Upload checkpoint-3000
Browse files- MS_Marco_ep10/checkpoint-3000/README.md +206 -0
- MS_Marco_ep10/checkpoint-3000/adapter_config.json +41 -0
- MS_Marco_ep10/checkpoint-3000/adapter_model.safetensors +3 -0
- MS_Marco_ep10/checkpoint-3000/optimizer.pt +3 -0
- MS_Marco_ep10/checkpoint-3000/rng_state_0.pth +3 -0
- MS_Marco_ep10/checkpoint-3000/rng_state_1.pth +3 -0
- MS_Marco_ep10/checkpoint-3000/scheduler.pt +3 -0
- MS_Marco_ep10/checkpoint-3000/trainer_state.json +2134 -0
- MS_Marco_ep10/checkpoint-3000/training_args.bin +3 -0
MS_Marco_ep10/checkpoint-3000/README.md
ADDED
|
@@ -0,0 +1,206 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: Qwen/Qwen3-Embedding-4B
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- base_model:adapter:Qwen/Qwen3-Embedding-4B
|
| 6 |
+
- lora
|
| 7 |
+
- transformers
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
# Model Card for Model ID
|
| 11 |
+
|
| 12 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 13 |
+
|
| 14 |
+
|
| 15 |
+
|
| 16 |
+
## Model Details
|
| 17 |
+
|
| 18 |
+
### Model Description
|
| 19 |
+
|
| 20 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 21 |
+
|
| 22 |
+
|
| 23 |
+
|
| 24 |
+
- **Developed by:** [More Information Needed]
|
| 25 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 26 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 27 |
+
- **Model type:** [More Information Needed]
|
| 28 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 29 |
+
- **License:** [More Information Needed]
|
| 30 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 31 |
+
|
| 32 |
+
### Model Sources [optional]
|
| 33 |
+
|
| 34 |
+
<!-- Provide the basic links for the model. -->
|
| 35 |
+
|
| 36 |
+
- **Repository:** [More Information Needed]
|
| 37 |
+
- **Paper [optional]:** [More Information Needed]
|
| 38 |
+
- **Demo [optional]:** [More Information Needed]
|
| 39 |
+
|
| 40 |
+
## Uses
|
| 41 |
+
|
| 42 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 43 |
+
|
| 44 |
+
### Direct Use
|
| 45 |
+
|
| 46 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 47 |
+
|
| 48 |
+
[More Information Needed]
|
| 49 |
+
|
| 50 |
+
### Downstream Use [optional]
|
| 51 |
+
|
| 52 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 53 |
+
|
| 54 |
+
[More Information Needed]
|
| 55 |
+
|
| 56 |
+
### Out-of-Scope Use
|
| 57 |
+
|
| 58 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 59 |
+
|
| 60 |
+
[More Information Needed]
|
| 61 |
+
|
| 62 |
+
## Bias, Risks, and Limitations
|
| 63 |
+
|
| 64 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 65 |
+
|
| 66 |
+
[More Information Needed]
|
| 67 |
+
|
| 68 |
+
### Recommendations
|
| 69 |
+
|
| 70 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 71 |
+
|
| 72 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 73 |
+
|
| 74 |
+
## How to Get Started with the Model
|
| 75 |
+
|
| 76 |
+
Use the code below to get started with the model.
|
| 77 |
+
|
| 78 |
+
[More Information Needed]
|
| 79 |
+
|
| 80 |
+
## Training Details
|
| 81 |
+
|
| 82 |
+
### Training Data
|
| 83 |
+
|
| 84 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 85 |
+
|
| 86 |
+
[More Information Needed]
|
| 87 |
+
|
| 88 |
+
### Training Procedure
|
| 89 |
+
|
| 90 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 91 |
+
|
| 92 |
+
#### Preprocessing [optional]
|
| 93 |
+
|
| 94 |
+
[More Information Needed]
|
| 95 |
+
|
| 96 |
+
|
| 97 |
+
#### Training Hyperparameters
|
| 98 |
+
|
| 99 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 100 |
+
|
| 101 |
+
#### Speeds, Sizes, Times [optional]
|
| 102 |
+
|
| 103 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 104 |
+
|
| 105 |
+
[More Information Needed]
|
| 106 |
+
|
| 107 |
+
## Evaluation
|
| 108 |
+
|
| 109 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 110 |
+
|
| 111 |
+
### Testing Data, Factors & Metrics
|
| 112 |
+
|
| 113 |
+
#### Testing Data
|
| 114 |
+
|
| 115 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 116 |
+
|
| 117 |
+
[More Information Needed]
|
| 118 |
+
|
| 119 |
+
#### Factors
|
| 120 |
+
|
| 121 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 122 |
+
|
| 123 |
+
[More Information Needed]
|
| 124 |
+
|
| 125 |
+
#### Metrics
|
| 126 |
+
|
| 127 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
### Results
|
| 132 |
+
|
| 133 |
+
[More Information Needed]
|
| 134 |
+
|
| 135 |
+
#### Summary
|
| 136 |
+
|
| 137 |
+
|
| 138 |
+
|
| 139 |
+
## Model Examination [optional]
|
| 140 |
+
|
| 141 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 142 |
+
|
| 143 |
+
[More Information Needed]
|
| 144 |
+
|
| 145 |
+
## Environmental Impact
|
| 146 |
+
|
| 147 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 148 |
+
|
| 149 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 150 |
+
|
| 151 |
+
- **Hardware Type:** [More Information Needed]
|
| 152 |
+
- **Hours used:** [More Information Needed]
|
| 153 |
+
- **Cloud Provider:** [More Information Needed]
|
| 154 |
+
- **Compute Region:** [More Information Needed]
|
| 155 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 156 |
+
|
| 157 |
+
## Technical Specifications [optional]
|
| 158 |
+
|
| 159 |
+
### Model Architecture and Objective
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
### Compute Infrastructure
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Hardware
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
#### Software
|
| 172 |
+
|
| 173 |
+
[More Information Needed]
|
| 174 |
+
|
| 175 |
+
## Citation [optional]
|
| 176 |
+
|
| 177 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 178 |
+
|
| 179 |
+
**BibTeX:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
**APA:**
|
| 184 |
+
|
| 185 |
+
[More Information Needed]
|
| 186 |
+
|
| 187 |
+
## Glossary [optional]
|
| 188 |
+
|
| 189 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## More Information [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Authors [optional]
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
|
| 201 |
+
## Model Card Contact
|
| 202 |
+
|
| 203 |
+
[More Information Needed]
|
| 204 |
+
### Framework versions
|
| 205 |
+
|
| 206 |
+
- PEFT 0.16.0
|
MS_Marco_ep10/checkpoint-3000/adapter_config.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "Qwen/Qwen3-Embedding-4B",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": true,
|
| 11 |
+
"init_lora_weights": "gaussian",
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 32,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.1,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"qalora_group_size": 16,
|
| 24 |
+
"r": 32,
|
| 25 |
+
"rank_pattern": {},
|
| 26 |
+
"revision": null,
|
| 27 |
+
"target_modules": [
|
| 28 |
+
"q_proj",
|
| 29 |
+
"down_proj",
|
| 30 |
+
"o_proj",
|
| 31 |
+
"gate_proj",
|
| 32 |
+
"up_proj",
|
| 33 |
+
"k_proj",
|
| 34 |
+
"v_proj"
|
| 35 |
+
],
|
| 36 |
+
"task_type": "FEATURE_EXTRACTION",
|
| 37 |
+
"trainable_token_indices": null,
|
| 38 |
+
"use_dora": false,
|
| 39 |
+
"use_qalora": false,
|
| 40 |
+
"use_rslora": false
|
| 41 |
+
}
|
MS_Marco_ep10/checkpoint-3000/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:da90eb7c5143a830fdb66efdd457962bbf797e6a459c93b0ed238c79d4dbeda1
|
| 3 |
+
size 264305872
|
MS_Marco_ep10/checkpoint-3000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9a50d671c73415ee7da1b898bc6033f60c2e940a046efd0917e25ef3221ec152
|
| 3 |
+
size 530221329
|
MS_Marco_ep10/checkpoint-3000/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ba9d053f96d4b1f7984679605375e9c703483287f34cdf01eb482f1935a342a5
|
| 3 |
+
size 14917
|
MS_Marco_ep10/checkpoint-3000/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:78761c6e4cc40084f18a92598e746d6263647d6fe439717e202c5cb11eb81603
|
| 3 |
+
size 14917
|
MS_Marco_ep10/checkpoint-3000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1d4e07d71dc466f87d5a0aa8f8b93f1fa229a492f8eee4c431b3e4f9b4f638e6
|
| 3 |
+
size 1465
|
MS_Marco_ep10/checkpoint-3000/trainer_state.json
ADDED
|
@@ -0,0 +1,2134 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.3817279552105866,
|
| 6 |
+
"eval_steps": 1000000,
|
| 7 |
+
"global_step": 3000,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.001272426517368622,
|
| 14 |
+
"grad_norm": 3.5877323150634766,
|
| 15 |
+
"learning_rate": 5.725919328158799e-08,
|
| 16 |
+
"loss": 0.1624,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.002544853034737244,
|
| 21 |
+
"grad_norm": 2.085402488708496,
|
| 22 |
+
"learning_rate": 1.2088051915001908e-07,
|
| 23 |
+
"loss": 0.1406,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.003817279552105866,
|
| 28 |
+
"grad_norm": 2.65560245513916,
|
| 29 |
+
"learning_rate": 1.845018450184502e-07,
|
| 30 |
+
"loss": 0.1539,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.005089706069474488,
|
| 35 |
+
"grad_norm": 4.92278528213501,
|
| 36 |
+
"learning_rate": 2.4812317088688133e-07,
|
| 37 |
+
"loss": 0.1836,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.00636213258684311,
|
| 42 |
+
"grad_norm": 3.515843152999878,
|
| 43 |
+
"learning_rate": 3.117444967553124e-07,
|
| 44 |
+
"loss": 0.1567,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.007634559104211732,
|
| 49 |
+
"grad_norm": 2.803701877593994,
|
| 50 |
+
"learning_rate": 3.7536582262374346e-07,
|
| 51 |
+
"loss": 0.1596,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.008906985621580354,
|
| 56 |
+
"grad_norm": 2.529664993286133,
|
| 57 |
+
"learning_rate": 4.389871484921746e-07,
|
| 58 |
+
"loss": 0.1436,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.010179412138948976,
|
| 63 |
+
"grad_norm": 4.315010070800781,
|
| 64 |
+
"learning_rate": 5.026084743606057e-07,
|
| 65 |
+
"loss": 0.175,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.011451838656317598,
|
| 70 |
+
"grad_norm": 3.158771276473999,
|
| 71 |
+
"learning_rate": 5.662298002290368e-07,
|
| 72 |
+
"loss": 0.1337,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.01272426517368622,
|
| 77 |
+
"grad_norm": 1.9685556888580322,
|
| 78 |
+
"learning_rate": 6.298511260974679e-07,
|
| 79 |
+
"loss": 0.1563,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.013996691691054842,
|
| 84 |
+
"grad_norm": 1.7232635021209717,
|
| 85 |
+
"learning_rate": 6.93472451965899e-07,
|
| 86 |
+
"loss": 0.1262,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.015269118208423464,
|
| 91 |
+
"grad_norm": 3.527454137802124,
|
| 92 |
+
"learning_rate": 7.570937778343301e-07,
|
| 93 |
+
"loss": 0.1413,
|
| 94 |
+
"step": 120
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.016541544725792084,
|
| 98 |
+
"grad_norm": 3.0089797973632812,
|
| 99 |
+
"learning_rate": 8.207151037027612e-07,
|
| 100 |
+
"loss": 0.1524,
|
| 101 |
+
"step": 130
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.017813971243160708,
|
| 105 |
+
"grad_norm": 1.7723190784454346,
|
| 106 |
+
"learning_rate": 8.843364295711924e-07,
|
| 107 |
+
"loss": 0.1307,
|
| 108 |
+
"step": 140
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.01908639776052933,
|
| 112 |
+
"grad_norm": 1.957555890083313,
|
| 113 |
+
"learning_rate": 9.479577554396234e-07,
|
| 114 |
+
"loss": 0.123,
|
| 115 |
+
"step": 150
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.020358824277897952,
|
| 119 |
+
"grad_norm": 1.7378482818603516,
|
| 120 |
+
"learning_rate": 1.0115790813080545e-06,
|
| 121 |
+
"loss": 0.1708,
|
| 122 |
+
"step": 160
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.021631250795266573,
|
| 126 |
+
"grad_norm": 1.664908766746521,
|
| 127 |
+
"learning_rate": 1.0752004071764857e-06,
|
| 128 |
+
"loss": 0.1132,
|
| 129 |
+
"step": 170
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.022903677312635196,
|
| 133 |
+
"grad_norm": 2.3183891773223877,
|
| 134 |
+
"learning_rate": 1.1388217330449168e-06,
|
| 135 |
+
"loss": 0.1107,
|
| 136 |
+
"step": 180
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.024176103830003817,
|
| 140 |
+
"grad_norm": 2.1844465732574463,
|
| 141 |
+
"learning_rate": 1.2024430589133478e-06,
|
| 142 |
+
"loss": 0.0953,
|
| 143 |
+
"step": 190
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.02544853034737244,
|
| 147 |
+
"grad_norm": 4.4184417724609375,
|
| 148 |
+
"learning_rate": 1.266064384781779e-06,
|
| 149 |
+
"loss": 0.0922,
|
| 150 |
+
"step": 200
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.02672095686474106,
|
| 154 |
+
"grad_norm": 2.0239903926849365,
|
| 155 |
+
"learning_rate": 1.32968571065021e-06,
|
| 156 |
+
"loss": 0.0699,
|
| 157 |
+
"step": 210
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.027993383382109684,
|
| 161 |
+
"grad_norm": 1.2873213291168213,
|
| 162 |
+
"learning_rate": 1.3933070365186412e-06,
|
| 163 |
+
"loss": 0.0717,
|
| 164 |
+
"step": 220
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.029265809899478305,
|
| 168 |
+
"grad_norm": 1.9870949983596802,
|
| 169 |
+
"learning_rate": 1.4569283623870722e-06,
|
| 170 |
+
"loss": 0.055,
|
| 171 |
+
"step": 230
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.03053823641684693,
|
| 175 |
+
"grad_norm": 0.75453120470047,
|
| 176 |
+
"learning_rate": 1.5205496882555034e-06,
|
| 177 |
+
"loss": 0.0558,
|
| 178 |
+
"step": 240
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.03181066293421555,
|
| 182 |
+
"grad_norm": 2.1326417922973633,
|
| 183 |
+
"learning_rate": 1.5841710141239346e-06,
|
| 184 |
+
"loss": 0.0428,
|
| 185 |
+
"step": 250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.03308308945158417,
|
| 189 |
+
"grad_norm": 0.530195951461792,
|
| 190 |
+
"learning_rate": 1.6477923399923656e-06,
|
| 191 |
+
"loss": 0.0344,
|
| 192 |
+
"step": 260
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.034355515968952796,
|
| 196 |
+
"grad_norm": 0.25554534792900085,
|
| 197 |
+
"learning_rate": 1.7114136658607965e-06,
|
| 198 |
+
"loss": 0.0342,
|
| 199 |
+
"step": 270
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.035627942486321416,
|
| 203 |
+
"grad_norm": 2.5654115676879883,
|
| 204 |
+
"learning_rate": 1.7750349917292275e-06,
|
| 205 |
+
"loss": 0.0464,
|
| 206 |
+
"step": 280
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.03690036900369004,
|
| 210 |
+
"grad_norm": 0.8986497521400452,
|
| 211 |
+
"learning_rate": 1.838656317597659e-06,
|
| 212 |
+
"loss": 0.0359,
|
| 213 |
+
"step": 290
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.03817279552105866,
|
| 217 |
+
"grad_norm": 0.4290733337402344,
|
| 218 |
+
"learning_rate": 1.90227764346609e-06,
|
| 219 |
+
"loss": 0.0269,
|
| 220 |
+
"step": 300
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.039445222038427284,
|
| 224 |
+
"grad_norm": 1.9061795473098755,
|
| 225 |
+
"learning_rate": 1.965898969334521e-06,
|
| 226 |
+
"loss": 0.0336,
|
| 227 |
+
"step": 310
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.040717648555795904,
|
| 231 |
+
"grad_norm": 2.097940444946289,
|
| 232 |
+
"learning_rate": 2.029520295202952e-06,
|
| 233 |
+
"loss": 0.0527,
|
| 234 |
+
"step": 320
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.041990075073164525,
|
| 238 |
+
"grad_norm": 2.3401193618774414,
|
| 239 |
+
"learning_rate": 2.093141621071383e-06,
|
| 240 |
+
"loss": 0.0254,
|
| 241 |
+
"step": 330
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.043262501590533145,
|
| 245 |
+
"grad_norm": 0.4466155171394348,
|
| 246 |
+
"learning_rate": 2.1567629469398143e-06,
|
| 247 |
+
"loss": 0.0365,
|
| 248 |
+
"step": 340
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.044534928107901765,
|
| 252 |
+
"grad_norm": 1.4632848501205444,
|
| 253 |
+
"learning_rate": 2.2203842728082453e-06,
|
| 254 |
+
"loss": 0.037,
|
| 255 |
+
"step": 350
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.04580735462527039,
|
| 259 |
+
"grad_norm": 1.3355021476745605,
|
| 260 |
+
"learning_rate": 2.2840055986766767e-06,
|
| 261 |
+
"loss": 0.0409,
|
| 262 |
+
"step": 360
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.04707978114263901,
|
| 266 |
+
"grad_norm": 2.0859885215759277,
|
| 267 |
+
"learning_rate": 2.3476269245451077e-06,
|
| 268 |
+
"loss": 0.0305,
|
| 269 |
+
"step": 370
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.04835220766000763,
|
| 273 |
+
"grad_norm": 1.3638544082641602,
|
| 274 |
+
"learning_rate": 2.4112482504135386e-06,
|
| 275 |
+
"loss": 0.0331,
|
| 276 |
+
"step": 380
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.04962463417737625,
|
| 280 |
+
"grad_norm": 0.41071686148643494,
|
| 281 |
+
"learning_rate": 2.47486957628197e-06,
|
| 282 |
+
"loss": 0.03,
|
| 283 |
+
"step": 390
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.05089706069474488,
|
| 287 |
+
"grad_norm": 0.8771544098854065,
|
| 288 |
+
"learning_rate": 2.538490902150401e-06,
|
| 289 |
+
"loss": 0.0306,
|
| 290 |
+
"step": 400
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.0521694872121135,
|
| 294 |
+
"grad_norm": 0.6460317373275757,
|
| 295 |
+
"learning_rate": 2.602112228018832e-06,
|
| 296 |
+
"loss": 0.0311,
|
| 297 |
+
"step": 410
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.05344191372948212,
|
| 301 |
+
"grad_norm": 0.19301742315292358,
|
| 302 |
+
"learning_rate": 2.6657335538872634e-06,
|
| 303 |
+
"loss": 0.0138,
|
| 304 |
+
"step": 420
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.05471434024685074,
|
| 308 |
+
"grad_norm": 2.0089757442474365,
|
| 309 |
+
"learning_rate": 2.7293548797556944e-06,
|
| 310 |
+
"loss": 0.0255,
|
| 311 |
+
"step": 430
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.05598676676421937,
|
| 315 |
+
"grad_norm": 0.8393608927726746,
|
| 316 |
+
"learning_rate": 2.7929762056241254e-06,
|
| 317 |
+
"loss": 0.0206,
|
| 318 |
+
"step": 440
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.05725919328158799,
|
| 322 |
+
"grad_norm": 0.8323113322257996,
|
| 323 |
+
"learning_rate": 2.8565975314925564e-06,
|
| 324 |
+
"loss": 0.0148,
|
| 325 |
+
"step": 450
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.05853161979895661,
|
| 329 |
+
"grad_norm": 1.5697057247161865,
|
| 330 |
+
"learning_rate": 2.9202188573609878e-06,
|
| 331 |
+
"loss": 0.0258,
|
| 332 |
+
"step": 460
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.05980404631632523,
|
| 336 |
+
"grad_norm": 0.22127273678779602,
|
| 337 |
+
"learning_rate": 2.9838401832294188e-06,
|
| 338 |
+
"loss": 0.0195,
|
| 339 |
+
"step": 470
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.06107647283369386,
|
| 343 |
+
"grad_norm": 1.421794056892395,
|
| 344 |
+
"learning_rate": 3.0474615090978497e-06,
|
| 345 |
+
"loss": 0.0202,
|
| 346 |
+
"step": 480
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.06234889935106248,
|
| 350 |
+
"grad_norm": 2.1492910385131836,
|
| 351 |
+
"learning_rate": 3.1110828349662807e-06,
|
| 352 |
+
"loss": 0.0244,
|
| 353 |
+
"step": 490
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.0636213258684311,
|
| 357 |
+
"grad_norm": 0.09726544469594955,
|
| 358 |
+
"learning_rate": 3.174704160834712e-06,
|
| 359 |
+
"loss": 0.0257,
|
| 360 |
+
"step": 500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.06489375238579972,
|
| 364 |
+
"grad_norm": 0.5567276477813721,
|
| 365 |
+
"learning_rate": 3.2383254867031427e-06,
|
| 366 |
+
"loss": 0.0103,
|
| 367 |
+
"step": 510
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.06616617890316834,
|
| 371 |
+
"grad_norm": 0.857915997505188,
|
| 372 |
+
"learning_rate": 3.301946812571574e-06,
|
| 373 |
+
"loss": 0.0198,
|
| 374 |
+
"step": 520
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.06743860542053697,
|
| 378 |
+
"grad_norm": 2.1099727153778076,
|
| 379 |
+
"learning_rate": 3.3655681384400055e-06,
|
| 380 |
+
"loss": 0.0169,
|
| 381 |
+
"step": 530
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.06871103193790559,
|
| 385 |
+
"grad_norm": 0.35235458612442017,
|
| 386 |
+
"learning_rate": 3.429189464308436e-06,
|
| 387 |
+
"loss": 0.0169,
|
| 388 |
+
"step": 540
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.0699834584552742,
|
| 392 |
+
"grad_norm": 0.27329525351524353,
|
| 393 |
+
"learning_rate": 3.4928107901768675e-06,
|
| 394 |
+
"loss": 0.025,
|
| 395 |
+
"step": 550
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.07125588497264283,
|
| 399 |
+
"grad_norm": 1.0509276390075684,
|
| 400 |
+
"learning_rate": 3.556432116045299e-06,
|
| 401 |
+
"loss": 0.0143,
|
| 402 |
+
"step": 560
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.07252831149001145,
|
| 406 |
+
"grad_norm": 2.021751880645752,
|
| 407 |
+
"learning_rate": 3.6200534419137294e-06,
|
| 408 |
+
"loss": 0.0248,
|
| 409 |
+
"step": 570
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.07380073800738007,
|
| 413 |
+
"grad_norm": 0.9538995027542114,
|
| 414 |
+
"learning_rate": 3.683674767782161e-06,
|
| 415 |
+
"loss": 0.0234,
|
| 416 |
+
"step": 580
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.0750731645247487,
|
| 420 |
+
"grad_norm": 1.5769826173782349,
|
| 421 |
+
"learning_rate": 3.7472960936505914e-06,
|
| 422 |
+
"loss": 0.0173,
|
| 423 |
+
"step": 590
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.07634559104211731,
|
| 427 |
+
"grad_norm": 1.1721569299697876,
|
| 428 |
+
"learning_rate": 3.810917419519023e-06,
|
| 429 |
+
"loss": 0.0283,
|
| 430 |
+
"step": 600
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.07761801755948594,
|
| 434 |
+
"grad_norm": 0.1278325915336609,
|
| 435 |
+
"learning_rate": 3.874538745387454e-06,
|
| 436 |
+
"loss": 0.01,
|
| 437 |
+
"step": 610
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.07889044407685457,
|
| 441 |
+
"grad_norm": 1.5084667205810547,
|
| 442 |
+
"learning_rate": 3.938160071255885e-06,
|
| 443 |
+
"loss": 0.0152,
|
| 444 |
+
"step": 620
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.08016287059422318,
|
| 448 |
+
"grad_norm": 0.1045418232679367,
|
| 449 |
+
"learning_rate": 4.001781397124316e-06,
|
| 450 |
+
"loss": 0.0196,
|
| 451 |
+
"step": 630
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.08143529711159181,
|
| 455 |
+
"grad_norm": 0.1617429554462433,
|
| 456 |
+
"learning_rate": 4.065402722992747e-06,
|
| 457 |
+
"loss": 0.0215,
|
| 458 |
+
"step": 640
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.08270772362896042,
|
| 462 |
+
"grad_norm": 0.11483286321163177,
|
| 463 |
+
"learning_rate": 4.129024048861178e-06,
|
| 464 |
+
"loss": 0.0206,
|
| 465 |
+
"step": 650
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.08398015014632905,
|
| 469 |
+
"grad_norm": 0.3859212100505829,
|
| 470 |
+
"learning_rate": 4.1926453747296096e-06,
|
| 471 |
+
"loss": 0.0067,
|
| 472 |
+
"step": 660
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.08525257666369768,
|
| 476 |
+
"grad_norm": 0.23510600626468658,
|
| 477 |
+
"learning_rate": 4.25626670059804e-06,
|
| 478 |
+
"loss": 0.0213,
|
| 479 |
+
"step": 670
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.08652500318106629,
|
| 483 |
+
"grad_norm": 1.86430823802948,
|
| 484 |
+
"learning_rate": 4.3198880264664715e-06,
|
| 485 |
+
"loss": 0.0217,
|
| 486 |
+
"step": 680
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.08779742969843492,
|
| 490 |
+
"grad_norm": 1.0131075382232666,
|
| 491 |
+
"learning_rate": 4.383509352334903e-06,
|
| 492 |
+
"loss": 0.0143,
|
| 493 |
+
"step": 690
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.08906985621580353,
|
| 497 |
+
"grad_norm": 0.29921114444732666,
|
| 498 |
+
"learning_rate": 4.4471306782033335e-06,
|
| 499 |
+
"loss": 0.0169,
|
| 500 |
+
"step": 700
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.09034228273317216,
|
| 504 |
+
"grad_norm": 0.39632511138916016,
|
| 505 |
+
"learning_rate": 4.510752004071765e-06,
|
| 506 |
+
"loss": 0.0091,
|
| 507 |
+
"step": 710
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.09161470925054079,
|
| 511 |
+
"grad_norm": 0.1986786276102066,
|
| 512 |
+
"learning_rate": 4.5743733299401955e-06,
|
| 513 |
+
"loss": 0.0077,
|
| 514 |
+
"step": 720
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.0928871357679094,
|
| 518 |
+
"grad_norm": 1.939620852470398,
|
| 519 |
+
"learning_rate": 4.637994655808627e-06,
|
| 520 |
+
"loss": 0.0182,
|
| 521 |
+
"step": 730
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.09415956228527803,
|
| 525 |
+
"grad_norm": 2.1149661540985107,
|
| 526 |
+
"learning_rate": 4.701615981677058e-06,
|
| 527 |
+
"loss": 0.0235,
|
| 528 |
+
"step": 740
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.09543198880264665,
|
| 532 |
+
"grad_norm": 0.03329145163297653,
|
| 533 |
+
"learning_rate": 4.765237307545489e-06,
|
| 534 |
+
"loss": 0.0172,
|
| 535 |
+
"step": 750
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.09670441532001527,
|
| 539 |
+
"grad_norm": 1.470470905303955,
|
| 540 |
+
"learning_rate": 4.82885863341392e-06,
|
| 541 |
+
"loss": 0.0178,
|
| 542 |
+
"step": 760
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.0979768418373839,
|
| 546 |
+
"grad_norm": 1.055908441543579,
|
| 547 |
+
"learning_rate": 4.892479959282352e-06,
|
| 548 |
+
"loss": 0.0133,
|
| 549 |
+
"step": 770
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.0992492683547525,
|
| 553 |
+
"grad_norm": 2.2330827713012695,
|
| 554 |
+
"learning_rate": 4.956101285150783e-06,
|
| 555 |
+
"loss": 0.0102,
|
| 556 |
+
"step": 780
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.10052169487212113,
|
| 560 |
+
"grad_norm": 0.20729655027389526,
|
| 561 |
+
"learning_rate": 5.019722611019214e-06,
|
| 562 |
+
"loss": 0.0081,
|
| 563 |
+
"step": 790
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.10179412138948976,
|
| 567 |
+
"grad_norm": 0.1920371800661087,
|
| 568 |
+
"learning_rate": 5.083343936887645e-06,
|
| 569 |
+
"loss": 0.0081,
|
| 570 |
+
"step": 800
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.10306654790685837,
|
| 574 |
+
"grad_norm": 0.5931546092033386,
|
| 575 |
+
"learning_rate": 5.1469652627560764e-06,
|
| 576 |
+
"loss": 0.0313,
|
| 577 |
+
"step": 810
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.104338974424227,
|
| 581 |
+
"grad_norm": 1.6505730152130127,
|
| 582 |
+
"learning_rate": 5.210586588624507e-06,
|
| 583 |
+
"loss": 0.01,
|
| 584 |
+
"step": 820
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.10561140094159563,
|
| 588 |
+
"grad_norm": 1.3409397602081299,
|
| 589 |
+
"learning_rate": 5.274207914492938e-06,
|
| 590 |
+
"loss": 0.0182,
|
| 591 |
+
"step": 830
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.10688382745896424,
|
| 595 |
+
"grad_norm": 0.2508680820465088,
|
| 596 |
+
"learning_rate": 5.33782924036137e-06,
|
| 597 |
+
"loss": 0.0108,
|
| 598 |
+
"step": 840
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.10815625397633287,
|
| 602 |
+
"grad_norm": 0.7329053282737732,
|
| 603 |
+
"learning_rate": 5.401450566229801e-06,
|
| 604 |
+
"loss": 0.0168,
|
| 605 |
+
"step": 850
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.10942868049370148,
|
| 609 |
+
"grad_norm": 0.12235169112682343,
|
| 610 |
+
"learning_rate": 5.465071892098232e-06,
|
| 611 |
+
"loss": 0.0149,
|
| 612 |
+
"step": 860
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.11070110701107011,
|
| 616 |
+
"grad_norm": 0.058564718812704086,
|
| 617 |
+
"learning_rate": 5.528693217966663e-06,
|
| 618 |
+
"loss": 0.0148,
|
| 619 |
+
"step": 870
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.11197353352843874,
|
| 623 |
+
"grad_norm": 0.6761524081230164,
|
| 624 |
+
"learning_rate": 5.592314543835094e-06,
|
| 625 |
+
"loss": 0.0131,
|
| 626 |
+
"step": 880
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.11324596004580735,
|
| 630 |
+
"grad_norm": 0.7170369029045105,
|
| 631 |
+
"learning_rate": 5.655935869703525e-06,
|
| 632 |
+
"loss": 0.0121,
|
| 633 |
+
"step": 890
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.11451838656317598,
|
| 637 |
+
"grad_norm": 0.5446187257766724,
|
| 638 |
+
"learning_rate": 5.7195571955719566e-06,
|
| 639 |
+
"loss": 0.0126,
|
| 640 |
+
"step": 900
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.1157908130805446,
|
| 644 |
+
"grad_norm": 0.03237615525722504,
|
| 645 |
+
"learning_rate": 5.783178521440387e-06,
|
| 646 |
+
"loss": 0.0043,
|
| 647 |
+
"step": 910
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.11706323959791322,
|
| 651 |
+
"grad_norm": 0.4705624580383301,
|
| 652 |
+
"learning_rate": 5.8467998473088185e-06,
|
| 653 |
+
"loss": 0.0122,
|
| 654 |
+
"step": 920
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.11833566611528185,
|
| 658 |
+
"grad_norm": 0.8848108053207397,
|
| 659 |
+
"learning_rate": 5.91042117317725e-06,
|
| 660 |
+
"loss": 0.0184,
|
| 661 |
+
"step": 930
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.11960809263265046,
|
| 665 |
+
"grad_norm": 0.5390125513076782,
|
| 666 |
+
"learning_rate": 5.9740424990456805e-06,
|
| 667 |
+
"loss": 0.0093,
|
| 668 |
+
"step": 940
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.12088051915001909,
|
| 672 |
+
"grad_norm": 0.38235408067703247,
|
| 673 |
+
"learning_rate": 6.037663824914112e-06,
|
| 674 |
+
"loss": 0.0264,
|
| 675 |
+
"step": 950
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.12215294566738771,
|
| 679 |
+
"grad_norm": 0.07413897663354874,
|
| 680 |
+
"learning_rate": 6.1012851507825425e-06,
|
| 681 |
+
"loss": 0.0154,
|
| 682 |
+
"step": 960
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.12342537218475633,
|
| 686 |
+
"grad_norm": 0.08041392266750336,
|
| 687 |
+
"learning_rate": 6.164906476650974e-06,
|
| 688 |
+
"loss": 0.0094,
|
| 689 |
+
"step": 970
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.12469779870212495,
|
| 693 |
+
"grad_norm": 0.4950060546398163,
|
| 694 |
+
"learning_rate": 6.228527802519405e-06,
|
| 695 |
+
"loss": 0.0078,
|
| 696 |
+
"step": 980
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.12597022521949358,
|
| 700 |
+
"grad_norm": 0.028932543471455574,
|
| 701 |
+
"learning_rate": 6.292149128387837e-06,
|
| 702 |
+
"loss": 0.0115,
|
| 703 |
+
"step": 990
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.1272426517368622,
|
| 707 |
+
"grad_norm": 1.5096838474273682,
|
| 708 |
+
"learning_rate": 6.355770454256267e-06,
|
| 709 |
+
"loss": 0.0165,
|
| 710 |
+
"step": 1000
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.1285150782542308,
|
| 714 |
+
"grad_norm": 0.11332298815250397,
|
| 715 |
+
"learning_rate": 6.419391780124698e-06,
|
| 716 |
+
"loss": 0.0095,
|
| 717 |
+
"step": 1010
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.12978750477159945,
|
| 721 |
+
"grad_norm": 0.6465795040130615,
|
| 722 |
+
"learning_rate": 6.48301310599313e-06,
|
| 723 |
+
"loss": 0.0195,
|
| 724 |
+
"step": 1020
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.13105993128896806,
|
| 728 |
+
"grad_norm": 0.25017666816711426,
|
| 729 |
+
"learning_rate": 6.546634431861561e-06,
|
| 730 |
+
"loss": 0.0061,
|
| 731 |
+
"step": 1030
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 0.13233235780633668,
|
| 735 |
+
"grad_norm": 1.8187178373336792,
|
| 736 |
+
"learning_rate": 6.610255757729991e-06,
|
| 737 |
+
"loss": 0.0138,
|
| 738 |
+
"step": 1040
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.13360478432370532,
|
| 742 |
+
"grad_norm": 3.078958749771118,
|
| 743 |
+
"learning_rate": 6.673877083598422e-06,
|
| 744 |
+
"loss": 0.0141,
|
| 745 |
+
"step": 1050
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.13487721084107393,
|
| 749 |
+
"grad_norm": 0.8495808839797974,
|
| 750 |
+
"learning_rate": 6.737498409466854e-06,
|
| 751 |
+
"loss": 0.0277,
|
| 752 |
+
"step": 1060
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.13614963735844254,
|
| 756 |
+
"grad_norm": 0.30749642848968506,
|
| 757 |
+
"learning_rate": 6.8011197353352845e-06,
|
| 758 |
+
"loss": 0.0062,
|
| 759 |
+
"step": 1070
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.13742206387581118,
|
| 763 |
+
"grad_norm": 0.13450919091701508,
|
| 764 |
+
"learning_rate": 6.864741061203715e-06,
|
| 765 |
+
"loss": 0.0162,
|
| 766 |
+
"step": 1080
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 0.1386944903931798,
|
| 770 |
+
"grad_norm": 0.32650208473205566,
|
| 771 |
+
"learning_rate": 6.928362387072147e-06,
|
| 772 |
+
"loss": 0.0111,
|
| 773 |
+
"step": 1090
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.1399669169105484,
|
| 777 |
+
"grad_norm": 0.04899647459387779,
|
| 778 |
+
"learning_rate": 6.991983712940578e-06,
|
| 779 |
+
"loss": 0.0027,
|
| 780 |
+
"step": 1100
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 0.14123934342791702,
|
| 784 |
+
"grad_norm": 0.06836508959531784,
|
| 785 |
+
"learning_rate": 7.0556050388090085e-06,
|
| 786 |
+
"loss": 0.0089,
|
| 787 |
+
"step": 1110
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 0.14251176994528567,
|
| 791 |
+
"grad_norm": 0.7668923139572144,
|
| 792 |
+
"learning_rate": 7.119226364677441e-06,
|
| 793 |
+
"loss": 0.0035,
|
| 794 |
+
"step": 1120
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.14378419646265428,
|
| 798 |
+
"grad_norm": 0.05036250501871109,
|
| 799 |
+
"learning_rate": 7.182847690545871e-06,
|
| 800 |
+
"loss": 0.0063,
|
| 801 |
+
"step": 1130
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.1450566229800229,
|
| 805 |
+
"grad_norm": 0.08341695368289948,
|
| 806 |
+
"learning_rate": 7.246469016414302e-06,
|
| 807 |
+
"loss": 0.0044,
|
| 808 |
+
"step": 1140
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 0.14632904949739153,
|
| 812 |
+
"grad_norm": 2.2805428504943848,
|
| 813 |
+
"learning_rate": 7.310090342282734e-06,
|
| 814 |
+
"loss": 0.0151,
|
| 815 |
+
"step": 1150
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 0.14760147601476015,
|
| 819 |
+
"grad_norm": 0.007249306421726942,
|
| 820 |
+
"learning_rate": 7.373711668151165e-06,
|
| 821 |
+
"loss": 0.006,
|
| 822 |
+
"step": 1160
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 0.14887390253212876,
|
| 826 |
+
"grad_norm": 0.09136034548282623,
|
| 827 |
+
"learning_rate": 7.437332994019595e-06,
|
| 828 |
+
"loss": 0.0117,
|
| 829 |
+
"step": 1170
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 0.1501463290494974,
|
| 833 |
+
"grad_norm": 0.3426164984703064,
|
| 834 |
+
"learning_rate": 7.5009543198880275e-06,
|
| 835 |
+
"loss": 0.0146,
|
| 836 |
+
"step": 1180
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 0.15141875556686601,
|
| 840 |
+
"grad_norm": 0.11082851141691208,
|
| 841 |
+
"learning_rate": 7.564575645756458e-06,
|
| 842 |
+
"loss": 0.027,
|
| 843 |
+
"step": 1190
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.15269118208423463,
|
| 847 |
+
"grad_norm": 0.05444815009832382,
|
| 848 |
+
"learning_rate": 7.628196971624889e-06,
|
| 849 |
+
"loss": 0.0184,
|
| 850 |
+
"step": 1200
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 0.15396360860160327,
|
| 854 |
+
"grad_norm": 0.7797910571098328,
|
| 855 |
+
"learning_rate": 7.69181829749332e-06,
|
| 856 |
+
"loss": 0.0058,
|
| 857 |
+
"step": 1210
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.15523603511897188,
|
| 861 |
+
"grad_norm": 0.05821133777499199,
|
| 862 |
+
"learning_rate": 7.755439623361751e-06,
|
| 863 |
+
"loss": 0.0113,
|
| 864 |
+
"step": 1220
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.1565084616363405,
|
| 868 |
+
"grad_norm": 0.03613057732582092,
|
| 869 |
+
"learning_rate": 7.819060949230183e-06,
|
| 870 |
+
"loss": 0.0075,
|
| 871 |
+
"step": 1230
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 0.15778088815370914,
|
| 875 |
+
"grad_norm": 0.21981610357761383,
|
| 876 |
+
"learning_rate": 7.882682275098613e-06,
|
| 877 |
+
"loss": 0.0101,
|
| 878 |
+
"step": 1240
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.15905331467107775,
|
| 882 |
+
"grad_norm": 0.20088253915309906,
|
| 883 |
+
"learning_rate": 7.946303600967046e-06,
|
| 884 |
+
"loss": 0.0042,
|
| 885 |
+
"step": 1250
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.16032574118844636,
|
| 889 |
+
"grad_norm": 0.07598040997982025,
|
| 890 |
+
"learning_rate": 8.009924926835475e-06,
|
| 891 |
+
"loss": 0.0072,
|
| 892 |
+
"step": 1260
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 0.16159816770581498,
|
| 896 |
+
"grad_norm": 0.12485750019550323,
|
| 897 |
+
"learning_rate": 8.073546252703907e-06,
|
| 898 |
+
"loss": 0.005,
|
| 899 |
+
"step": 1270
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 0.16287059422318362,
|
| 903 |
+
"grad_norm": 0.23695872724056244,
|
| 904 |
+
"learning_rate": 8.137167578572338e-06,
|
| 905 |
+
"loss": 0.0058,
|
| 906 |
+
"step": 1280
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.16414302074055223,
|
| 910 |
+
"grad_norm": 0.5497035384178162,
|
| 911 |
+
"learning_rate": 8.20078890444077e-06,
|
| 912 |
+
"loss": 0.0048,
|
| 913 |
+
"step": 1290
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 0.16541544725792084,
|
| 917 |
+
"grad_norm": 0.11535526812076569,
|
| 918 |
+
"learning_rate": 8.2644102303092e-06,
|
| 919 |
+
"loss": 0.0162,
|
| 920 |
+
"step": 1300
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 0.16668787377528949,
|
| 924 |
+
"grad_norm": 0.24588041007518768,
|
| 925 |
+
"learning_rate": 8.328031556177632e-06,
|
| 926 |
+
"loss": 0.0167,
|
| 927 |
+
"step": 1310
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.1679603002926581,
|
| 931 |
+
"grad_norm": 0.02810610644519329,
|
| 932 |
+
"learning_rate": 8.391652882046062e-06,
|
| 933 |
+
"loss": 0.015,
|
| 934 |
+
"step": 1320
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 0.1692327268100267,
|
| 938 |
+
"grad_norm": 1.970468282699585,
|
| 939 |
+
"learning_rate": 8.455274207914494e-06,
|
| 940 |
+
"loss": 0.0086,
|
| 941 |
+
"step": 1330
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 0.17050515332739535,
|
| 945 |
+
"grad_norm": 1.3369934558868408,
|
| 946 |
+
"learning_rate": 8.518895533782923e-06,
|
| 947 |
+
"loss": 0.0047,
|
| 948 |
+
"step": 1340
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 0.17177757984476397,
|
| 952 |
+
"grad_norm": 1.4428670406341553,
|
| 953 |
+
"learning_rate": 8.582516859651356e-06,
|
| 954 |
+
"loss": 0.0055,
|
| 955 |
+
"step": 1350
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 0.17305000636213258,
|
| 959 |
+
"grad_norm": 1.5606224536895752,
|
| 960 |
+
"learning_rate": 8.646138185519786e-06,
|
| 961 |
+
"loss": 0.0124,
|
| 962 |
+
"step": 1360
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.17432243287950122,
|
| 966 |
+
"grad_norm": 0.1116681918501854,
|
| 967 |
+
"learning_rate": 8.709759511388217e-06,
|
| 968 |
+
"loss": 0.0065,
|
| 969 |
+
"step": 1370
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.17559485939686983,
|
| 973 |
+
"grad_norm": 1.1111221313476562,
|
| 974 |
+
"learning_rate": 8.773380837256649e-06,
|
| 975 |
+
"loss": 0.0118,
|
| 976 |
+
"step": 1380
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 0.17686728591423845,
|
| 980 |
+
"grad_norm": 0.028176436200737953,
|
| 981 |
+
"learning_rate": 8.83700216312508e-06,
|
| 982 |
+
"loss": 0.004,
|
| 983 |
+
"step": 1390
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 0.17813971243160706,
|
| 987 |
+
"grad_norm": 0.046109430491924286,
|
| 988 |
+
"learning_rate": 8.90062348899351e-06,
|
| 989 |
+
"loss": 0.0065,
|
| 990 |
+
"step": 1400
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 0.1794121389489757,
|
| 994 |
+
"grad_norm": 0.23842725157737732,
|
| 995 |
+
"learning_rate": 8.964244814861943e-06,
|
| 996 |
+
"loss": 0.0039,
|
| 997 |
+
"step": 1410
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 0.18068456546634432,
|
| 1001 |
+
"grad_norm": 0.07986653596162796,
|
| 1002 |
+
"learning_rate": 9.027866140730373e-06,
|
| 1003 |
+
"loss": 0.0062,
|
| 1004 |
+
"step": 1420
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 0.18195699198371293,
|
| 1008 |
+
"grad_norm": 0.028882242739200592,
|
| 1009 |
+
"learning_rate": 9.091487466598804e-06,
|
| 1010 |
+
"loss": 0.0104,
|
| 1011 |
+
"step": 1430
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 0.18322941850108157,
|
| 1015 |
+
"grad_norm": 0.054946914315223694,
|
| 1016 |
+
"learning_rate": 9.155108792467236e-06,
|
| 1017 |
+
"loss": 0.0107,
|
| 1018 |
+
"step": 1440
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 0.18450184501845018,
|
| 1022 |
+
"grad_norm": 0.15618978440761566,
|
| 1023 |
+
"learning_rate": 9.218730118335667e-06,
|
| 1024 |
+
"loss": 0.0122,
|
| 1025 |
+
"step": 1450
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 0.1857742715358188,
|
| 1029 |
+
"grad_norm": 0.1851753294467926,
|
| 1030 |
+
"learning_rate": 9.282351444204097e-06,
|
| 1031 |
+
"loss": 0.0065,
|
| 1032 |
+
"step": 1460
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 0.18704669805318744,
|
| 1036 |
+
"grad_norm": 0.2444417029619217,
|
| 1037 |
+
"learning_rate": 9.34597277007253e-06,
|
| 1038 |
+
"loss": 0.0092,
|
| 1039 |
+
"step": 1470
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 0.18831912457055605,
|
| 1043 |
+
"grad_norm": 1.1832714080810547,
|
| 1044 |
+
"learning_rate": 9.40959409594096e-06,
|
| 1045 |
+
"loss": 0.0041,
|
| 1046 |
+
"step": 1480
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 0.18959155108792466,
|
| 1050 |
+
"grad_norm": 0.20352864265441895,
|
| 1051 |
+
"learning_rate": 9.473215421809391e-06,
|
| 1052 |
+
"loss": 0.0138,
|
| 1053 |
+
"step": 1490
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 0.1908639776052933,
|
| 1057 |
+
"grad_norm": 0.43454509973526,
|
| 1058 |
+
"learning_rate": 9.53683674767782e-06,
|
| 1059 |
+
"loss": 0.0127,
|
| 1060 |
+
"step": 1500
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 0.19213640412266192,
|
| 1064 |
+
"grad_norm": 0.8199312686920166,
|
| 1065 |
+
"learning_rate": 9.600458073546254e-06,
|
| 1066 |
+
"loss": 0.0123,
|
| 1067 |
+
"step": 1510
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 0.19340883064003053,
|
| 1071 |
+
"grad_norm": 0.016706250607967377,
|
| 1072 |
+
"learning_rate": 9.664079399414683e-06,
|
| 1073 |
+
"loss": 0.0127,
|
| 1074 |
+
"step": 1520
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 0.19468125715739917,
|
| 1078 |
+
"grad_norm": 1.3700906038284302,
|
| 1079 |
+
"learning_rate": 9.727700725283115e-06,
|
| 1080 |
+
"loss": 0.0082,
|
| 1081 |
+
"step": 1530
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 0.1959536836747678,
|
| 1085 |
+
"grad_norm": 0.05637359619140625,
|
| 1086 |
+
"learning_rate": 9.791322051151546e-06,
|
| 1087 |
+
"loss": 0.0229,
|
| 1088 |
+
"step": 1540
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 0.1972261101921364,
|
| 1092 |
+
"grad_norm": 0.05423460528254509,
|
| 1093 |
+
"learning_rate": 9.854943377019978e-06,
|
| 1094 |
+
"loss": 0.0067,
|
| 1095 |
+
"step": 1550
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 0.198498536709505,
|
| 1099 |
+
"grad_norm": 0.4112365245819092,
|
| 1100 |
+
"learning_rate": 9.918564702888407e-06,
|
| 1101 |
+
"loss": 0.0145,
|
| 1102 |
+
"step": 1560
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 0.19977096322687365,
|
| 1106 |
+
"grad_norm": 0.3613516092300415,
|
| 1107 |
+
"learning_rate": 9.98218602875684e-06,
|
| 1108 |
+
"loss": 0.0045,
|
| 1109 |
+
"step": 1570
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 0.20104338974424227,
|
| 1113 |
+
"grad_norm": 0.20391610264778137,
|
| 1114 |
+
"learning_rate": 1.004580735462527e-05,
|
| 1115 |
+
"loss": 0.0159,
|
| 1116 |
+
"step": 1580
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 0.20231581626161088,
|
| 1120 |
+
"grad_norm": 0.5387713313102722,
|
| 1121 |
+
"learning_rate": 1.0109428680493702e-05,
|
| 1122 |
+
"loss": 0.0136,
|
| 1123 |
+
"step": 1590
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 0.20358824277897952,
|
| 1127 |
+
"grad_norm": 0.14269393682479858,
|
| 1128 |
+
"learning_rate": 1.0173050006362133e-05,
|
| 1129 |
+
"loss": 0.0065,
|
| 1130 |
+
"step": 1600
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 0.20486066929634814,
|
| 1134 |
+
"grad_norm": 1.532262921333313,
|
| 1135 |
+
"learning_rate": 1.0236671332230564e-05,
|
| 1136 |
+
"loss": 0.0275,
|
| 1137 |
+
"step": 1610
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 0.20613309581371675,
|
| 1141 |
+
"grad_norm": 2.2569189071655273,
|
| 1142 |
+
"learning_rate": 1.0300292658098996e-05,
|
| 1143 |
+
"loss": 0.0165,
|
| 1144 |
+
"step": 1620
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 0.2074055223310854,
|
| 1148 |
+
"grad_norm": 0.21518416702747345,
|
| 1149 |
+
"learning_rate": 1.0363913983967426e-05,
|
| 1150 |
+
"loss": 0.0158,
|
| 1151 |
+
"step": 1630
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 0.208677948848454,
|
| 1155 |
+
"grad_norm": 0.041043154895305634,
|
| 1156 |
+
"learning_rate": 1.0427535309835857e-05,
|
| 1157 |
+
"loss": 0.0101,
|
| 1158 |
+
"step": 1640
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 0.20995037536582262,
|
| 1162 |
+
"grad_norm": 0.030664950609207153,
|
| 1163 |
+
"learning_rate": 1.0491156635704288e-05,
|
| 1164 |
+
"loss": 0.003,
|
| 1165 |
+
"step": 1650
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 0.21122280188319126,
|
| 1169 |
+
"grad_norm": 0.03374583646655083,
|
| 1170 |
+
"learning_rate": 1.055477796157272e-05,
|
| 1171 |
+
"loss": 0.0115,
|
| 1172 |
+
"step": 1660
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 0.21249522840055987,
|
| 1176 |
+
"grad_norm": 0.020480433478951454,
|
| 1177 |
+
"learning_rate": 1.0618399287441151e-05,
|
| 1178 |
+
"loss": 0.0039,
|
| 1179 |
+
"step": 1670
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 0.21376765491792848,
|
| 1183 |
+
"grad_norm": 0.04108405113220215,
|
| 1184 |
+
"learning_rate": 1.0682020613309583e-05,
|
| 1185 |
+
"loss": 0.0142,
|
| 1186 |
+
"step": 1680
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 0.2150400814352971,
|
| 1190 |
+
"grad_norm": 0.0639573484659195,
|
| 1191 |
+
"learning_rate": 1.0745641939178012e-05,
|
| 1192 |
+
"loss": 0.0053,
|
| 1193 |
+
"step": 1690
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 0.21631250795266574,
|
| 1197 |
+
"grad_norm": 1.848137378692627,
|
| 1198 |
+
"learning_rate": 1.0809263265046444e-05,
|
| 1199 |
+
"loss": 0.0071,
|
| 1200 |
+
"step": 1700
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 0.21758493447003435,
|
| 1204 |
+
"grad_norm": 0.271002858877182,
|
| 1205 |
+
"learning_rate": 1.0872884590914875e-05,
|
| 1206 |
+
"loss": 0.0096,
|
| 1207 |
+
"step": 1710
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 0.21885736098740297,
|
| 1211 |
+
"grad_norm": 0.02884743921458721,
|
| 1212 |
+
"learning_rate": 1.0936505916783307e-05,
|
| 1213 |
+
"loss": 0.0064,
|
| 1214 |
+
"step": 1720
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 0.2201297875047716,
|
| 1218 |
+
"grad_norm": 0.033135417848825455,
|
| 1219 |
+
"learning_rate": 1.1000127242651738e-05,
|
| 1220 |
+
"loss": 0.0122,
|
| 1221 |
+
"step": 1730
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 0.22140221402214022,
|
| 1225 |
+
"grad_norm": 0.10254822671413422,
|
| 1226 |
+
"learning_rate": 1.106374856852017e-05,
|
| 1227 |
+
"loss": 0.0095,
|
| 1228 |
+
"step": 1740
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 0.22267464053950883,
|
| 1232 |
+
"grad_norm": 0.023600544780492783,
|
| 1233 |
+
"learning_rate": 1.1127369894388599e-05,
|
| 1234 |
+
"loss": 0.0046,
|
| 1235 |
+
"step": 1750
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 0.22394706705687747,
|
| 1239 |
+
"grad_norm": 0.24926574528217316,
|
| 1240 |
+
"learning_rate": 1.1190991220257032e-05,
|
| 1241 |
+
"loss": 0.0034,
|
| 1242 |
+
"step": 1760
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 0.2252194935742461,
|
| 1246 |
+
"grad_norm": 0.11188559979200363,
|
| 1247 |
+
"learning_rate": 1.1254612546125462e-05,
|
| 1248 |
+
"loss": 0.0075,
|
| 1249 |
+
"step": 1770
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 0.2264919200916147,
|
| 1253 |
+
"grad_norm": 1.826882004737854,
|
| 1254 |
+
"learning_rate": 1.1318233871993893e-05,
|
| 1255 |
+
"loss": 0.0072,
|
| 1256 |
+
"step": 1780
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 0.22776434660898334,
|
| 1260 |
+
"grad_norm": 0.21881231665611267,
|
| 1261 |
+
"learning_rate": 1.1381855197862323e-05,
|
| 1262 |
+
"loss": 0.0079,
|
| 1263 |
+
"step": 1790
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 0.22903677312635196,
|
| 1267 |
+
"grad_norm": 0.031731124967336655,
|
| 1268 |
+
"learning_rate": 1.1445476523730756e-05,
|
| 1269 |
+
"loss": 0.0021,
|
| 1270 |
+
"step": 1800
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 0.23030919964372057,
|
| 1274 |
+
"grad_norm": 0.017091596499085426,
|
| 1275 |
+
"learning_rate": 1.1509097849599186e-05,
|
| 1276 |
+
"loss": 0.0041,
|
| 1277 |
+
"step": 1810
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 0.2315816261610892,
|
| 1281 |
+
"grad_norm": 2.5410568714141846,
|
| 1282 |
+
"learning_rate": 1.1572719175467617e-05,
|
| 1283 |
+
"loss": 0.0083,
|
| 1284 |
+
"step": 1820
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 0.23285405267845782,
|
| 1288 |
+
"grad_norm": 0.5720783472061157,
|
| 1289 |
+
"learning_rate": 1.1636340501336049e-05,
|
| 1290 |
+
"loss": 0.0065,
|
| 1291 |
+
"step": 1830
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 0.23412647919582644,
|
| 1295 |
+
"grad_norm": 0.1771746128797531,
|
| 1296 |
+
"learning_rate": 1.169996182720448e-05,
|
| 1297 |
+
"loss": 0.0051,
|
| 1298 |
+
"step": 1840
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 0.23539890571319505,
|
| 1302 |
+
"grad_norm": 0.3735668659210205,
|
| 1303 |
+
"learning_rate": 1.176358315307291e-05,
|
| 1304 |
+
"loss": 0.0037,
|
| 1305 |
+
"step": 1850
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 0.2366713322305637,
|
| 1309 |
+
"grad_norm": 0.025163499638438225,
|
| 1310 |
+
"learning_rate": 1.1827204478941343e-05,
|
| 1311 |
+
"loss": 0.0039,
|
| 1312 |
+
"step": 1860
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 0.2379437587479323,
|
| 1316 |
+
"grad_norm": 0.3122095465660095,
|
| 1317 |
+
"learning_rate": 1.1890825804809773e-05,
|
| 1318 |
+
"loss": 0.0026,
|
| 1319 |
+
"step": 1870
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 0.23921618526530092,
|
| 1323 |
+
"grad_norm": 0.5866298079490662,
|
| 1324 |
+
"learning_rate": 1.1954447130678204e-05,
|
| 1325 |
+
"loss": 0.0027,
|
| 1326 |
+
"step": 1880
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 0.24048861178266956,
|
| 1330 |
+
"grad_norm": 0.18981511890888214,
|
| 1331 |
+
"learning_rate": 1.2018068456546635e-05,
|
| 1332 |
+
"loss": 0.0111,
|
| 1333 |
+
"step": 1890
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 0.24176103830003817,
|
| 1337 |
+
"grad_norm": 0.4353330135345459,
|
| 1338 |
+
"learning_rate": 1.2081689782415067e-05,
|
| 1339 |
+
"loss": 0.0053,
|
| 1340 |
+
"step": 1900
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 0.24303346481740679,
|
| 1344 |
+
"grad_norm": 1.369036316871643,
|
| 1345 |
+
"learning_rate": 1.2145311108283496e-05,
|
| 1346 |
+
"loss": 0.0193,
|
| 1347 |
+
"step": 1910
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 0.24430589133477543,
|
| 1351 |
+
"grad_norm": 0.13712532818317413,
|
| 1352 |
+
"learning_rate": 1.220893243415193e-05,
|
| 1353 |
+
"loss": 0.0169,
|
| 1354 |
+
"step": 1920
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 0.24557831785214404,
|
| 1358 |
+
"grad_norm": 0.05920857936143875,
|
| 1359 |
+
"learning_rate": 1.227255376002036e-05,
|
| 1360 |
+
"loss": 0.0184,
|
| 1361 |
+
"step": 1930
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 0.24685074436951265,
|
| 1365 |
+
"grad_norm": 0.021631982177495956,
|
| 1366 |
+
"learning_rate": 1.233617508588879e-05,
|
| 1367 |
+
"loss": 0.0066,
|
| 1368 |
+
"step": 1940
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 0.2481231708868813,
|
| 1372 |
+
"grad_norm": 0.16193988919258118,
|
| 1373 |
+
"learning_rate": 1.239979641175722e-05,
|
| 1374 |
+
"loss": 0.0121,
|
| 1375 |
+
"step": 1950
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 0.2493955974042499,
|
| 1379 |
+
"grad_norm": 0.02966451644897461,
|
| 1380 |
+
"learning_rate": 1.2463417737625654e-05,
|
| 1381 |
+
"loss": 0.0113,
|
| 1382 |
+
"step": 1960
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 0.2506680239216185,
|
| 1386 |
+
"grad_norm": 0.1511862426996231,
|
| 1387 |
+
"learning_rate": 1.2527039063494083e-05,
|
| 1388 |
+
"loss": 0.0044,
|
| 1389 |
+
"step": 1970
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 0.25194045043898716,
|
| 1393 |
+
"grad_norm": 0.06729118525981903,
|
| 1394 |
+
"learning_rate": 1.2590660389362516e-05,
|
| 1395 |
+
"loss": 0.004,
|
| 1396 |
+
"step": 1980
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 0.25321287695635575,
|
| 1400 |
+
"grad_norm": 0.023136969655752182,
|
| 1401 |
+
"learning_rate": 1.2654281715230944e-05,
|
| 1402 |
+
"loss": 0.0033,
|
| 1403 |
+
"step": 1990
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 0.2544853034737244,
|
| 1407 |
+
"grad_norm": 0.4016958177089691,
|
| 1408 |
+
"learning_rate": 1.2717903041099377e-05,
|
| 1409 |
+
"loss": 0.0073,
|
| 1410 |
+
"step": 2000
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 0.25575772999109303,
|
| 1414 |
+
"grad_norm": 0.7486693263053894,
|
| 1415 |
+
"learning_rate": 1.2781524366967809e-05,
|
| 1416 |
+
"loss": 0.0058,
|
| 1417 |
+
"step": 2010
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 0.2570301565084616,
|
| 1421 |
+
"grad_norm": 0.2552649676799774,
|
| 1422 |
+
"learning_rate": 1.2845145692836239e-05,
|
| 1423 |
+
"loss": 0.005,
|
| 1424 |
+
"step": 2020
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 0.25830258302583026,
|
| 1428 |
+
"grad_norm": 0.07152820378541946,
|
| 1429 |
+
"learning_rate": 1.290876701870467e-05,
|
| 1430 |
+
"loss": 0.003,
|
| 1431 |
+
"step": 2030
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 0.2595750095431989,
|
| 1435 |
+
"grad_norm": 0.4438578188419342,
|
| 1436 |
+
"learning_rate": 1.2972388344573103e-05,
|
| 1437 |
+
"loss": 0.0088,
|
| 1438 |
+
"step": 2040
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 0.2608474360605675,
|
| 1442 |
+
"grad_norm": 0.052528318017721176,
|
| 1443 |
+
"learning_rate": 1.3036009670441531e-05,
|
| 1444 |
+
"loss": 0.0071,
|
| 1445 |
+
"step": 2050
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 0.2621198625779361,
|
| 1449 |
+
"grad_norm": 1.7935601472854614,
|
| 1450 |
+
"learning_rate": 1.3099630996309964e-05,
|
| 1451 |
+
"loss": 0.0083,
|
| 1452 |
+
"step": 2060
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 0.26339228909530477,
|
| 1456 |
+
"grad_norm": 0.2832243740558624,
|
| 1457 |
+
"learning_rate": 1.3163252322178396e-05,
|
| 1458 |
+
"loss": 0.0056,
|
| 1459 |
+
"step": 2070
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 0.26466471561267335,
|
| 1463 |
+
"grad_norm": 0.11939876526594162,
|
| 1464 |
+
"learning_rate": 1.3226873648046825e-05,
|
| 1465 |
+
"loss": 0.0025,
|
| 1466 |
+
"step": 2080
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 0.265937142130042,
|
| 1470 |
+
"grad_norm": 0.07402954995632172,
|
| 1471 |
+
"learning_rate": 1.3290494973915257e-05,
|
| 1472 |
+
"loss": 0.0065,
|
| 1473 |
+
"step": 2090
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 0.26720956864741063,
|
| 1477 |
+
"grad_norm": 0.3249404728412628,
|
| 1478 |
+
"learning_rate": 1.335411629978369e-05,
|
| 1479 |
+
"loss": 0.0023,
|
| 1480 |
+
"step": 2100
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 0.2684819951647792,
|
| 1484 |
+
"grad_norm": 1.273720622062683,
|
| 1485 |
+
"learning_rate": 1.3417737625652118e-05,
|
| 1486 |
+
"loss": 0.0037,
|
| 1487 |
+
"step": 2110
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 0.26975442168214786,
|
| 1491 |
+
"grad_norm": 2.491718053817749,
|
| 1492 |
+
"learning_rate": 1.3481358951520551e-05,
|
| 1493 |
+
"loss": 0.0085,
|
| 1494 |
+
"step": 2120
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 0.2710268481995165,
|
| 1498 |
+
"grad_norm": 0.6044092774391174,
|
| 1499 |
+
"learning_rate": 1.3544980277388982e-05,
|
| 1500 |
+
"loss": 0.0024,
|
| 1501 |
+
"step": 2130
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 0.2722992747168851,
|
| 1505 |
+
"grad_norm": 0.007103513460606337,
|
| 1506 |
+
"learning_rate": 1.3608601603257412e-05,
|
| 1507 |
+
"loss": 0.0078,
|
| 1508 |
+
"step": 2140
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 0.27357170123425373,
|
| 1512 |
+
"grad_norm": 0.03136291354894638,
|
| 1513 |
+
"learning_rate": 1.3672222929125843e-05,
|
| 1514 |
+
"loss": 0.0089,
|
| 1515 |
+
"step": 2150
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 0.27484412775162237,
|
| 1519 |
+
"grad_norm": 0.08181755989789963,
|
| 1520 |
+
"learning_rate": 1.3735844254994273e-05,
|
| 1521 |
+
"loss": 0.0033,
|
| 1522 |
+
"step": 2160
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 0.27611655426899095,
|
| 1526 |
+
"grad_norm": 1.7549971342086792,
|
| 1527 |
+
"learning_rate": 1.3799465580862706e-05,
|
| 1528 |
+
"loss": 0.0175,
|
| 1529 |
+
"step": 2170
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 0.2773889807863596,
|
| 1533 |
+
"grad_norm": 0.320430189371109,
|
| 1534 |
+
"learning_rate": 1.3863086906731138e-05,
|
| 1535 |
+
"loss": 0.0051,
|
| 1536 |
+
"step": 2180
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 0.27866140730372824,
|
| 1540 |
+
"grad_norm": 0.008512305095791817,
|
| 1541 |
+
"learning_rate": 1.3926708232599567e-05,
|
| 1542 |
+
"loss": 0.0056,
|
| 1543 |
+
"step": 2190
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 0.2799338338210968,
|
| 1547 |
+
"grad_norm": 0.038556866347789764,
|
| 1548 |
+
"learning_rate": 1.3990329558467999e-05,
|
| 1549 |
+
"loss": 0.0034,
|
| 1550 |
+
"step": 2200
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 0.28120626033846546,
|
| 1554 |
+
"grad_norm": 0.02490425482392311,
|
| 1555 |
+
"learning_rate": 1.405395088433643e-05,
|
| 1556 |
+
"loss": 0.008,
|
| 1557 |
+
"step": 2210
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 0.28247868685583405,
|
| 1561 |
+
"grad_norm": 0.09558805078268051,
|
| 1562 |
+
"learning_rate": 1.411757221020486e-05,
|
| 1563 |
+
"loss": 0.018,
|
| 1564 |
+
"step": 2220
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 0.2837511133732027,
|
| 1568 |
+
"grad_norm": 1.5566900968551636,
|
| 1569 |
+
"learning_rate": 1.4181193536073293e-05,
|
| 1570 |
+
"loss": 0.0125,
|
| 1571 |
+
"step": 2230
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 0.28502353989057133,
|
| 1575 |
+
"grad_norm": 0.05425062030553818,
|
| 1576 |
+
"learning_rate": 1.4244814861941724e-05,
|
| 1577 |
+
"loss": 0.0041,
|
| 1578 |
+
"step": 2240
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 0.2862959664079399,
|
| 1582 |
+
"grad_norm": 0.00941161997616291,
|
| 1583 |
+
"learning_rate": 1.4308436187810154e-05,
|
| 1584 |
+
"loss": 0.0028,
|
| 1585 |
+
"step": 2250
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 0.28756839292530856,
|
| 1589 |
+
"grad_norm": 0.08245985209941864,
|
| 1590 |
+
"learning_rate": 1.4372057513678586e-05,
|
| 1591 |
+
"loss": 0.0047,
|
| 1592 |
+
"step": 2260
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 0.2888408194426772,
|
| 1596 |
+
"grad_norm": 0.7605161666870117,
|
| 1597 |
+
"learning_rate": 1.4435678839547017e-05,
|
| 1598 |
+
"loss": 0.0071,
|
| 1599 |
+
"step": 2270
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 0.2901132459600458,
|
| 1603 |
+
"grad_norm": 0.09281841665506363,
|
| 1604 |
+
"learning_rate": 1.4499300165415447e-05,
|
| 1605 |
+
"loss": 0.0097,
|
| 1606 |
+
"step": 2280
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 0.2913856724774144,
|
| 1610 |
+
"grad_norm": 0.04518060013651848,
|
| 1611 |
+
"learning_rate": 1.456292149128388e-05,
|
| 1612 |
+
"loss": 0.0119,
|
| 1613 |
+
"step": 2290
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 0.29265809899478307,
|
| 1617 |
+
"grad_norm": 0.6776490211486816,
|
| 1618 |
+
"learning_rate": 1.4626542817152311e-05,
|
| 1619 |
+
"loss": 0.0052,
|
| 1620 |
+
"step": 2300
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 0.29393052551215165,
|
| 1624 |
+
"grad_norm": 0.4233013987541199,
|
| 1625 |
+
"learning_rate": 1.4690164143020741e-05,
|
| 1626 |
+
"loss": 0.0036,
|
| 1627 |
+
"step": 2310
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 0.2952029520295203,
|
| 1631 |
+
"grad_norm": 1.5548006296157837,
|
| 1632 |
+
"learning_rate": 1.4753785468889172e-05,
|
| 1633 |
+
"loss": 0.0063,
|
| 1634 |
+
"step": 2320
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 0.29647537854688893,
|
| 1638 |
+
"grad_norm": 0.19469067454338074,
|
| 1639 |
+
"learning_rate": 1.4817406794757604e-05,
|
| 1640 |
+
"loss": 0.0044,
|
| 1641 |
+
"step": 2330
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 0.2977478050642575,
|
| 1645 |
+
"grad_norm": 0.17912298440933228,
|
| 1646 |
+
"learning_rate": 1.4881028120626033e-05,
|
| 1647 |
+
"loss": 0.0047,
|
| 1648 |
+
"step": 2340
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 0.29902023158162616,
|
| 1652 |
+
"grad_norm": 0.3399372696876526,
|
| 1653 |
+
"learning_rate": 1.4944649446494467e-05,
|
| 1654 |
+
"loss": 0.0085,
|
| 1655 |
+
"step": 2350
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 0.3002926580989948,
|
| 1659 |
+
"grad_norm": 0.9351184368133545,
|
| 1660 |
+
"learning_rate": 1.5008270772362898e-05,
|
| 1661 |
+
"loss": 0.0052,
|
| 1662 |
+
"step": 2360
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 0.3015650846163634,
|
| 1666 |
+
"grad_norm": 0.11992344260215759,
|
| 1667 |
+
"learning_rate": 1.5071892098231328e-05,
|
| 1668 |
+
"loss": 0.0092,
|
| 1669 |
+
"step": 2370
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 0.30283751113373203,
|
| 1673 |
+
"grad_norm": 1.076342225074768,
|
| 1674 |
+
"learning_rate": 1.5135513424099759e-05,
|
| 1675 |
+
"loss": 0.007,
|
| 1676 |
+
"step": 2380
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 0.30410993765110067,
|
| 1680 |
+
"grad_norm": 0.2611420154571533,
|
| 1681 |
+
"learning_rate": 1.5199134749968192e-05,
|
| 1682 |
+
"loss": 0.0055,
|
| 1683 |
+
"step": 2390
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 0.30538236416846926,
|
| 1687 |
+
"grad_norm": 0.04634341970086098,
|
| 1688 |
+
"learning_rate": 1.526275607583662e-05,
|
| 1689 |
+
"loss": 0.017,
|
| 1690 |
+
"step": 2400
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 0.3066547906858379,
|
| 1694 |
+
"grad_norm": 0.32857760787010193,
|
| 1695 |
+
"learning_rate": 1.5326377401705053e-05,
|
| 1696 |
+
"loss": 0.0136,
|
| 1697 |
+
"step": 2410
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 0.30792721720320654,
|
| 1701 |
+
"grad_norm": 0.31227806210517883,
|
| 1702 |
+
"learning_rate": 1.5389998727573486e-05,
|
| 1703 |
+
"loss": 0.0052,
|
| 1704 |
+
"step": 2420
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 0.3091996437205751,
|
| 1708 |
+
"grad_norm": 0.8206414580345154,
|
| 1709 |
+
"learning_rate": 1.5453620053441913e-05,
|
| 1710 |
+
"loss": 0.0031,
|
| 1711 |
+
"step": 2430
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 0.31047207023794376,
|
| 1715 |
+
"grad_norm": 0.054517824202775955,
|
| 1716 |
+
"learning_rate": 1.5517241379310346e-05,
|
| 1717 |
+
"loss": 0.0201,
|
| 1718 |
+
"step": 2440
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 0.3117444967553124,
|
| 1722 |
+
"grad_norm": 0.028341468423604965,
|
| 1723 |
+
"learning_rate": 1.5580862705178776e-05,
|
| 1724 |
+
"loss": 0.0047,
|
| 1725 |
+
"step": 2450
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 0.313016923272681,
|
| 1729 |
+
"grad_norm": 0.19524231553077698,
|
| 1730 |
+
"learning_rate": 1.564448403104721e-05,
|
| 1731 |
+
"loss": 0.0085,
|
| 1732 |
+
"step": 2460
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 0.31428934979004963,
|
| 1736 |
+
"grad_norm": 0.018349912017583847,
|
| 1737 |
+
"learning_rate": 1.570810535691564e-05,
|
| 1738 |
+
"loss": 0.0068,
|
| 1739 |
+
"step": 2470
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 0.3155617763074183,
|
| 1743 |
+
"grad_norm": 0.17483970522880554,
|
| 1744 |
+
"learning_rate": 1.5771726682784068e-05,
|
| 1745 |
+
"loss": 0.0075,
|
| 1746 |
+
"step": 2480
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 0.31683420282478686,
|
| 1750 |
+
"grad_norm": 0.037000373005867004,
|
| 1751 |
+
"learning_rate": 1.58353480086525e-05,
|
| 1752 |
+
"loss": 0.0088,
|
| 1753 |
+
"step": 2490
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 0.3181066293421555,
|
| 1757 |
+
"grad_norm": 0.02603023685514927,
|
| 1758 |
+
"learning_rate": 1.5898969334520934e-05,
|
| 1759 |
+
"loss": 0.0018,
|
| 1760 |
+
"step": 2500
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 0.3193790558595241,
|
| 1764 |
+
"grad_norm": 0.045412492007017136,
|
| 1765 |
+
"learning_rate": 1.596259066038936e-05,
|
| 1766 |
+
"loss": 0.0038,
|
| 1767 |
+
"step": 2510
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 0.3206514823768927,
|
| 1771 |
+
"grad_norm": 0.25764328241348267,
|
| 1772 |
+
"learning_rate": 1.6026211986257794e-05,
|
| 1773 |
+
"loss": 0.0035,
|
| 1774 |
+
"step": 2520
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 0.32192390889426137,
|
| 1778 |
+
"grad_norm": 0.0599120631814003,
|
| 1779 |
+
"learning_rate": 1.6089833312126227e-05,
|
| 1780 |
+
"loss": 0.008,
|
| 1781 |
+
"step": 2530
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 0.32319633541162995,
|
| 1785 |
+
"grad_norm": 0.8628143072128296,
|
| 1786 |
+
"learning_rate": 1.6153454637994656e-05,
|
| 1787 |
+
"loss": 0.0063,
|
| 1788 |
+
"step": 2540
|
| 1789 |
+
},
|
| 1790 |
+
{
|
| 1791 |
+
"epoch": 0.3244687619289986,
|
| 1792 |
+
"grad_norm": 0.03839100897312164,
|
| 1793 |
+
"learning_rate": 1.6217075963863086e-05,
|
| 1794 |
+
"loss": 0.0063,
|
| 1795 |
+
"step": 2550
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 0.32574118844636724,
|
| 1799 |
+
"grad_norm": 0.15891259908676147,
|
| 1800 |
+
"learning_rate": 1.628069728973152e-05,
|
| 1801 |
+
"loss": 0.0031,
|
| 1802 |
+
"step": 2560
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 0.3270136149637358,
|
| 1806 |
+
"grad_norm": 0.3186804950237274,
|
| 1807 |
+
"learning_rate": 1.634431861559995e-05,
|
| 1808 |
+
"loss": 0.0027,
|
| 1809 |
+
"step": 2570
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 0.32828604148110446,
|
| 1813 |
+
"grad_norm": 0.015442784875631332,
|
| 1814 |
+
"learning_rate": 1.6407939941468382e-05,
|
| 1815 |
+
"loss": 0.0029,
|
| 1816 |
+
"step": 2580
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 0.3295584679984731,
|
| 1820 |
+
"grad_norm": 0.04158645495772362,
|
| 1821 |
+
"learning_rate": 1.6471561267336812e-05,
|
| 1822 |
+
"loss": 0.0086,
|
| 1823 |
+
"step": 2590
|
| 1824 |
+
},
|
| 1825 |
+
{
|
| 1826 |
+
"epoch": 0.3308308945158417,
|
| 1827 |
+
"grad_norm": 0.2870713174343109,
|
| 1828 |
+
"learning_rate": 1.653518259320524e-05,
|
| 1829 |
+
"loss": 0.0071,
|
| 1830 |
+
"step": 2600
|
| 1831 |
+
},
|
| 1832 |
+
{
|
| 1833 |
+
"epoch": 0.33210332103321033,
|
| 1834 |
+
"grad_norm": 0.485315203666687,
|
| 1835 |
+
"learning_rate": 1.6598803919073675e-05,
|
| 1836 |
+
"loss": 0.0033,
|
| 1837 |
+
"step": 2610
|
| 1838 |
+
},
|
| 1839 |
+
{
|
| 1840 |
+
"epoch": 0.33337574755057897,
|
| 1841 |
+
"grad_norm": 1.7755225896835327,
|
| 1842 |
+
"learning_rate": 1.6662425244942108e-05,
|
| 1843 |
+
"loss": 0.0126,
|
| 1844 |
+
"step": 2620
|
| 1845 |
+
},
|
| 1846 |
+
{
|
| 1847 |
+
"epoch": 0.33464817406794756,
|
| 1848 |
+
"grad_norm": 0.04747285693883896,
|
| 1849 |
+
"learning_rate": 1.6726046570810534e-05,
|
| 1850 |
+
"loss": 0.003,
|
| 1851 |
+
"step": 2630
|
| 1852 |
+
},
|
| 1853 |
+
{
|
| 1854 |
+
"epoch": 0.3359206005853162,
|
| 1855 |
+
"grad_norm": 0.7506772875785828,
|
| 1856 |
+
"learning_rate": 1.6789667896678967e-05,
|
| 1857 |
+
"loss": 0.0105,
|
| 1858 |
+
"step": 2640
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 0.33719302710268484,
|
| 1862 |
+
"grad_norm": 0.012777579948306084,
|
| 1863 |
+
"learning_rate": 1.68532892225474e-05,
|
| 1864 |
+
"loss": 0.0034,
|
| 1865 |
+
"step": 2650
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 0.3384654536200534,
|
| 1869 |
+
"grad_norm": 0.8292739391326904,
|
| 1870 |
+
"learning_rate": 1.691691054841583e-05,
|
| 1871 |
+
"loss": 0.0113,
|
| 1872 |
+
"step": 2660
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 0.33973788013742207,
|
| 1876 |
+
"grad_norm": 0.10886216908693314,
|
| 1877 |
+
"learning_rate": 1.698053187428426e-05,
|
| 1878 |
+
"loss": 0.0034,
|
| 1879 |
+
"step": 2670
|
| 1880 |
+
},
|
| 1881 |
+
{
|
| 1882 |
+
"epoch": 0.3410103066547907,
|
| 1883 |
+
"grad_norm": 0.010381593368947506,
|
| 1884 |
+
"learning_rate": 1.7044153200152693e-05,
|
| 1885 |
+
"loss": 0.0041,
|
| 1886 |
+
"step": 2680
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 0.3422827331721593,
|
| 1890 |
+
"grad_norm": 0.2505902945995331,
|
| 1891 |
+
"learning_rate": 1.7107774526021123e-05,
|
| 1892 |
+
"loss": 0.0052,
|
| 1893 |
+
"step": 2690
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 0.34355515968952793,
|
| 1897 |
+
"grad_norm": 0.11117465049028397,
|
| 1898 |
+
"learning_rate": 1.7171395851889556e-05,
|
| 1899 |
+
"loss": 0.0151,
|
| 1900 |
+
"step": 2700
|
| 1901 |
+
},
|
| 1902 |
+
{
|
| 1903 |
+
"epoch": 0.3448275862068966,
|
| 1904 |
+
"grad_norm": 0.04362442344427109,
|
| 1905 |
+
"learning_rate": 1.7235017177757985e-05,
|
| 1906 |
+
"loss": 0.0226,
|
| 1907 |
+
"step": 2710
|
| 1908 |
+
},
|
| 1909 |
+
{
|
| 1910 |
+
"epoch": 0.34610001272426516,
|
| 1911 |
+
"grad_norm": 1.0498507022857666,
|
| 1912 |
+
"learning_rate": 1.7298638503626415e-05,
|
| 1913 |
+
"loss": 0.0037,
|
| 1914 |
+
"step": 2720
|
| 1915 |
+
},
|
| 1916 |
+
{
|
| 1917 |
+
"epoch": 0.3473724392416338,
|
| 1918 |
+
"grad_norm": 0.009742997586727142,
|
| 1919 |
+
"learning_rate": 1.7362259829494848e-05,
|
| 1920 |
+
"loss": 0.0014,
|
| 1921 |
+
"step": 2730
|
| 1922 |
+
},
|
| 1923 |
+
{
|
| 1924 |
+
"epoch": 0.34864486575900244,
|
| 1925 |
+
"grad_norm": 0.16426251828670502,
|
| 1926 |
+
"learning_rate": 1.7425881155363278e-05,
|
| 1927 |
+
"loss": 0.0029,
|
| 1928 |
+
"step": 2740
|
| 1929 |
+
},
|
| 1930 |
+
{
|
| 1931 |
+
"epoch": 0.34991729227637103,
|
| 1932 |
+
"grad_norm": 0.009812717325985432,
|
| 1933 |
+
"learning_rate": 1.748950248123171e-05,
|
| 1934 |
+
"loss": 0.0035,
|
| 1935 |
+
"step": 2750
|
| 1936 |
+
},
|
| 1937 |
+
{
|
| 1938 |
+
"epoch": 0.35118971879373967,
|
| 1939 |
+
"grad_norm": 0.4048633873462677,
|
| 1940 |
+
"learning_rate": 1.755312380710014e-05,
|
| 1941 |
+
"loss": 0.0054,
|
| 1942 |
+
"step": 2760
|
| 1943 |
+
},
|
| 1944 |
+
{
|
| 1945 |
+
"epoch": 0.3524621453111083,
|
| 1946 |
+
"grad_norm": 0.049217529594898224,
|
| 1947 |
+
"learning_rate": 1.761674513296857e-05,
|
| 1948 |
+
"loss": 0.0073,
|
| 1949 |
+
"step": 2770
|
| 1950 |
+
},
|
| 1951 |
+
{
|
| 1952 |
+
"epoch": 0.3537345718284769,
|
| 1953 |
+
"grad_norm": 0.15697529911994934,
|
| 1954 |
+
"learning_rate": 1.7680366458837003e-05,
|
| 1955 |
+
"loss": 0.0057,
|
| 1956 |
+
"step": 2780
|
| 1957 |
+
},
|
| 1958 |
+
{
|
| 1959 |
+
"epoch": 0.35500699834584554,
|
| 1960 |
+
"grad_norm": 0.43548473715782166,
|
| 1961 |
+
"learning_rate": 1.7743987784705433e-05,
|
| 1962 |
+
"loss": 0.0056,
|
| 1963 |
+
"step": 2790
|
| 1964 |
+
},
|
| 1965 |
+
{
|
| 1966 |
+
"epoch": 0.3562794248632141,
|
| 1967 |
+
"grad_norm": 0.47208288311958313,
|
| 1968 |
+
"learning_rate": 1.7807609110573863e-05,
|
| 1969 |
+
"loss": 0.0055,
|
| 1970 |
+
"step": 2800
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"epoch": 0.35755185138058276,
|
| 1974 |
+
"grad_norm": 0.11203566938638687,
|
| 1975 |
+
"learning_rate": 1.7871230436442296e-05,
|
| 1976 |
+
"loss": 0.0048,
|
| 1977 |
+
"step": 2810
|
| 1978 |
+
},
|
| 1979 |
+
{
|
| 1980 |
+
"epoch": 0.3588242778979514,
|
| 1981 |
+
"grad_norm": 0.04425804316997528,
|
| 1982 |
+
"learning_rate": 1.793485176231073e-05,
|
| 1983 |
+
"loss": 0.0046,
|
| 1984 |
+
"step": 2820
|
| 1985 |
+
},
|
| 1986 |
+
{
|
| 1987 |
+
"epoch": 0.36009670441532,
|
| 1988 |
+
"grad_norm": 0.29293137788772583,
|
| 1989 |
+
"learning_rate": 1.799847308817916e-05,
|
| 1990 |
+
"loss": 0.0014,
|
| 1991 |
+
"step": 2830
|
| 1992 |
+
},
|
| 1993 |
+
{
|
| 1994 |
+
"epoch": 0.36136913093268863,
|
| 1995 |
+
"grad_norm": 0.35622870922088623,
|
| 1996 |
+
"learning_rate": 1.806209441404759e-05,
|
| 1997 |
+
"loss": 0.0083,
|
| 1998 |
+
"step": 2840
|
| 1999 |
+
},
|
| 2000 |
+
{
|
| 2001 |
+
"epoch": 0.3626415574500573,
|
| 2002 |
+
"grad_norm": 0.05916297808289528,
|
| 2003 |
+
"learning_rate": 1.812571573991602e-05,
|
| 2004 |
+
"loss": 0.0055,
|
| 2005 |
+
"step": 2850
|
| 2006 |
+
},
|
| 2007 |
+
{
|
| 2008 |
+
"epoch": 0.36391398396742586,
|
| 2009 |
+
"grad_norm": 0.02308017760515213,
|
| 2010 |
+
"learning_rate": 1.818933706578445e-05,
|
| 2011 |
+
"loss": 0.0033,
|
| 2012 |
+
"step": 2860
|
| 2013 |
+
},
|
| 2014 |
+
{
|
| 2015 |
+
"epoch": 0.3651864104847945,
|
| 2016 |
+
"grad_norm": 0.01846274547278881,
|
| 2017 |
+
"learning_rate": 1.8252958391652884e-05,
|
| 2018 |
+
"loss": 0.0043,
|
| 2019 |
+
"step": 2870
|
| 2020 |
+
},
|
| 2021 |
+
{
|
| 2022 |
+
"epoch": 0.36645883700216314,
|
| 2023 |
+
"grad_norm": 1.4691132307052612,
|
| 2024 |
+
"learning_rate": 1.8316579717521314e-05,
|
| 2025 |
+
"loss": 0.0085,
|
| 2026 |
+
"step": 2880
|
| 2027 |
+
},
|
| 2028 |
+
{
|
| 2029 |
+
"epoch": 0.3677312635195317,
|
| 2030 |
+
"grad_norm": 0.014681387692689896,
|
| 2031 |
+
"learning_rate": 1.8380201043389744e-05,
|
| 2032 |
+
"loss": 0.0089,
|
| 2033 |
+
"step": 2890
|
| 2034 |
+
},
|
| 2035 |
+
{
|
| 2036 |
+
"epoch": 0.36900369003690037,
|
| 2037 |
+
"grad_norm": 0.48359155654907227,
|
| 2038 |
+
"learning_rate": 1.8443822369258177e-05,
|
| 2039 |
+
"loss": 0.0033,
|
| 2040 |
+
"step": 2900
|
| 2041 |
+
},
|
| 2042 |
+
{
|
| 2043 |
+
"epoch": 0.370276116554269,
|
| 2044 |
+
"grad_norm": 0.03644372895359993,
|
| 2045 |
+
"learning_rate": 1.8507443695126607e-05,
|
| 2046 |
+
"loss": 0.0026,
|
| 2047 |
+
"step": 2910
|
| 2048 |
+
},
|
| 2049 |
+
{
|
| 2050 |
+
"epoch": 0.3715485430716376,
|
| 2051 |
+
"grad_norm": 0.00955995637923479,
|
| 2052 |
+
"learning_rate": 1.8571065020995036e-05,
|
| 2053 |
+
"loss": 0.0117,
|
| 2054 |
+
"step": 2920
|
| 2055 |
+
},
|
| 2056 |
+
{
|
| 2057 |
+
"epoch": 0.37282096958900623,
|
| 2058 |
+
"grad_norm": 0.07726261019706726,
|
| 2059 |
+
"learning_rate": 1.863468634686347e-05,
|
| 2060 |
+
"loss": 0.0043,
|
| 2061 |
+
"step": 2930
|
| 2062 |
+
},
|
| 2063 |
+
{
|
| 2064 |
+
"epoch": 0.3740933961063749,
|
| 2065 |
+
"grad_norm": 0.07256468385457993,
|
| 2066 |
+
"learning_rate": 1.8698307672731903e-05,
|
| 2067 |
+
"loss": 0.0043,
|
| 2068 |
+
"step": 2940
|
| 2069 |
+
},
|
| 2070 |
+
{
|
| 2071 |
+
"epoch": 0.37536582262374346,
|
| 2072 |
+
"grad_norm": 0.04830784350633621,
|
| 2073 |
+
"learning_rate": 1.8761928998600332e-05,
|
| 2074 |
+
"loss": 0.0036,
|
| 2075 |
+
"step": 2950
|
| 2076 |
+
},
|
| 2077 |
+
{
|
| 2078 |
+
"epoch": 0.3766382491411121,
|
| 2079 |
+
"grad_norm": 1.5503113269805908,
|
| 2080 |
+
"learning_rate": 1.8825550324468762e-05,
|
| 2081 |
+
"loss": 0.0042,
|
| 2082 |
+
"step": 2960
|
| 2083 |
+
},
|
| 2084 |
+
{
|
| 2085 |
+
"epoch": 0.37791067565848074,
|
| 2086 |
+
"grad_norm": 1.545857310295105,
|
| 2087 |
+
"learning_rate": 1.8889171650337195e-05,
|
| 2088 |
+
"loss": 0.0126,
|
| 2089 |
+
"step": 2970
|
| 2090 |
+
},
|
| 2091 |
+
{
|
| 2092 |
+
"epoch": 0.37918310217584933,
|
| 2093 |
+
"grad_norm": 0.0384180061519146,
|
| 2094 |
+
"learning_rate": 1.8952792976205625e-05,
|
| 2095 |
+
"loss": 0.0016,
|
| 2096 |
+
"step": 2980
|
| 2097 |
+
},
|
| 2098 |
+
{
|
| 2099 |
+
"epoch": 0.38045552869321797,
|
| 2100 |
+
"grad_norm": 0.04663410782814026,
|
| 2101 |
+
"learning_rate": 1.9016414302074058e-05,
|
| 2102 |
+
"loss": 0.0135,
|
| 2103 |
+
"step": 2990
|
| 2104 |
+
},
|
| 2105 |
+
{
|
| 2106 |
+
"epoch": 0.3817279552105866,
|
| 2107 |
+
"grad_norm": 1.142086386680603,
|
| 2108 |
+
"learning_rate": 1.9080035627942488e-05,
|
| 2109 |
+
"loss": 0.0108,
|
| 2110 |
+
"step": 3000
|
| 2111 |
+
}
|
| 2112 |
+
],
|
| 2113 |
+
"logging_steps": 10,
|
| 2114 |
+
"max_steps": 78590,
|
| 2115 |
+
"num_input_tokens_seen": 0,
|
| 2116 |
+
"num_train_epochs": 10,
|
| 2117 |
+
"save_steps": 1000,
|
| 2118 |
+
"stateful_callbacks": {
|
| 2119 |
+
"TrainerControl": {
|
| 2120 |
+
"args": {
|
| 2121 |
+
"should_epoch_stop": false,
|
| 2122 |
+
"should_evaluate": false,
|
| 2123 |
+
"should_log": false,
|
| 2124 |
+
"should_save": true,
|
| 2125 |
+
"should_training_stop": false
|
| 2126 |
+
},
|
| 2127 |
+
"attributes": {}
|
| 2128 |
+
}
|
| 2129 |
+
},
|
| 2130 |
+
"total_flos": 7.345969800339784e+17,
|
| 2131 |
+
"train_batch_size": 32,
|
| 2132 |
+
"trial_name": null,
|
| 2133 |
+
"trial_params": null
|
| 2134 |
+
}
|
MS_Marco_ep10/checkpoint-3000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b7c3a81dbd821ff62fe2820db3a336ec894be47026ddefd26dc3159ee1f50881
|
| 3 |
+
size 5841
|