Upload folder using huggingface_hub
Browse files- README.md +202 -3
- adapter_config.json +36 -0
- adapter_model.safetensors +3 -0
- experiment_cfg/metadata.json +203 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +383 -0
README.md
CHANGED
|
@@ -1,3 +1,202 @@
|
|
| 1 |
-
---
|
| 2 |
-
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: nvidia/GR00T-N1-2B
|
| 3 |
+
library_name: peft
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.14.0
|
adapter_config.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "/root/.cache/huggingface/hub/models--nvidia--GR00T-N1-2B/snapshots/32e1fd2507f7739fad443e6b449c8188e0e02fcb",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"eva_config": null,
|
| 7 |
+
"exclude_modules": null,
|
| 8 |
+
"fan_in_fan_out": false,
|
| 9 |
+
"inference_mode": true,
|
| 10 |
+
"init_lora_weights": true,
|
| 11 |
+
"layer_replication": null,
|
| 12 |
+
"layers_pattern": null,
|
| 13 |
+
"layers_to_transform": null,
|
| 14 |
+
"loftq_config": {},
|
| 15 |
+
"lora_alpha": 128,
|
| 16 |
+
"lora_bias": false,
|
| 17 |
+
"lora_dropout": 0.1,
|
| 18 |
+
"megatron_config": null,
|
| 19 |
+
"megatron_core": "megatron.core",
|
| 20 |
+
"modules_to_save": null,
|
| 21 |
+
"peft_type": "LORA",
|
| 22 |
+
"r": 64,
|
| 23 |
+
"rank_pattern": {},
|
| 24 |
+
"revision": null,
|
| 25 |
+
"target_modules": [
|
| 26 |
+
"to_q",
|
| 27 |
+
"q_proj",
|
| 28 |
+
"to_v",
|
| 29 |
+
"v_proj",
|
| 30 |
+
"to_k",
|
| 31 |
+
"k_proj"
|
| 32 |
+
],
|
| 33 |
+
"task_type": "CAUSAL_LM",
|
| 34 |
+
"use_dora": false,
|
| 35 |
+
"use_rslora": false
|
| 36 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:12e92d22f48dff8407cc37f610b1b7a4af227cb792b25a76f6fd4132e955eb02
|
| 3 |
+
size 123328576
|
experiment_cfg/metadata.json
ADDED
|
@@ -0,0 +1,203 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"new_embodiment": {
|
| 3 |
+
"statistics": {
|
| 4 |
+
"state": {
|
| 5 |
+
"single_arm": {
|
| 6 |
+
"max": [
|
| 7 |
+
1.3256829977035522,
|
| 8 |
+
1.6831878423690796,
|
| 9 |
+
1.6018670797348022,
|
| 10 |
+
1.6540350914001465,
|
| 11 |
+
0.19793184101581573
|
| 12 |
+
],
|
| 13 |
+
"min": [
|
| 14 |
+
-1.350232720375061,
|
| 15 |
+
-1.8304859399795532,
|
| 16 |
+
-1.3625075817108154,
|
| 17 |
+
-1.8488982915878296,
|
| 18 |
+
-0.13809198141098022
|
| 19 |
+
],
|
| 20 |
+
"mean": [
|
| 21 |
+
-0.21111595630645752,
|
| 22 |
+
-0.37636134028434753,
|
| 23 |
+
0.8651418685913086,
|
| 24 |
+
-0.8441829681396484,
|
| 25 |
+
0.04267279431223869
|
| 26 |
+
],
|
| 27 |
+
"std": [
|
| 28 |
+
0.6699364185333252,
|
| 29 |
+
1.0180519819259644,
|
| 30 |
+
0.8384478092193604,
|
| 31 |
+
0.5619941353797913,
|
| 32 |
+
0.0544276125729084
|
| 33 |
+
],
|
| 34 |
+
"q01": [
|
| 35 |
+
-1.3241486549377441,
|
| 36 |
+
-1.7844552993774414,
|
| 37 |
+
-1.3042020797729492,
|
| 38 |
+
-1.6939283609390259,
|
| 39 |
+
-0.13655762374401093
|
| 40 |
+
],
|
| 41 |
+
"q99": [
|
| 42 |
+
1.2980647087097168,
|
| 43 |
+
1.480652928352356,
|
| 44 |
+
1.6003326177597046,
|
| 45 |
+
1.3333548307418823,
|
| 46 |
+
0.15957295894622803
|
| 47 |
+
]
|
| 48 |
+
},
|
| 49 |
+
"gripper": {
|
| 50 |
+
"max": [
|
| 51 |
+
2.0713796615600586
|
| 52 |
+
],
|
| 53 |
+
"min": [
|
| 54 |
+
0.009206132031977177
|
| 55 |
+
],
|
| 56 |
+
"mean": [
|
| 57 |
+
0.322316437959671
|
| 58 |
+
],
|
| 59 |
+
"std": [
|
| 60 |
+
0.5169613361358643
|
| 61 |
+
],
|
| 62 |
+
"q01": [
|
| 63 |
+
0.009206132031977177
|
| 64 |
+
],
|
| 65 |
+
"q99": [
|
| 66 |
+
1.7307528257369995
|
| 67 |
+
]
|
| 68 |
+
}
|
| 69 |
+
},
|
| 70 |
+
"action": {
|
| 71 |
+
"single_arm": {
|
| 72 |
+
"max": [
|
| 73 |
+
1.3256829977035522,
|
| 74 |
+
1.6831878423690796,
|
| 75 |
+
1.6018670797348022,
|
| 76 |
+
1.6540350914001465,
|
| 77 |
+
0.19793184101581573
|
| 78 |
+
],
|
| 79 |
+
"min": [
|
| 80 |
+
-1.350232720375061,
|
| 81 |
+
-1.8304859399795532,
|
| 82 |
+
-1.3625075817108154,
|
| 83 |
+
-1.8488982915878296,
|
| 84 |
+
-0.13809198141098022
|
| 85 |
+
],
|
| 86 |
+
"mean": [
|
| 87 |
+
-0.21111606061458588,
|
| 88 |
+
-0.3763605058193207,
|
| 89 |
+
0.8651413917541504,
|
| 90 |
+
-0.8441831469535828,
|
| 91 |
+
0.04267395660281181
|
| 92 |
+
],
|
| 93 |
+
"std": [
|
| 94 |
+
0.6699364185333252,
|
| 95 |
+
1.018051028251648,
|
| 96 |
+
0.838447630405426,
|
| 97 |
+
0.5619938969612122,
|
| 98 |
+
0.054428581148386
|
| 99 |
+
],
|
| 100 |
+
"q01": [
|
| 101 |
+
-1.3241486549377441,
|
| 102 |
+
-1.7844552993774414,
|
| 103 |
+
-1.3042020797729492,
|
| 104 |
+
-1.6939283609390259,
|
| 105 |
+
-0.13655762374401093
|
| 106 |
+
],
|
| 107 |
+
"q99": [
|
| 108 |
+
1.2980647087097168,
|
| 109 |
+
1.480652928352356,
|
| 110 |
+
1.6003326177597046,
|
| 111 |
+
1.3333548307418823,
|
| 112 |
+
0.15957295894622803
|
| 113 |
+
]
|
| 114 |
+
},
|
| 115 |
+
"gripper": {
|
| 116 |
+
"max": [
|
| 117 |
+
2.0713796615600586
|
| 118 |
+
],
|
| 119 |
+
"min": [
|
| 120 |
+
0.009206132031977177
|
| 121 |
+
],
|
| 122 |
+
"mean": [
|
| 123 |
+
0.32231196761131287
|
| 124 |
+
],
|
| 125 |
+
"std": [
|
| 126 |
+
0.5169665813446045
|
| 127 |
+
],
|
| 128 |
+
"q01": [
|
| 129 |
+
0.009206132031977177
|
| 130 |
+
],
|
| 131 |
+
"q99": [
|
| 132 |
+
1.7307528257369995
|
| 133 |
+
]
|
| 134 |
+
}
|
| 135 |
+
}
|
| 136 |
+
},
|
| 137 |
+
"modalities": {
|
| 138 |
+
"video": {
|
| 139 |
+
"main": {
|
| 140 |
+
"resolution": [
|
| 141 |
+
320,
|
| 142 |
+
240
|
| 143 |
+
],
|
| 144 |
+
"channels": 3,
|
| 145 |
+
"fps": 30.0
|
| 146 |
+
},
|
| 147 |
+
"secondary_0": {
|
| 148 |
+
"resolution": [
|
| 149 |
+
320,
|
| 150 |
+
240
|
| 151 |
+
],
|
| 152 |
+
"channels": 3,
|
| 153 |
+
"fps": 30.0
|
| 154 |
+
},
|
| 155 |
+
"secondary_1": {
|
| 156 |
+
"resolution": [
|
| 157 |
+
320,
|
| 158 |
+
240
|
| 159 |
+
],
|
| 160 |
+
"channels": 3,
|
| 161 |
+
"fps": 30.0
|
| 162 |
+
}
|
| 163 |
+
},
|
| 164 |
+
"state": {
|
| 165 |
+
"single_arm": {
|
| 166 |
+
"absolute": true,
|
| 167 |
+
"rotation_type": null,
|
| 168 |
+
"shape": [
|
| 169 |
+
5
|
| 170 |
+
],
|
| 171 |
+
"continuous": true
|
| 172 |
+
},
|
| 173 |
+
"gripper": {
|
| 174 |
+
"absolute": true,
|
| 175 |
+
"rotation_type": null,
|
| 176 |
+
"shape": [
|
| 177 |
+
1
|
| 178 |
+
],
|
| 179 |
+
"continuous": true
|
| 180 |
+
}
|
| 181 |
+
},
|
| 182 |
+
"action": {
|
| 183 |
+
"single_arm": {
|
| 184 |
+
"absolute": true,
|
| 185 |
+
"rotation_type": null,
|
| 186 |
+
"shape": [
|
| 187 |
+
5
|
| 188 |
+
],
|
| 189 |
+
"continuous": true
|
| 190 |
+
},
|
| 191 |
+
"gripper": {
|
| 192 |
+
"absolute": true,
|
| 193 |
+
"rotation_type": null,
|
| 194 |
+
"shape": [
|
| 195 |
+
1
|
| 196 |
+
],
|
| 197 |
+
"continuous": true
|
| 198 |
+
}
|
| 199 |
+
}
|
| 200 |
+
},
|
| 201 |
+
"embodiment_tag": "new_embodiment"
|
| 202 |
+
}
|
| 203 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a523ad8dc9a069c3050531ba45bb3d7ee500f4a826779cff7a5626279ae926f0
|
| 3 |
+
size 246824634
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7de0bc89615aaf6a6ee78f1d06925ed7d331eee501d3484ea259c3a244333f49
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fe1d153de177b356f9e3a70d6e4ec979560b0c300994e71ca4cb89afc74c5b3a
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
@@ -0,0 +1,383 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.16852039096730703,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 500,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.003370407819346141,
|
| 13 |
+
"grad_norm": 0.6622726321220398,
|
| 14 |
+
"learning_rate": 4e-05,
|
| 15 |
+
"loss": 1.1086,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.006740815638692282,
|
| 20 |
+
"grad_norm": 0.6852302551269531,
|
| 21 |
+
"learning_rate": 8e-05,
|
| 22 |
+
"loss": 1.0139,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.010111223458038422,
|
| 27 |
+
"grad_norm": 0.7799952626228333,
|
| 28 |
+
"learning_rate": 9.997266286704631e-05,
|
| 29 |
+
"loss": 0.7389,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.013481631277384564,
|
| 34 |
+
"grad_norm": 1.3821028470993042,
|
| 35 |
+
"learning_rate": 9.975414512725057e-05,
|
| 36 |
+
"loss": 0.4005,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.016852039096730706,
|
| 41 |
+
"grad_norm": 1.4913556575775146,
|
| 42 |
+
"learning_rate": 9.931806517013612e-05,
|
| 43 |
+
"loss": 0.5061,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.020222446916076844,
|
| 48 |
+
"grad_norm": 1.5664910078048706,
|
| 49 |
+
"learning_rate": 9.86663298624003e-05,
|
| 50 |
+
"loss": 0.4028,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.023592854735422986,
|
| 55 |
+
"grad_norm": 1.2872231006622314,
|
| 56 |
+
"learning_rate": 9.780178907671789e-05,
|
| 57 |
+
"loss": 0.3596,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.026963262554769128,
|
| 62 |
+
"grad_norm": 1.8300050497055054,
|
| 63 |
+
"learning_rate": 9.672822322997305e-05,
|
| 64 |
+
"loss": 0.3788,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.030333670374115267,
|
| 69 |
+
"grad_norm": 1.0094068050384521,
|
| 70 |
+
"learning_rate": 9.545032675245813e-05,
|
| 71 |
+
"loss": 0.3413,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.03370407819346141,
|
| 76 |
+
"grad_norm": 1.8348039388656616,
|
| 77 |
+
"learning_rate": 9.397368756032445e-05,
|
| 78 |
+
"loss": 0.3873,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.03707448601280755,
|
| 83 |
+
"grad_norm": 0.6941381692886353,
|
| 84 |
+
"learning_rate": 9.230476262104677e-05,
|
| 85 |
+
"loss": 0.2787,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.04044489383215369,
|
| 90 |
+
"grad_norm": 1.146726131439209,
|
| 91 |
+
"learning_rate": 9.045084971874738e-05,
|
| 92 |
+
"loss": 0.3802,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.043815301651499834,
|
| 97 |
+
"grad_norm": 1.0894972085952759,
|
| 98 |
+
"learning_rate": 8.842005554284296e-05,
|
| 99 |
+
"loss": 0.3474,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.04718570947084597,
|
| 104 |
+
"grad_norm": 1.1947873830795288,
|
| 105 |
+
"learning_rate": 8.622126023955446e-05,
|
| 106 |
+
"loss": 0.303,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.05055611729019211,
|
| 111 |
+
"grad_norm": 0.881015419960022,
|
| 112 |
+
"learning_rate": 8.386407858128706e-05,
|
| 113 |
+
"loss": 0.3656,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.053926525109538256,
|
| 118 |
+
"grad_norm": 0.44869264960289,
|
| 119 |
+
"learning_rate": 8.135881792367686e-05,
|
| 120 |
+
"loss": 0.3268,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.057296932928884395,
|
| 125 |
+
"grad_norm": 1.1546025276184082,
|
| 126 |
+
"learning_rate": 7.871643313414718e-05,
|
| 127 |
+
"loss": 0.3123,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.06066734074823053,
|
| 132 |
+
"grad_norm": 0.6667796969413757,
|
| 133 |
+
"learning_rate": 7.594847868906076e-05,
|
| 134 |
+
"loss": 0.3069,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.06403774856757667,
|
| 139 |
+
"grad_norm": 1.3780990839004517,
|
| 140 |
+
"learning_rate": 7.30670581489344e-05,
|
| 141 |
+
"loss": 0.2845,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.06740815638692282,
|
| 146 |
+
"grad_norm": 1.0180288553237915,
|
| 147 |
+
"learning_rate": 7.008477123264848e-05,
|
| 148 |
+
"loss": 0.2592,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.07077856420626896,
|
| 153 |
+
"grad_norm": 0.7397503852844238,
|
| 154 |
+
"learning_rate": 6.701465872208216e-05,
|
| 155 |
+
"loss": 0.2507,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.0741489720256151,
|
| 160 |
+
"grad_norm": 0.6356308460235596,
|
| 161 |
+
"learning_rate": 6.387014543809223e-05,
|
| 162 |
+
"loss": 0.3174,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.07751937984496124,
|
| 167 |
+
"grad_norm": 1.1012778282165527,
|
| 168 |
+
"learning_rate": 6.066498153718735e-05,
|
| 169 |
+
"loss": 0.2273,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.08088978766430738,
|
| 174 |
+
"grad_norm": 0.9452115297317505,
|
| 175 |
+
"learning_rate": 5.74131823855921e-05,
|
| 176 |
+
"loss": 0.2841,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.08426019548365352,
|
| 181 |
+
"grad_norm": 1.153079867362976,
|
| 182 |
+
"learning_rate": 5.4128967273616625e-05,
|
| 183 |
+
"loss": 0.2687,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.08763060330299967,
|
| 188 |
+
"grad_norm": 0.485048770904541,
|
| 189 |
+
"learning_rate": 5.0826697238317935e-05,
|
| 190 |
+
"loss": 0.2322,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.0910010111223458,
|
| 195 |
+
"grad_norm": 0.4272606372833252,
|
| 196 |
+
"learning_rate": 4.7520812266338885e-05,
|
| 197 |
+
"loss": 0.1996,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.09437141894169195,
|
| 202 |
+
"grad_norm": 0.9538323879241943,
|
| 203 |
+
"learning_rate": 4.4225768151520694e-05,
|
| 204 |
+
"loss": 0.2667,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.09774182676103808,
|
| 209 |
+
"grad_norm": 1.2973414659500122,
|
| 210 |
+
"learning_rate": 4.095597328339452e-05,
|
| 211 |
+
"loss": 0.274,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.10111223458038422,
|
| 216 |
+
"grad_norm": 0.9469539523124695,
|
| 217 |
+
"learning_rate": 3.772572564296005e-05,
|
| 218 |
+
"loss": 0.2769,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.10448264239973036,
|
| 223 |
+
"grad_norm": 0.8325055241584778,
|
| 224 |
+
"learning_rate": 3.4549150281252636e-05,
|
| 225 |
+
"loss": 0.1807,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.10785305021907651,
|
| 230 |
+
"grad_norm": 1.1702295541763306,
|
| 231 |
+
"learning_rate": 3.144013755408895e-05,
|
| 232 |
+
"loss": 0.2512,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.11122345803842265,
|
| 237 |
+
"grad_norm": 0.5195464491844177,
|
| 238 |
+
"learning_rate": 2.8412282383075363e-05,
|
| 239 |
+
"loss": 0.2479,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.11459386585776879,
|
| 244 |
+
"grad_norm": 1.5858228206634521,
|
| 245 |
+
"learning_rate": 2.547882480847461e-05,
|
| 246 |
+
"loss": 0.2569,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.11796427367711493,
|
| 251 |
+
"grad_norm": 0.6920508742332458,
|
| 252 |
+
"learning_rate": 2.2652592093878666e-05,
|
| 253 |
+
"loss": 0.2354,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.12133468149646107,
|
| 258 |
+
"grad_norm": 0.9595134258270264,
|
| 259 |
+
"learning_rate": 1.9945942635848748e-05,
|
| 260 |
+
"loss": 0.2104,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.12470508931580722,
|
| 265 |
+
"grad_norm": 0.80647873878479,
|
| 266 |
+
"learning_rate": 1.7370711923791567e-05,
|
| 267 |
+
"loss": 0.2296,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.12807549713515334,
|
| 272 |
+
"grad_norm": 1.2443121671676636,
|
| 273 |
+
"learning_rate": 1.4938160786375572e-05,
|
| 274 |
+
"loss": 0.2175,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.13144590495449948,
|
| 279 |
+
"grad_norm": 1.084061861038208,
|
| 280 |
+
"learning_rate": 1.2658926150792322e-05,
|
| 281 |
+
"loss": 0.3018,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.13481631277384565,
|
| 286 |
+
"grad_norm": 1.718507170677185,
|
| 287 |
+
"learning_rate": 1.0542974530180327e-05,
|
| 288 |
+
"loss": 0.2336,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.1381867205931918,
|
| 293 |
+
"grad_norm": 1.6592141389846802,
|
| 294 |
+
"learning_rate": 8.599558442598998e-06,
|
| 295 |
+
"loss": 0.2068,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.14155712841253792,
|
| 300 |
+
"grad_norm": 0.9472789764404297,
|
| 301 |
+
"learning_rate": 6.837175952121306e-06,
|
| 302 |
+
"loss": 0.2019,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.14492753623188406,
|
| 307 |
+
"grad_norm": 0.6342177987098694,
|
| 308 |
+
"learning_rate": 5.263533508961827e-06,
|
| 309 |
+
"loss": 0.207,
|
| 310 |
+
"step": 430
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.1482979440512302,
|
| 314 |
+
"grad_norm": 1.4079145193099976,
|
| 315 |
+
"learning_rate": 3.885512251130763e-06,
|
| 316 |
+
"loss": 0.2979,
|
| 317 |
+
"step": 440
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.15166835187057634,
|
| 321 |
+
"grad_norm": 1.145531415939331,
|
| 322 |
+
"learning_rate": 2.7091379149682685e-06,
|
| 323 |
+
"loss": 0.195,
|
| 324 |
+
"step": 450
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.15503875968992248,
|
| 328 |
+
"grad_norm": 1.4974510669708252,
|
| 329 |
+
"learning_rate": 1.7395544861325718e-06,
|
| 330 |
+
"loss": 0.2252,
|
| 331 |
+
"step": 460
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.15840916750926862,
|
| 335 |
+
"grad_norm": 1.1619243621826172,
|
| 336 |
+
"learning_rate": 9.810017062595322e-07,
|
| 337 |
+
"loss": 0.2068,
|
| 338 |
+
"step": 470
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.16177957532861476,
|
| 342 |
+
"grad_norm": 0.5374842286109924,
|
| 343 |
+
"learning_rate": 4.367965336512403e-07,
|
| 344 |
+
"loss": 0.2431,
|
| 345 |
+
"step": 480
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.1651499831479609,
|
| 349 |
+
"grad_norm": 1.352457880973816,
|
| 350 |
+
"learning_rate": 1.0931863906127327e-07,
|
| 351 |
+
"loss": 0.2363,
|
| 352 |
+
"step": 490
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.16852039096730703,
|
| 356 |
+
"grad_norm": 1.1476552486419678,
|
| 357 |
+
"learning_rate": 0.0,
|
| 358 |
+
"loss": 0.1907,
|
| 359 |
+
"step": 500
|
| 360 |
+
}
|
| 361 |
+
],
|
| 362 |
+
"logging_steps": 10,
|
| 363 |
+
"max_steps": 500,
|
| 364 |
+
"num_input_tokens_seen": 0,
|
| 365 |
+
"num_train_epochs": 1,
|
| 366 |
+
"save_steps": 500,
|
| 367 |
+
"stateful_callbacks": {
|
| 368 |
+
"TrainerControl": {
|
| 369 |
+
"args": {
|
| 370 |
+
"should_epoch_stop": false,
|
| 371 |
+
"should_evaluate": false,
|
| 372 |
+
"should_log": false,
|
| 373 |
+
"should_save": true,
|
| 374 |
+
"should_training_stop": true
|
| 375 |
+
},
|
| 376 |
+
"attributes": {}
|
| 377 |
+
}
|
| 378 |
+
},
|
| 379 |
+
"total_flos": 6303999518208000.0,
|
| 380 |
+
"train_batch_size": 4,
|
| 381 |
+
"trial_name": null,
|
| 382 |
+
"trial_params": null
|
| 383 |
+
}
|