
| 2955 |
+
"learning_rate": 0.00015003429355281208,
|
| 2956 |
+
"loss": 0.838437557220459,
|
| 2957 |
+
"step": 4210
|
| 2958 |
+
},
|
| 2959 |
+
{
|
| 2960 |
+
"epoch": 0.32564869296807175,
|
| 2961 |
+
"grad_norm": 0.13366325199604034,
|
| 2962 |
+
"learning_rate": 0.00014986282578875173,
|
| 2963 |
+
"loss": 0.8127938270568847,
|
| 2964 |
+
"step": 4220
|
| 2965 |
+
},
|
| 2966 |
+
{
|
| 2967 |
+
"epoch": 0.3264203723352947,
|
| 2968 |
+
"grad_norm": 0.12844043970108032,
|
| 2969 |
+
"learning_rate": 0.00014969135802469136,
|
| 2970 |
+
"loss": 0.8002336502075196,
|
| 2971 |
+
"step": 4230
|
| 2972 |
+
},
|
| 2973 |
+
{
|
| 2974 |
+
"epoch": 0.3271920517025176,
|
| 2975 |
+
"grad_norm": 0.1347084790468216,
|
| 2976 |
+
"learning_rate": 0.000149519890260631,
|
| 2977 |
+
"loss": 0.9231692314147949,
|
| 2978 |
+
"step": 4240
|
| 2979 |
+
},
|
| 2980 |
+
{
|
| 2981 |
+
"epoch": 0.3279637310697405,
|
| 2982 |
+
"grad_norm": 0.12897898256778717,
|
| 2983 |
+
"learning_rate": 0.00014934842249657065,
|
| 2984 |
+
"loss": 0.77931227684021,
|
| 2985 |
+
"step": 4250
|
| 2986 |
+
},
|
| 2987 |
+
{
|
| 2988 |
+
"epoch": 0.3287354104369634,
|
| 2989 |
+
"grad_norm": 0.12322626262903214,
|
| 2990 |
+
"learning_rate": 0.0001491769547325103,
|
| 2991 |
+
"loss": 0.8108692169189453,
|
| 2992 |
+
"step": 4260
|
| 2993 |
+
},
|
| 2994 |
+
{
|
| 2995 |
+
"epoch": 0.32950708980418636,
|
| 2996 |
+
"grad_norm": 0.13034410774707794,
|
| 2997 |
+
"learning_rate": 0.00014900548696844993,
|
| 2998 |
+
"loss": 0.8122691154479981,
|
| 2999 |
+
"step": 4270
|
| 3000 |
+
},
|
| 3001 |
+
{
|
| 3002 |
+
"epoch": 0.3302787691714093,
|
| 3003 |
+
"grad_norm": 0.1363651156425476,
|
| 3004 |
+
"learning_rate": 0.00014883401920438958,
|
| 3005 |
+
"loss": 0.9003480911254883,
|
| 3006 |
+
"step": 4280
|
| 3007 |
+
},
|
| 3008 |
+
{
|
| 3009 |
+
"epoch": 0.3310504485386322,
|
| 3010 |
+
"grad_norm": 0.15051127970218658,
|
| 3011 |
+
"learning_rate": 0.00014866255144032923,
|
| 3012 |
+
"loss": 0.8498348236083985,
|
| 3013 |
+
"step": 4290
|
| 3014 |
+
},
|
| 3015 |
+
{
|
| 3016 |
+
"epoch": 0.33182212790585514,
|
| 3017 |
+
"grad_norm": 0.12777823209762573,
|
| 3018 |
+
"learning_rate": 0.00014849108367626887,
|
| 3019 |
+
"loss": 0.6783880710601806,
|
| 3020 |
+
"step": 4300
|
| 3021 |
+
},
|
| 3022 |
+
{
|
| 3023 |
+
"epoch": 0.332593807273078,
|
| 3024 |
+
"grad_norm": 0.13575886189937592,
|
| 3025 |
+
"learning_rate": 0.0001483196159122085,
|
| 3026 |
+
"loss": 0.7898497581481934,
|
| 3027 |
+
"step": 4310
|
| 3028 |
+
},
|
| 3029 |
+
{
|
| 3030 |
+
"epoch": 0.33336548664030097,
|
| 3031 |
+
"grad_norm": 0.13227303326129913,
|
| 3032 |
+
"learning_rate": 0.00014814814814814815,
|
| 3033 |
+
"loss": 0.8330442428588867,
|
| 3034 |
+
"step": 4320
|
| 3035 |
+
},
|
| 3036 |
+
{
|
| 3037 |
+
"epoch": 0.33413716600752386,
|
| 3038 |
+
"grad_norm": 0.13202738761901855,
|
| 3039 |
+
"learning_rate": 0.0001479766803840878,
|
| 3040 |
+
"loss": 0.8135555267333985,
|
| 3041 |
+
"step": 4330
|
| 3042 |
+
},
|
| 3043 |
+
{
|
| 3044 |
+
"epoch": 0.3349088453747468,
|
| 3045 |
+
"grad_norm": 0.16807517409324646,
|
| 3046 |
+
"learning_rate": 0.00014780521262002745,
|
| 3047 |
+
"loss": 0.9015239715576172,
|
| 3048 |
+
"step": 4340
|
| 3049 |
+
},
|
| 3050 |
+
{
|
| 3051 |
+
"epoch": 0.3356805247419697,
|
| 3052 |
+
"grad_norm": 0.14190301299095154,
|
| 3053 |
+
"learning_rate": 0.0001476337448559671,
|
| 3054 |
+
"loss": 0.8392891883850098,
|
| 3055 |
+
"step": 4350
|
| 3056 |
+
},
|
| 3057 |
+
{
|
| 3058 |
+
"epoch": 0.33645220410919263,
|
| 3059 |
+
"grad_norm": 0.11172544956207275,
|
| 3060 |
+
"learning_rate": 0.00014746227709190672,
|
| 3061 |
+
"loss": 0.8557074546813965,
|
| 3062 |
+
"step": 4360
|
| 3063 |
+
},
|
| 3064 |
+
{
|
| 3065 |
+
"epoch": 0.3372238834764156,
|
| 3066 |
+
"grad_norm": 0.12184961885213852,
|
| 3067 |
+
"learning_rate": 0.00014729080932784637,
|
| 3068 |
+
"loss": 0.7816982269287109,
|
| 3069 |
+
"step": 4370
|
| 3070 |
+
},
|
| 3071 |
+
{
|
| 3072 |
+
"epoch": 0.33799556284363846,
|
| 3073 |
+
"grad_norm": 0.13183486461639404,
|
| 3074 |
+
"learning_rate": 0.00014711934156378602,
|
| 3075 |
+
"loss": 0.8120223045349121,
|
| 3076 |
+
"step": 4380
|
| 3077 |
+
},
|
| 3078 |
+
{
|
| 3079 |
+
"epoch": 0.3387672422108614,
|
| 3080 |
+
"grad_norm": 0.1273968368768692,
|
| 3081 |
+
"learning_rate": 0.00014694787379972566,
|
| 3082 |
+
"loss": 0.8377267837524414,
|
| 3083 |
+
"step": 4390
|
| 3084 |
+
},
|
| 3085 |
+
{
|
| 3086 |
+
"epoch": 0.3395389215780843,
|
| 3087 |
+
"grad_norm": 0.1453665792942047,
|
| 3088 |
+
"learning_rate": 0.0001467764060356653,
|
| 3089 |
+
"loss": 0.7802158832550049,
|
| 3090 |
+
"step": 4400
|
| 3091 |
+
},
|
| 3092 |
+
{
|
| 3093 |
+
"epoch": 0.34031060094530724,
|
| 3094 |
+
"grad_norm": 0.16375884413719177,
|
| 3095 |
+
"learning_rate": 0.00014660493827160496,
|
| 3096 |
+
"loss": 0.8365504264831543,
|
| 3097 |
+
"step": 4410
|
| 3098 |
+
},
|
| 3099 |
+
{
|
| 3100 |
+
"epoch": 0.34108228031253013,
|
| 3101 |
+
"grad_norm": 0.13078755140304565,
|
| 3102 |
+
"learning_rate": 0.00014643347050754459,
|
| 3103 |
+
"loss": 0.8306023597717285,
|
| 3104 |
+
"step": 4420
|
| 3105 |
+
},
|
| 3106 |
+
{
|
| 3107 |
+
"epoch": 0.34185395967975307,
|
| 3108 |
+
"grad_norm": 0.12786859273910522,
|
| 3109 |
+
"learning_rate": 0.00014626200274348424,
|
| 3110 |
+
"loss": 0.7702694416046143,
|
| 3111 |
+
"step": 4430
|
| 3112 |
+
},
|
| 3113 |
+
{
|
| 3114 |
+
"epoch": 0.34262563904697596,
|
| 3115 |
+
"grad_norm": 0.10945647209882736,
|
| 3116 |
+
"learning_rate": 0.00014609053497942386,
|
| 3117 |
+
"loss": 0.7941019535064697,
|
| 3118 |
+
"step": 4440
|
| 3119 |
+
},
|
| 3120 |
+
{
|
| 3121 |
+
"epoch": 0.3433973184141989,
|
| 3122 |
+
"grad_norm": 0.11679490655660629,
|
| 3123 |
+
"learning_rate": 0.00014591906721536353,
|
| 3124 |
+
"loss": 0.832430076599121,
|
| 3125 |
+
"step": 4450
|
| 3126 |
+
},
|
| 3127 |
+
{
|
| 3128 |
+
"epoch": 0.3441689977814218,
|
| 3129 |
+
"grad_norm": 0.10478997975587845,
|
| 3130 |
+
"learning_rate": 0.00014574759945130316,
|
| 3131 |
+
"loss": 0.8652594566345215,
|
| 3132 |
+
"step": 4460
|
| 3133 |
+
},
|
| 3134 |
+
{
|
| 3135 |
+
"epoch": 0.34494067714864474,
|
| 3136 |
+
"grad_norm": 0.15972398221492767,
|
| 3137 |
+
"learning_rate": 0.0001455761316872428,
|
| 3138 |
+
"loss": 0.8060592651367188,
|
| 3139 |
+
"step": 4470
|
| 3140 |
+
},
|
| 3141 |
+
{
|
| 3142 |
+
"epoch": 0.3457123565158677,
|
| 3143 |
+
"grad_norm": 0.11833195388317108,
|
| 3144 |
+
"learning_rate": 0.00014540466392318243,
|
| 3145 |
+
"loss": 0.8139182090759277,
|
| 3146 |
+
"step": 4480
|
| 3147 |
+
},
|
| 3148 |
+
{
|
| 3149 |
+
"epoch": 0.34648403588309057,
|
| 3150 |
+
"grad_norm": 0.13358113169670105,
|
| 3151 |
+
"learning_rate": 0.0001452331961591221,
|
| 3152 |
+
"loss": 0.8154877662658692,
|
| 3153 |
+
"step": 4490
|
| 3154 |
+
},
|
| 3155 |
+
{
|
| 3156 |
+
"epoch": 0.3472557152503135,
|
| 3157 |
+
"grad_norm": 0.14406244456768036,
|
| 3158 |
+
"learning_rate": 0.00014506172839506173,
|
| 3159 |
+
"loss": 0.828406810760498,
|
| 3160 |
+
"step": 4500
|
| 3161 |
+
},
|
| 3162 |
+
{
|
| 3163 |
+
"epoch": 0.3480273946175364,
|
| 3164 |
+
"grad_norm": 0.14771930873394012,
|
| 3165 |
+
"learning_rate": 0.00014489026063100138,
|
| 3166 |
+
"loss": 0.800572681427002,
|
| 3167 |
+
"step": 4510
|
| 3168 |
+
},
|
| 3169 |
+
{
|
| 3170 |
+
"epoch": 0.34879907398475934,
|
| 3171 |
+
"grad_norm": 0.10739558935165405,
|
| 3172 |
+
"learning_rate": 0.00014471879286694103,
|
| 3173 |
+
"loss": 0.791358232498169,
|
| 3174 |
+
"step": 4520
|
| 3175 |
+
},
|
| 3176 |
+
{
|
| 3177 |
+
"epoch": 0.34957075335198223,
|
| 3178 |
+
"grad_norm": 0.12839984893798828,
|
| 3179 |
+
"learning_rate": 0.00014454732510288068,
|
| 3180 |
+
"loss": 0.819278335571289,
|
| 3181 |
+
"step": 4530
|
| 3182 |
+
},
|
| 3183 |
+
{
|
| 3184 |
+
"epoch": 0.3503424327192052,
|
| 3185 |
+
"grad_norm": 0.12612596154212952,
|
| 3186 |
+
"learning_rate": 0.0001443758573388203,
|
| 3187 |
+
"loss": 0.8036989212036133,
|
| 3188 |
+
"step": 4540
|
| 3189 |
+
},
|
| 3190 |
+
{
|
| 3191 |
+
"epoch": 0.35111411208642807,
|
| 3192 |
+
"grad_norm": 0.15920689702033997,
|
| 3193 |
+
"learning_rate": 0.00014420438957475995,
|
| 3194 |
+
"loss": 0.8325424194335938,
|
| 3195 |
+
"step": 4550
|
| 3196 |
+
},
|
| 3197 |
+
{
|
| 3198 |
+
"epoch": 0.351885791453651,
|
| 3199 |
+
"grad_norm": 0.12964633107185364,
|
| 3200 |
+
"learning_rate": 0.0001440329218106996,
|
| 3201 |
+
"loss": 0.8799901962280273,
|
| 3202 |
+
"step": 4560
|
| 3203 |
+
},
|
| 3204 |
+
{
|
| 3205 |
+
"epoch": 0.35265747082087395,
|
| 3206 |
+
"grad_norm": 0.14742450416088104,
|
| 3207 |
+
"learning_rate": 0.00014386145404663925,
|
| 3208 |
+
"loss": 0.871920394897461,
|
| 3209 |
+
"step": 4570
|
| 3210 |
+
},
|
| 3211 |
+
{
|
| 3212 |
+
"epoch": 0.35342915018809684,
|
| 3213 |
+
"grad_norm": 0.13931940495967865,
|
| 3214 |
+
"learning_rate": 0.00014368998628257887,
|
| 3215 |
+
"loss": 0.7537837505340577,
|
| 3216 |
+
"step": 4580
|
| 3217 |
+
},
|
| 3218 |
+
{
|
| 3219 |
+
"epoch": 0.3542008295553198,
|
| 3220 |
+
"grad_norm": 0.140437513589859,
|
| 3221 |
+
"learning_rate": 0.00014351851851851852,
|
| 3222 |
+
"loss": 0.7717479228973388,
|
| 3223 |
+
"step": 4590
|
| 3224 |
+
},
|
| 3225 |
+
{
|
| 3226 |
+
"epoch": 0.3549725089225427,
|
| 3227 |
+
"grad_norm": 0.13492359220981598,
|
| 3228 |
+
"learning_rate": 0.00014334705075445817,
|
| 3229 |
+
"loss": 0.8396642684936524,
|
| 3230 |
+
"step": 4600
|
| 3231 |
+
},
|
| 3232 |
+
{
|
| 3233 |
+
"epoch": 0.3557441882897656,
|
| 3234 |
+
"grad_norm": 0.12470181286334991,
|
| 3235 |
+
"learning_rate": 0.00014317558299039782,
|
| 3236 |
+
"loss": 0.8109576225280761,
|
| 3237 |
+
"step": 4610
|
| 3238 |
+
}
|
| 3239 |
+
],
|
| 3240 |
+
"logging_steps": 10,
|
| 3241 |
+
"max_steps": 12959,
|
| 3242 |
+
"num_input_tokens_seen": 0,
|
| 3243 |
+
"num_train_epochs": 1,
|
| 3244 |
+
"save_steps": 300,
|
| 3245 |
+
"stateful_callbacks": {
|
| 3246 |
+
"TrainerControl": {
|
| 3247 |
+
"args": {
|
| 3248 |
+
"should_epoch_stop": false,
|
| 3249 |
+
"should_evaluate": false,
|
| 3250 |
+
"should_log": false,
|
| 3251 |
+
"should_save": true,
|
| 3252 |
+
"should_training_stop": true
|
| 3253 |
+
},
|
| 3254 |
+
"attributes": {}
|
| 3255 |
+
}
|
| 3256 |
+
},
|
| 3257 |
+
"total_flos": 4.148469158718259e+17,
|
| 3258 |
+
"train_batch_size": 1,
|
| 3259 |
+
"trial_name": null,
|
| 3260 |
+
"trial_params": null
|
| 3261 |
+
}
|
checkpoint-4610/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:910df878d9c3e0e70d1e104a26707dab2636b00fa7d935aafd85be8429d2ab76
|
| 3 |
+
size 5201
|