Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes. See raw diff
- checkpoints/010000/pretrained_model/config.json +101 -0
- checkpoints/010000/pretrained_model/model.safetensors +3 -0
- checkpoints/010000/pretrained_model/policy_postprocessor.json +32 -0
- checkpoints/010000/pretrained_model/policy_postprocessor_step_0_unnormalizer_processor.safetensors +3 -0
- checkpoints/010000/pretrained_model/policy_preprocessor.json +87 -0
- checkpoints/010000/pretrained_model/policy_preprocessor_step_5_normalizer_processor.safetensors +3 -0
- checkpoints/010000/pretrained_model/train_config.json +239 -0
- checkpoints/010000/training_state/optimizer_param_groups.json +521 -0
- checkpoints/010000/training_state/optimizer_state.safetensors +3 -0
- checkpoints/010000/training_state/rng_state.safetensors +3 -0
- checkpoints/010000/training_state/scheduler_state.json +15 -0
- checkpoints/010000/training_state/training_step.json +3 -0
- checkpoints/020000/pretrained_model/config.json +101 -0
- checkpoints/020000/pretrained_model/model.safetensors +3 -0
- checkpoints/020000/pretrained_model/policy_postprocessor.json +32 -0
- checkpoints/020000/pretrained_model/policy_postprocessor_step_0_unnormalizer_processor.safetensors +3 -0
- checkpoints/020000/pretrained_model/policy_preprocessor.json +87 -0
- checkpoints/020000/pretrained_model/policy_preprocessor_step_5_normalizer_processor.safetensors +3 -0
- checkpoints/020000/pretrained_model/train_config.json +239 -0
- checkpoints/020000/training_state/optimizer_param_groups.json +521 -0
- checkpoints/020000/training_state/optimizer_state.safetensors +3 -0
- checkpoints/020000/training_state/rng_state.safetensors +3 -0
- checkpoints/020000/training_state/scheduler_state.json +15 -0
- checkpoints/020000/training_state/training_step.json +3 -0
- checkpoints/030000/pretrained_model/config.json +101 -0
- checkpoints/030000/pretrained_model/model.safetensors +3 -0
- checkpoints/030000/pretrained_model/policy_postprocessor.json +32 -0
- checkpoints/030000/pretrained_model/policy_postprocessor_step_0_unnormalizer_processor.safetensors +3 -0
- checkpoints/030000/pretrained_model/policy_preprocessor.json +87 -0
- checkpoints/030000/pretrained_model/policy_preprocessor_step_5_normalizer_processor.safetensors +3 -0
- checkpoints/030000/pretrained_model/train_config.json +239 -0
- checkpoints/030000/training_state/optimizer_param_groups.json +521 -0
- checkpoints/030000/training_state/optimizer_state.safetensors +3 -0
- checkpoints/030000/training_state/rng_state.safetensors +3 -0
- checkpoints/030000/training_state/scheduler_state.json +15 -0
- checkpoints/030000/training_state/training_step.json +3 -0
- checkpoints/040000/pretrained_model/config.json +101 -0
- checkpoints/040000/pretrained_model/model.safetensors +3 -0
- checkpoints/040000/pretrained_model/policy_postprocessor.json +32 -0
- checkpoints/040000/pretrained_model/policy_postprocessor_step_0_unnormalizer_processor.safetensors +3 -0
- checkpoints/040000/pretrained_model/policy_preprocessor.json +87 -0
- checkpoints/040000/pretrained_model/policy_preprocessor_step_5_normalizer_processor.safetensors +3 -0
- checkpoints/040000/pretrained_model/train_config.json +239 -0
- checkpoints/040000/training_state/optimizer_param_groups.json +521 -0
- checkpoints/040000/training_state/optimizer_state.safetensors +3 -0
- checkpoints/040000/training_state/rng_state.safetensors +3 -0
- checkpoints/040000/training_state/scheduler_state.json +15 -0
- checkpoints/040000/training_state/training_step.json +3 -0
- checkpoints/050000/pretrained_model/config.json +101 -0
- checkpoints/050000/pretrained_model/model.safetensors +3 -0
checkpoints/010000/pretrained_model/config.json
ADDED
|
@@ -0,0 +1,101 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"type": "smolvla",
|
| 3 |
+
"n_obs_steps": 1,
|
| 4 |
+
"input_features": {
|
| 5 |
+
"observation.state": {
|
| 6 |
+
"type": "STATE",
|
| 7 |
+
"shape": [
|
| 8 |
+
6
|
| 9 |
+
]
|
| 10 |
+
},
|
| 11 |
+
"observation.images.camera1": {
|
| 12 |
+
"type": "VISUAL",
|
| 13 |
+
"shape": [
|
| 14 |
+
3,
|
| 15 |
+
256,
|
| 16 |
+
256
|
| 17 |
+
]
|
| 18 |
+
},
|
| 19 |
+
"observation.images.camera2": {
|
| 20 |
+
"type": "VISUAL",
|
| 21 |
+
"shape": [
|
| 22 |
+
3,
|
| 23 |
+
256,
|
| 24 |
+
256
|
| 25 |
+
]
|
| 26 |
+
},
|
| 27 |
+
"observation.images.camera3": {
|
| 28 |
+
"type": "VISUAL",
|
| 29 |
+
"shape": [
|
| 30 |
+
3,
|
| 31 |
+
256,
|
| 32 |
+
256
|
| 33 |
+
]
|
| 34 |
+
}
|
| 35 |
+
},
|
| 36 |
+
"output_features": {
|
| 37 |
+
"action": {
|
| 38 |
+
"type": "ACTION",
|
| 39 |
+
"shape": [
|
| 40 |
+
6
|
| 41 |
+
]
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"device": "cuda",
|
| 45 |
+
"use_amp": false,
|
| 46 |
+
"use_peft": false,
|
| 47 |
+
"push_to_hub": true,
|
| 48 |
+
"repo_id": "BrandonAL/my_sim_smolvla_all_ft60k",
|
| 49 |
+
"private": null,
|
| 50 |
+
"tags": null,
|
| 51 |
+
"license": null,
|
| 52 |
+
"pretrained_path": "BrandonAL/my_sim_smolvla_all_step010000",
|
| 53 |
+
"chunk_size": 50,
|
| 54 |
+
"n_action_steps": 50,
|
| 55 |
+
"normalization_mapping": {
|
| 56 |
+
"VISUAL": "IDENTITY",
|
| 57 |
+
"STATE": "MEAN_STD",
|
| 58 |
+
"ACTION": "MEAN_STD"
|
| 59 |
+
},
|
| 60 |
+
"max_state_dim": 32,
|
| 61 |
+
"max_action_dim": 32,
|
| 62 |
+
"resize_imgs_with_padding": [
|
| 63 |
+
512,
|
| 64 |
+
512
|
| 65 |
+
],
|
| 66 |
+
"empty_cameras": 0,
|
| 67 |
+
"adapt_to_pi_aloha": false,
|
| 68 |
+
"use_delta_joint_actions_aloha": false,
|
| 69 |
+
"tokenizer_max_length": 48,
|
| 70 |
+
"num_steps": 10,
|
| 71 |
+
"use_cache": true,
|
| 72 |
+
"freeze_vision_encoder": true,
|
| 73 |
+
"train_expert_only": true,
|
| 74 |
+
"train_state_proj": true,
|
| 75 |
+
"optimizer_lr": 0.0001,
|
| 76 |
+
"optimizer_betas": [
|
| 77 |
+
0.9,
|
| 78 |
+
0.95
|
| 79 |
+
],
|
| 80 |
+
"optimizer_eps": 1e-08,
|
| 81 |
+
"optimizer_weight_decay": 1e-10,
|
| 82 |
+
"optimizer_grad_clip_norm": 10.0,
|
| 83 |
+
"scheduler_warmup_steps": 1000,
|
| 84 |
+
"scheduler_decay_steps": 30000,
|
| 85 |
+
"scheduler_decay_lr": 2.5e-06,
|
| 86 |
+
"vlm_model_name": "HuggingFaceTB/SmolVLM2-500M-Video-Instruct",
|
| 87 |
+
"load_vlm_weights": true,
|
| 88 |
+
"add_image_special_tokens": false,
|
| 89 |
+
"attention_mode": "cross_attn",
|
| 90 |
+
"prefix_length": 0,
|
| 91 |
+
"pad_language_to": "max_length",
|
| 92 |
+
"num_expert_layers": 0,
|
| 93 |
+
"num_vlm_layers": 16,
|
| 94 |
+
"self_attn_every_n_layers": 2,
|
| 95 |
+
"expert_width_multiplier": 0.75,
|
| 96 |
+
"min_period": 0.004,
|
| 97 |
+
"max_period": 4.0,
|
| 98 |
+
"rtc_config": null,
|
| 99 |
+
"compile_model": false,
|
| 100 |
+
"compile_mode": "max-autotune"
|
| 101 |
+
}
|
checkpoints/010000/pretrained_model/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:418599bcb9347ecb780a94cad6ebdb5284c38987372854efd4ef94ec5ba4d897
|
| 3 |
+
size 906712520
|
checkpoints/010000/pretrained_model/policy_postprocessor.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"name": "policy_postprocessor",
|
| 3 |
+
"steps": [
|
| 4 |
+
{
|
| 5 |
+
"registry_name": "unnormalizer_processor",
|
| 6 |
+
"config": {
|
| 7 |
+
"eps": 1e-08,
|
| 8 |
+
"features": {
|
| 9 |
+
"action": {
|
| 10 |
+
"type": "ACTION",
|
| 11 |
+
"shape": [
|
| 12 |
+
6
|
| 13 |
+
]
|
| 14 |
+
}
|
| 15 |
+
},
|
| 16 |
+
"norm_map": {
|
| 17 |
+
"VISUAL": "IDENTITY",
|
| 18 |
+
"STATE": "MEAN_STD",
|
| 19 |
+
"ACTION": "MEAN_STD"
|
| 20 |
+
}
|
| 21 |
+
},
|
| 22 |
+
"state_file": "policy_postprocessor_step_0_unnormalizer_processor.safetensors"
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"registry_name": "device_processor",
|
| 26 |
+
"config": {
|
| 27 |
+
"device": "cpu",
|
| 28 |
+
"float_dtype": null
|
| 29 |
+
}
|
| 30 |
+
}
|
| 31 |
+
]
|
| 32 |
+
}
|
checkpoints/010000/pretrained_model/policy_postprocessor_step_0_unnormalizer_processor.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7e560b7d5832bf20dfaa2db407540e3042344409d4fce910831109e0e74e7368
|
| 3 |
+
size 7592
|
checkpoints/010000/pretrained_model/policy_preprocessor.json
ADDED
|
@@ -0,0 +1,87 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"name": "policy_preprocessor",
|
| 3 |
+
"steps": [
|
| 4 |
+
{
|
| 5 |
+
"registry_name": "rename_observations_processor",
|
| 6 |
+
"config": {
|
| 7 |
+
"rename_map": {}
|
| 8 |
+
}
|
| 9 |
+
},
|
| 10 |
+
{
|
| 11 |
+
"registry_name": "to_batch_processor",
|
| 12 |
+
"config": {}
|
| 13 |
+
},
|
| 14 |
+
{
|
| 15 |
+
"registry_name": "smolvla_new_line_processor",
|
| 16 |
+
"config": {}
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"registry_name": "tokenizer_processor",
|
| 20 |
+
"config": {
|
| 21 |
+
"max_length": 48,
|
| 22 |
+
"task_key": "task",
|
| 23 |
+
"padding_side": "right",
|
| 24 |
+
"padding": "max_length",
|
| 25 |
+
"truncation": true,
|
| 26 |
+
"tokenizer_name": "HuggingFaceTB/SmolVLM2-500M-Video-Instruct"
|
| 27 |
+
}
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"registry_name": "device_processor",
|
| 31 |
+
"config": {
|
| 32 |
+
"device": "cuda",
|
| 33 |
+
"float_dtype": null
|
| 34 |
+
}
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"registry_name": "normalizer_processor",
|
| 38 |
+
"config": {
|
| 39 |
+
"eps": 1e-08,
|
| 40 |
+
"features": {
|
| 41 |
+
"observation.state": {
|
| 42 |
+
"type": "STATE",
|
| 43 |
+
"shape": [
|
| 44 |
+
6
|
| 45 |
+
]
|
| 46 |
+
},
|
| 47 |
+
"observation.images.camera1": {
|
| 48 |
+
"type": "VISUAL",
|
| 49 |
+
"shape": [
|
| 50 |
+
3,
|
| 51 |
+
256,
|
| 52 |
+
256
|
| 53 |
+
]
|
| 54 |
+
},
|
| 55 |
+
"observation.images.camera2": {
|
| 56 |
+
"type": "VISUAL",
|
| 57 |
+
"shape": [
|
| 58 |
+
3,
|
| 59 |
+
256,
|
| 60 |
+
256
|
| 61 |
+
]
|
| 62 |
+
},
|
| 63 |
+
"observation.images.camera3": {
|
| 64 |
+
"type": "VISUAL",
|
| 65 |
+
"shape": [
|
| 66 |
+
3,
|
| 67 |
+
256,
|
| 68 |
+
256
|
| 69 |
+
]
|
| 70 |
+
},
|
| 71 |
+
"action": {
|
| 72 |
+
"type": "ACTION",
|
| 73 |
+
"shape": [
|
| 74 |
+
6
|
| 75 |
+
]
|
| 76 |
+
}
|
| 77 |
+
},
|
| 78 |
+
"norm_map": {
|
| 79 |
+
"VISUAL": "IDENTITY",
|
| 80 |
+
"STATE": "MEAN_STD",
|
| 81 |
+
"ACTION": "MEAN_STD"
|
| 82 |
+
}
|
| 83 |
+
},
|
| 84 |
+
"state_file": "policy_preprocessor_step_5_normalizer_processor.safetensors"
|
| 85 |
+
}
|
| 86 |
+
]
|
| 87 |
+
}
|
checkpoints/010000/pretrained_model/policy_preprocessor_step_5_normalizer_processor.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7e560b7d5832bf20dfaa2db407540e3042344409d4fce910831109e0e74e7368
|
| 3 |
+
size 7592
|
checkpoints/010000/pretrained_model/train_config.json
ADDED
|
@@ -0,0 +1,239 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"dataset": {
|
| 3 |
+
"repo_id": "BrandonAL/my_sim_merged",
|
| 4 |
+
"root": null,
|
| 5 |
+
"episodes": null,
|
| 6 |
+
"image_transforms": {
|
| 7 |
+
"enable": true,
|
| 8 |
+
"max_num_transforms": 3,
|
| 9 |
+
"random_order": false,
|
| 10 |
+
"tfs": {
|
| 11 |
+
"brightness": {
|
| 12 |
+
"weight": 1.0,
|
| 13 |
+
"type": "ColorJitter",
|
| 14 |
+
"kwargs": {
|
| 15 |
+
"brightness": [
|
| 16 |
+
0.8,
|
| 17 |
+
1.2
|
| 18 |
+
]
|
| 19 |
+
}
|
| 20 |
+
},
|
| 21 |
+
"contrast": {
|
| 22 |
+
"weight": 1.0,
|
| 23 |
+
"type": "ColorJitter",
|
| 24 |
+
"kwargs": {
|
| 25 |
+
"contrast": [
|
| 26 |
+
0.8,
|
| 27 |
+
1.2
|
| 28 |
+
]
|
| 29 |
+
}
|
| 30 |
+
},
|
| 31 |
+
"saturation": {
|
| 32 |
+
"weight": 1.0,
|
| 33 |
+
"type": "ColorJitter",
|
| 34 |
+
"kwargs": {
|
| 35 |
+
"saturation": [
|
| 36 |
+
0.5,
|
| 37 |
+
1.5
|
| 38 |
+
]
|
| 39 |
+
}
|
| 40 |
+
},
|
| 41 |
+
"hue": {
|
| 42 |
+
"weight": 1.0,
|
| 43 |
+
"type": "ColorJitter",
|
| 44 |
+
"kwargs": {
|
| 45 |
+
"hue": [
|
| 46 |
+
-0.05,
|
| 47 |
+
0.05
|
| 48 |
+
]
|
| 49 |
+
}
|
| 50 |
+
},
|
| 51 |
+
"sharpness": {
|
| 52 |
+
"weight": 1.0,
|
| 53 |
+
"type": "SharpnessJitter",
|
| 54 |
+
"kwargs": {
|
| 55 |
+
"sharpness": [
|
| 56 |
+
0.5,
|
| 57 |
+
1.5
|
| 58 |
+
]
|
| 59 |
+
}
|
| 60 |
+
},
|
| 61 |
+
"affine": {
|
| 62 |
+
"weight": 1.0,
|
| 63 |
+
"type": "RandomAffine",
|
| 64 |
+
"kwargs": {
|
| 65 |
+
"degrees": [
|
| 66 |
+
-5.0,
|
| 67 |
+
5.0
|
| 68 |
+
],
|
| 69 |
+
"translate": [
|
| 70 |
+
0.05,
|
| 71 |
+
0.05
|
| 72 |
+
]
|
| 73 |
+
}
|
| 74 |
+
}
|
| 75 |
+
}
|
| 76 |
+
},
|
| 77 |
+
"revision": null,
|
| 78 |
+
"use_imagenet_stats": true,
|
| 79 |
+
"video_backend": "pyav",
|
| 80 |
+
"streaming": false
|
| 81 |
+
},
|
| 82 |
+
"env": null,
|
| 83 |
+
"policy": {
|
| 84 |
+
"type": "smolvla",
|
| 85 |
+
"n_obs_steps": 1,
|
| 86 |
+
"input_features": {
|
| 87 |
+
"observation.state": {
|
| 88 |
+
"type": "STATE",
|
| 89 |
+
"shape": [
|
| 90 |
+
6
|
| 91 |
+
]
|
| 92 |
+
},
|
| 93 |
+
"observation.images.camera1": {
|
| 94 |
+
"type": "VISUAL",
|
| 95 |
+
"shape": [
|
| 96 |
+
3,
|
| 97 |
+
256,
|
| 98 |
+
256
|
| 99 |
+
]
|
| 100 |
+
},
|
| 101 |
+
"observation.images.camera2": {
|
| 102 |
+
"type": "VISUAL",
|
| 103 |
+
"shape": [
|
| 104 |
+
3,
|
| 105 |
+
256,
|
| 106 |
+
256
|
| 107 |
+
]
|
| 108 |
+
},
|
| 109 |
+
"observation.images.camera3": {
|
| 110 |
+
"type": "VISUAL",
|
| 111 |
+
"shape": [
|
| 112 |
+
3,
|
| 113 |
+
256,
|
| 114 |
+
256
|
| 115 |
+
]
|
| 116 |
+
}
|
| 117 |
+
},
|
| 118 |
+
"output_features": {
|
| 119 |
+
"action": {
|
| 120 |
+
"type": "ACTION",
|
| 121 |
+
"shape": [
|
| 122 |
+
6
|
| 123 |
+
]
|
| 124 |
+
}
|
| 125 |
+
},
|
| 126 |
+
"device": "cuda",
|
| 127 |
+
"use_amp": false,
|
| 128 |
+
"use_peft": false,
|
| 129 |
+
"push_to_hub": true,
|
| 130 |
+
"repo_id": "BrandonAL/my_sim_smolvla_all_ft60k",
|
| 131 |
+
"private": null,
|
| 132 |
+
"tags": null,
|
| 133 |
+
"license": null,
|
| 134 |
+
"pretrained_path": "BrandonAL/my_sim_smolvla_all_step010000",
|
| 135 |
+
"chunk_size": 50,
|
| 136 |
+
"n_action_steps": 50,
|
| 137 |
+
"normalization_mapping": {
|
| 138 |
+
"VISUAL": "IDENTITY",
|
| 139 |
+
"STATE": "MEAN_STD",
|
| 140 |
+
"ACTION": "MEAN_STD"
|
| 141 |
+
},
|
| 142 |
+
"max_state_dim": 32,
|
| 143 |
+
"max_action_dim": 32,
|
| 144 |
+
"resize_imgs_with_padding": [
|
| 145 |
+
512,
|
| 146 |
+
512
|
| 147 |
+
],
|
| 148 |
+
"empty_cameras": 0,
|
| 149 |
+
"adapt_to_pi_aloha": false,
|
| 150 |
+
"use_delta_joint_actions_aloha": false,
|
| 151 |
+
"tokenizer_max_length": 48,
|
| 152 |
+
"num_steps": 10,
|
| 153 |
+
"use_cache": true,
|
| 154 |
+
"freeze_vision_encoder": true,
|
| 155 |
+
"train_expert_only": true,
|
| 156 |
+
"train_state_proj": true,
|
| 157 |
+
"optimizer_lr": 0.0001,
|
| 158 |
+
"optimizer_betas": [
|
| 159 |
+
0.9,
|
| 160 |
+
0.95
|
| 161 |
+
],
|
| 162 |
+
"optimizer_eps": 1e-08,
|
| 163 |
+
"optimizer_weight_decay": 1e-10,
|
| 164 |
+
"optimizer_grad_clip_norm": 10.0,
|
| 165 |
+
"scheduler_warmup_steps": 1000,
|
| 166 |
+
"scheduler_decay_steps": 30000,
|
| 167 |
+
"scheduler_decay_lr": 2.5e-06,
|
| 168 |
+
"vlm_model_name": "HuggingFaceTB/SmolVLM2-500M-Video-Instruct",
|
| 169 |
+
"load_vlm_weights": true,
|
| 170 |
+
"add_image_special_tokens": false,
|
| 171 |
+
"attention_mode": "cross_attn",
|
| 172 |
+
"prefix_length": 0,
|
| 173 |
+
"pad_language_to": "max_length",
|
| 174 |
+
"num_expert_layers": 0,
|
| 175 |
+
"num_vlm_layers": 16,
|
| 176 |
+
"self_attn_every_n_layers": 2,
|
| 177 |
+
"expert_width_multiplier": 0.75,
|
| 178 |
+
"min_period": 0.004,
|
| 179 |
+
"max_period": 4.0,
|
| 180 |
+
"rtc_config": null,
|
| 181 |
+
"compile_model": false,
|
| 182 |
+
"compile_mode": "max-autotune"
|
| 183 |
+
},
|
| 184 |
+
"output_dir": "outputs/train/my_sim_smolvla_all_ft60k",
|
| 185 |
+
"job_name": "my_smolvla_all_ft60k",
|
| 186 |
+
"resume": false,
|
| 187 |
+
"seed": 1000,
|
| 188 |
+
"cudnn_deterministic": false,
|
| 189 |
+
"num_workers": 4,
|
| 190 |
+
"batch_size": 64,
|
| 191 |
+
"steps": 50000,
|
| 192 |
+
"eval_freq": 20000,
|
| 193 |
+
"log_freq": 200,
|
| 194 |
+
"tolerance_s": 0.0001,
|
| 195 |
+
"save_checkpoint": true,
|
| 196 |
+
"save_freq": 10000,
|
| 197 |
+
"use_policy_training_preset": true,
|
| 198 |
+
"optimizer": {
|
| 199 |
+
"type": "adamw",
|
| 200 |
+
"lr": 0.0001,
|
| 201 |
+
"weight_decay": 1e-10,
|
| 202 |
+
"grad_clip_norm": 10.0,
|
| 203 |
+
"betas": [
|
| 204 |
+
0.9,
|
| 205 |
+
0.95
|
| 206 |
+
],
|
| 207 |
+
"eps": 1e-08
|
| 208 |
+
},
|
| 209 |
+
"scheduler": {
|
| 210 |
+
"type": "cosine_decay_with_warmup",
|
| 211 |
+
"num_warmup_steps": 1000,
|
| 212 |
+
"num_decay_steps": 30000,
|
| 213 |
+
"peak_lr": 0.0001,
|
| 214 |
+
"decay_lr": 2.5e-06
|
| 215 |
+
},
|
| 216 |
+
"eval": {
|
| 217 |
+
"n_episodes": 50,
|
| 218 |
+
"batch_size": 44,
|
| 219 |
+
"use_async_envs": true
|
| 220 |
+
},
|
| 221 |
+
"wandb": {
|
| 222 |
+
"enable": false,
|
| 223 |
+
"disable_artifact": false,
|
| 224 |
+
"project": "lerobot",
|
| 225 |
+
"entity": null,
|
| 226 |
+
"notes": null,
|
| 227 |
+
"run_id": null,
|
| 228 |
+
"mode": null,
|
| 229 |
+
"add_tags": true
|
| 230 |
+
},
|
| 231 |
+
"peft": null,
|
| 232 |
+
"use_rabc": false,
|
| 233 |
+
"rabc_progress_path": null,
|
| 234 |
+
"rabc_kappa": 0.01,
|
| 235 |
+
"rabc_epsilon": 1e-06,
|
| 236 |
+
"rabc_head_mode": "sparse",
|
| 237 |
+
"rename_map": {},
|
| 238 |
+
"checkpoint_path": null
|
| 239 |
+
}
|
checkpoints/010000/training_state/optimizer_param_groups.json
ADDED
|
@@ -0,0 +1,521 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[
|
| 2 |
+
{
|
| 3 |
+
"lr": 7.5625e-05,
|
| 4 |
+
"betas": [
|
| 5 |
+
0.9,
|
| 6 |
+
0.95
|
| 7 |
+
],
|
| 8 |
+
"eps": 1e-08,
|
| 9 |
+
"weight_decay": 1e-10,
|
| 10 |
+
"amsgrad": false,
|
| 11 |
+
"maximize": false,
|
| 12 |
+
"foreach": null,
|
| 13 |
+
"capturable": false,
|
| 14 |
+
"differentiable": false,
|
| 15 |
+
"fused": null,
|
| 16 |
+
"decoupled_weight_decay": true,
|
| 17 |
+
"initial_lr": 0.0001,
|
| 18 |
+
"params": [
|
| 19 |
+
0,
|
| 20 |
+
1,
|
| 21 |
+
2,
|
| 22 |
+
3,
|
| 23 |
+
4,
|
| 24 |
+
5,
|
| 25 |
+
6,
|
| 26 |
+
7,
|
| 27 |
+
8,
|
| 28 |
+
9,
|
| 29 |
+
10,
|
| 30 |
+
11,
|
| 31 |
+
12,
|
| 32 |
+
13,
|
| 33 |
+
14,
|
| 34 |
+
15,
|
| 35 |
+
16,
|
| 36 |
+
17,
|
| 37 |
+
18,
|
| 38 |
+
19,
|
| 39 |
+
20,
|
| 40 |
+
21,
|
| 41 |
+
22,
|
| 42 |
+
23,
|
| 43 |
+
24,
|
| 44 |
+
25,
|
| 45 |
+
26,
|
| 46 |
+
27,
|
| 47 |
+
28,
|
| 48 |
+
29,
|
| 49 |
+
30,
|
| 50 |
+
31,
|
| 51 |
+
32,
|
| 52 |
+
33,
|
| 53 |
+
34,
|
| 54 |
+
35,
|
| 55 |
+
36,
|
| 56 |
+
37,
|
| 57 |
+
38,
|
| 58 |
+
39,
|
| 59 |
+
40,
|
| 60 |
+
41,
|
| 61 |
+
42,
|
| 62 |
+
43,
|
| 63 |
+
44,
|
| 64 |
+
45,
|
| 65 |
+
46,
|
| 66 |
+
47,
|
| 67 |
+
48,
|
| 68 |
+
49,
|
| 69 |
+
50,
|
| 70 |
+
51,
|
| 71 |
+
52,
|
| 72 |
+
53,
|
| 73 |
+
54,
|
| 74 |
+
55,
|
| 75 |
+
56,
|
| 76 |
+
57,
|
| 77 |
+
58,
|
| 78 |
+
59,
|
| 79 |
+
60,
|
| 80 |
+
61,
|
| 81 |
+
62,
|
| 82 |
+
63,
|
| 83 |
+
64,
|
| 84 |
+
65,
|
| 85 |
+
66,
|
| 86 |
+
67,
|
| 87 |
+
68,
|
| 88 |
+
69,
|
| 89 |
+
70,
|
| 90 |
+
71,
|
| 91 |
+
72,
|
| 92 |
+
73,
|
| 93 |
+
74,
|
| 94 |
+
75,
|
| 95 |
+
76,
|
| 96 |
+
77,
|
| 97 |
+
78,
|
| 98 |
+
79,
|
| 99 |
+
80,
|
| 100 |
+
81,
|
| 101 |
+
82,
|
| 102 |
+
83,
|
| 103 |
+
84,
|
| 104 |
+
85,
|
| 105 |
+
86,
|
| 106 |
+
87,
|
| 107 |
+
88,
|
| 108 |
+
89,
|
| 109 |
+
90,
|
| 110 |
+
91,
|
| 111 |
+
92,
|
| 112 |
+
93,
|
| 113 |
+
94,
|
| 114 |
+
95,
|
| 115 |
+
96,
|
| 116 |
+
97,
|
| 117 |
+
98,
|
| 118 |
+
99,
|
| 119 |
+
100,
|
| 120 |
+
101,
|
| 121 |
+
102,
|
| 122 |
+
103,
|
| 123 |
+
104,
|
| 124 |
+
105,
|
| 125 |
+
106,
|
| 126 |
+
107,
|
| 127 |
+
108,
|
| 128 |
+
109,
|
| 129 |
+
110,
|
| 130 |
+
111,
|
| 131 |
+
112,
|
| 132 |
+
113,
|
| 133 |
+
114,
|
| 134 |
+
115,
|
| 135 |
+
116,
|
| 136 |
+
117,
|
| 137 |
+
118,
|
| 138 |
+
119,
|
| 139 |
+
120,
|
| 140 |
+
121,
|
| 141 |
+
122,
|
| 142 |
+
123,
|
| 143 |
+
124,
|
| 144 |
+
125,
|
| 145 |
+
126,
|
| 146 |
+
127,
|
| 147 |
+
128,
|
| 148 |
+
129,
|
| 149 |
+
130,
|
| 150 |
+
131,
|
| 151 |
+
132,
|
| 152 |
+
133,
|
| 153 |
+
134,
|
| 154 |
+
135,
|
| 155 |
+
136,
|
| 156 |
+
137,
|
| 157 |
+
138,
|
| 158 |
+
139,
|
| 159 |
+
140,
|
| 160 |
+
141,
|
| 161 |
+
142,
|
| 162 |
+
143,
|
| 163 |
+
144,
|
| 164 |
+
145,
|
| 165 |
+
146,
|
| 166 |
+
147,
|
| 167 |
+
148,
|
| 168 |
+
149,
|
| 169 |
+
150,
|
| 170 |
+
151,
|
| 171 |
+
152,
|
| 172 |
+
153,
|
| 173 |
+
154,
|
| 174 |
+
155,
|
| 175 |
+
156,
|
| 176 |
+
157,
|
| 177 |
+
158,
|
| 178 |
+
159,
|
| 179 |
+
160,
|
| 180 |
+
161,
|
| 181 |
+
162,
|
| 182 |
+
163,
|
| 183 |
+
164,
|
| 184 |
+
165,
|
| 185 |
+
166,
|
| 186 |
+
167,
|
| 187 |
+
168,
|
| 188 |
+
169,
|
| 189 |
+
170,
|
| 190 |
+
171,
|
| 191 |
+
172,
|
| 192 |
+
173,
|
| 193 |
+
174,
|
| 194 |
+
175,
|
| 195 |
+
176,
|
| 196 |
+
177,
|
| 197 |
+
178,
|
| 198 |
+
179,
|
| 199 |
+
180,
|
| 200 |
+
181,
|
| 201 |
+
182,
|
| 202 |
+
183,
|
| 203 |
+
184,
|
| 204 |
+
185,
|
| 205 |
+
186,
|
| 206 |
+
187,
|
| 207 |
+
188,
|
| 208 |
+
189,
|
| 209 |
+
190,
|
| 210 |
+
191,
|
| 211 |
+
192,
|
| 212 |
+
193,
|
| 213 |
+
194,
|
| 214 |
+
195,
|
| 215 |
+
196,
|
| 216 |
+
197,
|
| 217 |
+
198,
|
| 218 |
+
199,
|
| 219 |
+
200,
|
| 220 |
+
201,
|
| 221 |
+
202,
|
| 222 |
+
203,
|
| 223 |
+
204,
|
| 224 |
+
205,
|
| 225 |
+
206,
|
| 226 |
+
207,
|
| 227 |
+
208,
|
| 228 |
+
209,
|
| 229 |
+
210,
|
| 230 |
+
211,
|
| 231 |
+
212,
|
| 232 |
+
213,
|
| 233 |
+
214,
|
| 234 |
+
215,
|
| 235 |
+
216,
|
| 236 |
+
217,
|
| 237 |
+
218,
|
| 238 |
+
219,
|
| 239 |
+
220,
|
| 240 |
+
221,
|
| 241 |
+
222,
|
| 242 |
+
223,
|
| 243 |
+
224,
|
| 244 |
+
225,
|
| 245 |
+
226,
|
| 246 |
+
227,
|
| 247 |
+
228,
|
| 248 |
+
229,
|
| 249 |
+
230,
|
| 250 |
+
231,
|
| 251 |
+
232,
|
| 252 |
+
233,
|
| 253 |
+
234,
|
| 254 |
+
235,
|
| 255 |
+
236,
|
| 256 |
+
237,
|
| 257 |
+
238,
|
| 258 |
+
239,
|
| 259 |
+
240,
|
| 260 |
+
241,
|
| 261 |
+
242,
|
| 262 |
+
243,
|
| 263 |
+
244,
|
| 264 |
+
245,
|
| 265 |
+
246,
|
| 266 |
+
247,
|
| 267 |
+
248,
|
| 268 |
+
249,
|
| 269 |
+
250,
|
| 270 |
+
251,
|
| 271 |
+
252,
|
| 272 |
+
253,
|
| 273 |
+
254,
|
| 274 |
+
255,
|
| 275 |
+
256,
|
| 276 |
+
257,
|
| 277 |
+
258,
|
| 278 |
+
259,
|
| 279 |
+
260,
|
| 280 |
+
261,
|
| 281 |
+
262,
|
| 282 |
+
263,
|
| 283 |
+
264,
|
| 284 |
+
265,
|
| 285 |
+
266,
|
| 286 |
+
267,
|
| 287 |
+
268,
|
| 288 |
+
269,
|
| 289 |
+
270,
|
| 290 |
+
271,
|
| 291 |
+
272,
|
| 292 |
+
273,
|
| 293 |
+
274,
|
| 294 |
+
275,
|
| 295 |
+
276,
|
| 296 |
+
277,
|
| 297 |
+
278,
|
| 298 |
+
279,
|
| 299 |
+
280,
|
| 300 |
+
281,
|
| 301 |
+
282,
|
| 302 |
+
283,
|
| 303 |
+
284,
|
| 304 |
+
285,
|
| 305 |
+
286,
|
| 306 |
+
287,
|
| 307 |
+
288,
|
| 308 |
+
289,
|
| 309 |
+
290,
|
| 310 |
+
291,
|
| 311 |
+
292,
|
| 312 |
+
293,
|
| 313 |
+
294,
|
| 314 |
+
295,
|
| 315 |
+
296,
|
| 316 |
+
297,
|
| 317 |
+
298,
|
| 318 |
+
299,
|
| 319 |
+
300,
|
| 320 |
+
301,
|
| 321 |
+
302,
|
| 322 |
+
303,
|
| 323 |
+
304,
|
| 324 |
+
305,
|
| 325 |
+
306,
|
| 326 |
+
307,
|
| 327 |
+
308,
|
| 328 |
+
309,
|
| 329 |
+
310,
|
| 330 |
+
311,
|
| 331 |
+
312,
|
| 332 |
+
313,
|
| 333 |
+
314,
|
| 334 |
+
315,
|
| 335 |
+
316,
|
| 336 |
+
317,
|
| 337 |
+
318,
|
| 338 |
+
319,
|
| 339 |
+
320,
|
| 340 |
+
321,
|
| 341 |
+
322,
|
| 342 |
+
323,
|
| 343 |
+
324,
|
| 344 |
+
325,
|
| 345 |
+
326,
|
| 346 |
+
327,
|
| 347 |
+
328,
|
| 348 |
+
329,
|
| 349 |
+
330,
|
| 350 |
+
331,
|
| 351 |
+
332,
|
| 352 |
+
333,
|
| 353 |
+
334,
|
| 354 |
+
335,
|
| 355 |
+
336,
|
| 356 |
+
337,
|
| 357 |
+
338,
|
| 358 |
+
339,
|
| 359 |
+
340,
|
| 360 |
+
341,
|
| 361 |
+
342,
|
| 362 |
+
343,
|
| 363 |
+
344,
|
| 364 |
+
345,
|
| 365 |
+
346,
|
| 366 |
+
347,
|
| 367 |
+
348,
|
| 368 |
+
349,
|
| 369 |
+
350,
|
| 370 |
+
351,
|
| 371 |
+
352,
|
| 372 |
+
353,
|
| 373 |
+
354,
|
| 374 |
+
355,
|
| 375 |
+
356,
|
| 376 |
+
357,
|
| 377 |
+
358,
|
| 378 |
+
359,
|
| 379 |
+
360,
|
| 380 |
+
361,
|
| 381 |
+
362,
|
| 382 |
+
363,
|
| 383 |
+
364,
|
| 384 |
+
365,
|
| 385 |
+
366,
|
| 386 |
+
367,
|
| 387 |
+
368,
|
| 388 |
+
369,
|
| 389 |
+
370,
|
| 390 |
+
371,
|
| 391 |
+
372,
|
| 392 |
+
373,
|
| 393 |
+
374,
|
| 394 |
+
375,
|
| 395 |
+
376,
|
| 396 |
+
377,
|
| 397 |
+
378,
|
| 398 |
+
379,
|
| 399 |
+
380,
|
| 400 |
+
381,
|
| 401 |
+
382,
|
| 402 |
+
383,
|
| 403 |
+
384,
|
| 404 |
+
385,
|
| 405 |
+
386,
|
| 406 |
+
387,
|
| 407 |
+
388,
|
| 408 |
+
389,
|
| 409 |
+
390,
|
| 410 |
+
391,
|
| 411 |
+
392,
|
| 412 |
+
393,
|
| 413 |
+
394,
|
| 414 |
+
395,
|
| 415 |
+
396,
|
| 416 |
+
397,
|
| 417 |
+
398,
|
| 418 |
+
399,
|
| 419 |
+
400,
|
| 420 |
+
401,
|
| 421 |
+
402,
|
| 422 |
+
403,
|
| 423 |
+
404,
|
| 424 |
+
405,
|
| 425 |
+
406,
|
| 426 |
+
407,
|
| 427 |
+
408,
|
| 428 |
+
409,
|
| 429 |
+
410,
|
| 430 |
+
411,
|
| 431 |
+
412,
|
| 432 |
+
413,
|
| 433 |
+
414,
|
| 434 |
+
415,
|
| 435 |
+
416,
|
| 436 |
+
417,
|
| 437 |
+
418,
|
| 438 |
+
419,
|
| 439 |
+
420,
|
| 440 |
+
421,
|
| 441 |
+
422,
|
| 442 |
+
423,
|
| 443 |
+
424,
|
| 444 |
+
425,
|
| 445 |
+
426,
|
| 446 |
+
427,
|
| 447 |
+
428,
|
| 448 |
+
429,
|
| 449 |
+
430,
|
| 450 |
+
431,
|
| 451 |
+
432,
|
| 452 |
+
433,
|
| 453 |
+
434,
|
| 454 |
+
435,
|
| 455 |
+
436,
|
| 456 |
+
437,
|
| 457 |
+
438,
|
| 458 |
+
439,
|
| 459 |
+
440,
|
| 460 |
+
441,
|
| 461 |
+
442,
|
| 462 |
+
443,
|
| 463 |
+
444,
|
| 464 |
+
445,
|
| 465 |
+
446,
|
| 466 |
+
447,
|
| 467 |
+
448,
|
| 468 |
+
449,
|
| 469 |
+
450,
|
| 470 |
+
451,
|
| 471 |
+
452,
|
| 472 |
+
453,
|
| 473 |
+
454,
|
| 474 |
+
455,
|
| 475 |
+
456,
|
| 476 |
+
457,
|
| 477 |
+
458,
|
| 478 |
+
459,
|
| 479 |
+
460,
|
| 480 |
+
461,
|
| 481 |
+
462,
|
| 482 |
+
463,
|
| 483 |
+
464,
|
| 484 |
+
465,
|
| 485 |
+
466,
|
| 486 |
+
467,
|
| 487 |
+
468,
|
| 488 |
+
469,
|
| 489 |
+
470,
|
| 490 |
+
471,
|
| 491 |
+
472,
|
| 492 |
+
473,
|
| 493 |
+
474,
|
| 494 |
+
475,
|
| 495 |
+
476,
|
| 496 |
+
477,
|
| 497 |
+
478,
|
| 498 |
+
479,
|
| 499 |
+
480,
|
| 500 |
+
481,
|
| 501 |
+
482,
|
| 502 |
+
483,
|
| 503 |
+
484,
|
| 504 |
+
485,
|
| 505 |
+
486,
|
| 506 |
+
487,
|
| 507 |
+
488,
|
| 508 |
+
489,
|
| 509 |
+
490,
|
| 510 |
+
491,
|
| 511 |
+
492,
|
| 512 |
+
493,
|
| 513 |
+
494,
|
| 514 |
+
495,
|
| 515 |
+
496,
|
| 516 |
+
497,
|
| 517 |
+
498,
|
| 518 |
+
499
|
| 519 |
+
]
|
| 520 |
+
}
|
| 521 |
+
]
|
checkpoints/010000/training_state/optimizer_state.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4e9751acc3d3a61f2976bf92fda888afe3b1484e2184281e39ede80e9f7d7293
|
| 3 |
+
size 412659164
|
checkpoints/010000/training_state/rng_state.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bb95d3cc82994b61a3e55dff0e8c085e41d9d8b82778d079245d14908861f053
|
| 3 |
+
size 15708
|
checkpoints/010000/training_state/scheduler_state.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"base_lrs": [
|
| 3 |
+
0.0001
|
| 4 |
+
],
|
| 5 |
+
"last_epoch": 10000,
|
| 6 |
+
"_step_count": 10001,
|
| 7 |
+
"_is_initial": false,
|
| 8 |
+
"_get_lr_called_within_step": false,
|
| 9 |
+
"_last_lr": [
|
| 10 |
+
7.5625e-05
|
| 11 |
+
],
|
| 12 |
+
"lr_lambdas": [
|
| 13 |
+
null
|
| 14 |
+
]
|
| 15 |
+
}
|
checkpoints/010000/training_state/training_step.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"step": 10000
|
| 3 |
+
}
|
checkpoints/020000/pretrained_model/config.json
ADDED
|
@@ -0,0 +1,101 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"type": "smolvla",
|
| 3 |
+
"n_obs_steps": 1,
|
| 4 |
+
"input_features": {
|
| 5 |
+
"observation.state": {
|
| 6 |
+
"type": "STATE",
|
| 7 |
+
"shape": [
|
| 8 |
+
6
|
| 9 |
+
]
|
| 10 |
+
},
|
| 11 |
+
"observation.images.camera1": {
|
| 12 |
+
"type": "VISUAL",
|
| 13 |
+
"shape": [
|
| 14 |
+
3,
|
| 15 |
+
256,
|
| 16 |
+
256
|
| 17 |
+
]
|
| 18 |
+
},
|
| 19 |
+
"observation.images.camera2": {
|
| 20 |
+
"type": "VISUAL",
|
| 21 |
+
"shape": [
|
| 22 |
+
3,
|
| 23 |
+
256,
|
| 24 |
+
256
|
| 25 |
+
]
|
| 26 |
+
},
|
| 27 |
+
"observation.images.camera3": {
|
| 28 |
+
"type": "VISUAL",
|
| 29 |
+
"shape": [
|
| 30 |
+
3,
|
| 31 |
+
256,
|
| 32 |
+
256
|
| 33 |
+
]
|
| 34 |
+
}
|
| 35 |
+
},
|
| 36 |
+
"output_features": {
|
| 37 |
+
"action": {
|
| 38 |
+
"type": "ACTION",
|
| 39 |
+
"shape": [
|
| 40 |
+
6
|
| 41 |
+
]
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"device": "cuda",
|
| 45 |
+
"use_amp": false,
|
| 46 |
+
"use_peft": false,
|
| 47 |
+
"push_to_hub": true,
|
| 48 |
+
"repo_id": "BrandonAL/my_sim_smolvla_all_ft60k",
|
| 49 |
+
"private": null,
|
| 50 |
+
"tags": null,
|
| 51 |
+
"license": null,
|
| 52 |
+
"pretrained_path": "BrandonAL/my_sim_smolvla_all_step010000",
|
| 53 |
+
"chunk_size": 50,
|
| 54 |
+
"n_action_steps": 50,
|
| 55 |
+
"normalization_mapping": {
|
| 56 |
+
"VISUAL": "IDENTITY",
|
| 57 |
+
"STATE": "MEAN_STD",
|
| 58 |
+
"ACTION": "MEAN_STD"
|
| 59 |
+
},
|
| 60 |
+
"max_state_dim": 32,
|
| 61 |
+
"max_action_dim": 32,
|
| 62 |
+
"resize_imgs_with_padding": [
|
| 63 |
+
512,
|
| 64 |
+
512
|
| 65 |
+
],
|
| 66 |
+
"empty_cameras": 0,
|
| 67 |
+
"adapt_to_pi_aloha": false,
|
| 68 |
+
"use_delta_joint_actions_aloha": false,
|
| 69 |
+
"tokenizer_max_length": 48,
|
| 70 |
+
"num_steps": 10,
|
| 71 |
+
"use_cache": true,
|
| 72 |
+
"freeze_vision_encoder": true,
|
| 73 |
+
"train_expert_only": true,
|
| 74 |
+
"train_state_proj": true,
|
| 75 |
+
"optimizer_lr": 0.0001,
|
| 76 |
+
"optimizer_betas": [
|
| 77 |
+
0.9,
|
| 78 |
+
0.95
|
| 79 |
+
],
|
| 80 |
+
"optimizer_eps": 1e-08,
|
| 81 |
+
"optimizer_weight_decay": 1e-10,
|
| 82 |
+
"optimizer_grad_clip_norm": 10.0,
|
| 83 |
+
"scheduler_warmup_steps": 1000,
|
| 84 |
+
"scheduler_decay_steps": 30000,
|
| 85 |
+
"scheduler_decay_lr": 2.5e-06,
|
| 86 |
+
"vlm_model_name": "HuggingFaceTB/SmolVLM2-500M-Video-Instruct",
|
| 87 |
+
"load_vlm_weights": true,
|
| 88 |
+
"add_image_special_tokens": false,
|
| 89 |
+
"attention_mode": "cross_attn",
|
| 90 |
+
"prefix_length": 0,
|
| 91 |
+
"pad_language_to": "max_length",
|
| 92 |
+
"num_expert_layers": 0,
|
| 93 |
+
"num_vlm_layers": 16,
|
| 94 |
+
"self_attn_every_n_layers": 2,
|
| 95 |
+
"expert_width_multiplier": 0.75,
|
| 96 |
+
"min_period": 0.004,
|
| 97 |
+
"max_period": 4.0,
|
| 98 |
+
"rtc_config": null,
|
| 99 |
+
"compile_model": false,
|
| 100 |
+
"compile_mode": "max-autotune"
|
| 101 |
+
}
|
checkpoints/020000/pretrained_model/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c560979f869a353ab1f0e9feca48861ded8fe8eb7936dc105bf0126d10d875bc
|
| 3 |
+
size 906712520
|
checkpoints/020000/pretrained_model/policy_postprocessor.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"name": "policy_postprocessor",
|
| 3 |
+
"steps": [
|
| 4 |
+
{
|
| 5 |
+
"registry_name": "unnormalizer_processor",
|
| 6 |
+
"config": {
|
| 7 |
+
"eps": 1e-08,
|
| 8 |
+
"features": {
|
| 9 |
+
"action": {
|
| 10 |
+
"type": "ACTION",
|
| 11 |
+
"shape": [
|
| 12 |
+
6
|
| 13 |
+
]
|
| 14 |
+
}
|
| 15 |
+
},
|
| 16 |
+
"norm_map": {
|
| 17 |
+
"VISUAL": "IDENTITY",
|
| 18 |
+
"STATE": "MEAN_STD",
|
| 19 |
+
"ACTION": "MEAN_STD"
|
| 20 |
+
}
|
| 21 |
+
},
|
| 22 |
+
"state_file": "policy_postprocessor_step_0_unnormalizer_processor.safetensors"
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"registry_name": "device_processor",
|
| 26 |
+
"config": {
|
| 27 |
+
"device": "cpu",
|
| 28 |
+
"float_dtype": null
|
| 29 |
+
}
|
| 30 |
+
}
|
| 31 |
+
]
|
| 32 |
+
}
|
checkpoints/020000/pretrained_model/policy_postprocessor_step_0_unnormalizer_processor.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7e560b7d5832bf20dfaa2db407540e3042344409d4fce910831109e0e74e7368
|
| 3 |
+
size 7592
|
checkpoints/020000/pretrained_model/policy_preprocessor.json
ADDED
|
@@ -0,0 +1,87 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"name": "policy_preprocessor",
|
| 3 |
+
"steps": [
|
| 4 |
+
{
|
| 5 |
+
"registry_name": "rename_observations_processor",
|
| 6 |
+
"config": {
|
| 7 |
+
"rename_map": {}
|
| 8 |
+
}
|
| 9 |
+
},
|
| 10 |
+
{
|
| 11 |
+
"registry_name": "to_batch_processor",
|
| 12 |
+
"config": {}
|
| 13 |
+
},
|
| 14 |
+
{
|
| 15 |
+
"registry_name": "smolvla_new_line_processor",
|
| 16 |
+
"config": {}
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"registry_name": "tokenizer_processor",
|
| 20 |
+
"config": {
|
| 21 |
+
"max_length": 48,
|
| 22 |
+
"task_key": "task",
|
| 23 |
+
"padding_side": "right",
|
| 24 |
+
"padding": "max_length",
|
| 25 |
+
"truncation": true,
|
| 26 |
+
"tokenizer_name": "HuggingFaceTB/SmolVLM2-500M-Video-Instruct"
|
| 27 |
+
}
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"registry_name": "device_processor",
|
| 31 |
+
"config": {
|
| 32 |
+
"device": "cuda",
|
| 33 |
+
"float_dtype": null
|
| 34 |
+
}
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"registry_name": "normalizer_processor",
|
| 38 |
+
"config": {
|
| 39 |
+
"eps": 1e-08,
|
| 40 |
+
"features": {
|
| 41 |
+
"observation.state": {
|
| 42 |
+
"type": "STATE",
|
| 43 |
+
"shape": [
|
| 44 |
+
6
|
| 45 |
+
]
|
| 46 |
+
},
|
| 47 |
+
"observation.images.camera1": {
|
| 48 |
+
"type": "VISUAL",
|
| 49 |
+
"shape": [
|
| 50 |
+
3,
|
| 51 |
+
256,
|
| 52 |
+
256
|
| 53 |
+
]
|
| 54 |
+
},
|
| 55 |
+
"observation.images.camera2": {
|
| 56 |
+
"type": "VISUAL",
|
| 57 |
+
"shape": [
|
| 58 |
+
3,
|
| 59 |
+
256,
|
| 60 |
+
256
|
| 61 |
+
]
|
| 62 |
+
},
|
| 63 |
+
"observation.images.camera3": {
|
| 64 |
+
"type": "VISUAL",
|
| 65 |
+
"shape": [
|
| 66 |
+
3,
|
| 67 |
+
256,
|
| 68 |
+
256
|
| 69 |
+
]
|
| 70 |
+
},
|
| 71 |
+
"action": {
|
| 72 |
+
"type": "ACTION",
|
| 73 |
+
"shape": [
|
| 74 |
+
6
|
| 75 |
+
]
|
| 76 |
+
}
|
| 77 |
+
},
|
| 78 |
+
"norm_map": {
|
| 79 |
+
"VISUAL": "IDENTITY",
|
| 80 |
+
"STATE": "MEAN_STD",
|
| 81 |
+
"ACTION": "MEAN_STD"
|
| 82 |
+
}
|
| 83 |
+
},
|
| 84 |
+
"state_file": "policy_preprocessor_step_5_normalizer_processor.safetensors"
|
| 85 |
+
}
|
| 86 |
+
]
|
| 87 |
+
}
|
checkpoints/020000/pretrained_model/policy_preprocessor_step_5_normalizer_processor.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7e560b7d5832bf20dfaa2db407540e3042344409d4fce910831109e0e74e7368
|
| 3 |
+
size 7592
|
checkpoints/020000/pretrained_model/train_config.json
ADDED
|
@@ -0,0 +1,239 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"dataset": {
|
| 3 |
+
"repo_id": "BrandonAL/my_sim_merged",
|
| 4 |
+
"root": null,
|
| 5 |
+
"episodes": null,
|
| 6 |
+
"image_transforms": {
|
| 7 |
+
"enable": true,
|
| 8 |
+
"max_num_transforms": 3,
|
| 9 |
+
"random_order": false,
|
| 10 |
+
"tfs": {
|
| 11 |
+
"brightness": {
|
| 12 |
+
"weight": 1.0,
|
| 13 |
+
"type": "ColorJitter",
|
| 14 |
+
"kwargs": {
|
| 15 |
+
"brightness": [
|
| 16 |
+
0.8,
|
| 17 |
+
1.2
|
| 18 |
+
]
|
| 19 |
+
}
|
| 20 |
+
},
|
| 21 |
+
"contrast": {
|
| 22 |
+
"weight": 1.0,
|
| 23 |
+
"type": "ColorJitter",
|
| 24 |
+
"kwargs": {
|
| 25 |
+
"contrast": [
|
| 26 |
+
0.8,
|
| 27 |
+
1.2
|
| 28 |
+
]
|
| 29 |
+
}
|
| 30 |
+
},
|
| 31 |
+
"saturation": {
|
| 32 |
+
"weight": 1.0,
|
| 33 |
+
"type": "ColorJitter",
|
| 34 |
+
"kwargs": {
|
| 35 |
+
"saturation": [
|
| 36 |
+
0.5,
|
| 37 |
+
1.5
|
| 38 |
+
]
|
| 39 |
+
}
|
| 40 |
+
},
|
| 41 |
+
"hue": {
|
| 42 |
+
"weight": 1.0,
|
| 43 |
+
"type": "ColorJitter",
|
| 44 |
+
"kwargs": {
|
| 45 |
+
"hue": [
|
| 46 |
+
-0.05,
|
| 47 |
+
0.05
|
| 48 |
+
]
|
| 49 |
+
}
|
| 50 |
+
},
|
| 51 |
+
"sharpness": {
|
| 52 |
+
"weight": 1.0,
|
| 53 |
+
"type": "SharpnessJitter",
|
| 54 |
+
"kwargs": {
|
| 55 |
+
"sharpness": [
|
| 56 |
+
0.5,
|
| 57 |
+
1.5
|
| 58 |
+
]
|
| 59 |
+
}
|
| 60 |
+
},
|
| 61 |
+
"affine": {
|
| 62 |
+
"weight": 1.0,
|
| 63 |
+
"type": "RandomAffine",
|
| 64 |
+
"kwargs": {
|
| 65 |
+
"degrees": [
|
| 66 |
+
-5.0,
|
| 67 |
+
5.0
|
| 68 |
+
],
|
| 69 |
+
"translate": [
|
| 70 |
+
0.05,
|
| 71 |
+
0.05
|
| 72 |
+
]
|
| 73 |
+
}
|
| 74 |
+
}
|
| 75 |
+
}
|
| 76 |
+
},
|
| 77 |
+
"revision": null,
|
| 78 |
+
"use_imagenet_stats": true,
|
| 79 |
+
"video_backend": "pyav",
|
| 80 |
+
"streaming": false
|
| 81 |
+
},
|
| 82 |
+
"env": null,
|
| 83 |
+
"policy": {
|
| 84 |
+
"type": "smolvla",
|
| 85 |
+
"n_obs_steps": 1,
|
| 86 |
+
"input_features": {
|
| 87 |
+
"observation.state": {
|
| 88 |
+
"type": "STATE",
|
| 89 |
+
"shape": [
|
| 90 |
+
6
|
| 91 |
+
]
|
| 92 |
+
},
|
| 93 |
+
"observation.images.camera1": {
|
| 94 |
+
"type": "VISUAL",
|
| 95 |
+
"shape": [
|
| 96 |
+
3,
|
| 97 |
+
256,
|
| 98 |
+
256
|
| 99 |
+
]
|
| 100 |
+
},
|
| 101 |
+
"observation.images.camera2": {
|
| 102 |
+
"type": "VISUAL",
|
| 103 |
+
"shape": [
|
| 104 |
+
3,
|
| 105 |
+
256,
|
| 106 |
+
256
|
| 107 |
+
]
|
| 108 |
+
},
|
| 109 |
+
"observation.images.camera3": {
|
| 110 |
+
"type": "VISUAL",
|
| 111 |
+
"shape": [
|
| 112 |
+
3,
|
| 113 |
+
256,
|
| 114 |
+
256
|
| 115 |
+
]
|
| 116 |
+
}
|
| 117 |
+
},
|
| 118 |
+
"output_features": {
|
| 119 |
+
"action": {
|
| 120 |
+
"type": "ACTION",
|
| 121 |
+
"shape": [
|
| 122 |
+
6
|
| 123 |
+
]
|
| 124 |
+
}
|
| 125 |
+
},
|
| 126 |
+
"device": "cuda",
|
| 127 |
+
"use_amp": false,
|
| 128 |
+
"use_peft": false,
|
| 129 |
+
"push_to_hub": true,
|
| 130 |
+
"repo_id": "BrandonAL/my_sim_smolvla_all_ft60k",
|
| 131 |
+
"private": null,
|
| 132 |
+
"tags": null,
|
| 133 |
+
"license": null,
|
| 134 |
+
"pretrained_path": "BrandonAL/my_sim_smolvla_all_step010000",
|
| 135 |
+
"chunk_size": 50,
|
| 136 |
+
"n_action_steps": 50,
|
| 137 |
+
"normalization_mapping": {
|
| 138 |
+
"VISUAL": "IDENTITY",
|
| 139 |
+
"STATE": "MEAN_STD",
|
| 140 |
+
"ACTION": "MEAN_STD"
|
| 141 |
+
},
|
| 142 |
+
"max_state_dim": 32,
|
| 143 |
+
"max_action_dim": 32,
|
| 144 |
+
"resize_imgs_with_padding": [
|
| 145 |
+
512,
|
| 146 |
+
512
|
| 147 |
+
],
|
| 148 |
+
"empty_cameras": 0,
|
| 149 |
+
"adapt_to_pi_aloha": false,
|
| 150 |
+
"use_delta_joint_actions_aloha": false,
|
| 151 |
+
"tokenizer_max_length": 48,
|
| 152 |
+
"num_steps": 10,
|
| 153 |
+
"use_cache": true,
|
| 154 |
+
"freeze_vision_encoder": true,
|
| 155 |
+
"train_expert_only": true,
|
| 156 |
+
"train_state_proj": true,
|
| 157 |
+
"optimizer_lr": 0.0001,
|
| 158 |
+
"optimizer_betas": [
|
| 159 |
+
0.9,
|
| 160 |
+
0.95
|
| 161 |
+
],
|
| 162 |
+
"optimizer_eps": 1e-08,
|
| 163 |
+
"optimizer_weight_decay": 1e-10,
|
| 164 |
+
"optimizer_grad_clip_norm": 10.0,
|
| 165 |
+
"scheduler_warmup_steps": 1000,
|
| 166 |
+
"scheduler_decay_steps": 30000,
|
| 167 |
+
"scheduler_decay_lr": 2.5e-06,
|
| 168 |
+
"vlm_model_name": "HuggingFaceTB/SmolVLM2-500M-Video-Instruct",
|
| 169 |
+
"load_vlm_weights": true,
|
| 170 |
+
"add_image_special_tokens": false,
|
| 171 |
+
"attention_mode": "cross_attn",
|
| 172 |
+
"prefix_length": 0,
|
| 173 |
+
"pad_language_to": "max_length",
|
| 174 |
+
"num_expert_layers": 0,
|
| 175 |
+
"num_vlm_layers": 16,
|
| 176 |
+
"self_attn_every_n_layers": 2,
|
| 177 |
+
"expert_width_multiplier": 0.75,
|
| 178 |
+
"min_period": 0.004,
|
| 179 |
+
"max_period": 4.0,
|
| 180 |
+
"rtc_config": null,
|
| 181 |
+
"compile_model": false,
|
| 182 |
+
"compile_mode": "max-autotune"
|
| 183 |
+
},
|
| 184 |
+
"output_dir": "outputs/train/my_sim_smolvla_all_ft60k",
|
| 185 |
+
"job_name": "my_smolvla_all_ft60k",
|
| 186 |
+
"resume": false,
|
| 187 |
+
"seed": 1000,
|
| 188 |
+
"cudnn_deterministic": false,
|
| 189 |
+
"num_workers": 4,
|
| 190 |
+
"batch_size": 64,
|
| 191 |
+
"steps": 50000,
|
| 192 |
+
"eval_freq": 20000,
|
| 193 |
+
"log_freq": 200,
|
| 194 |
+
"tolerance_s": 0.0001,
|
| 195 |
+
"save_checkpoint": true,
|
| 196 |
+
"save_freq": 10000,
|
| 197 |
+
"use_policy_training_preset": true,
|
| 198 |
+
"optimizer": {
|
| 199 |
+
"type": "adamw",
|
| 200 |
+
"lr": 0.0001,
|
| 201 |
+
"weight_decay": 1e-10,
|
| 202 |
+
"grad_clip_norm": 10.0,
|
| 203 |
+
"betas": [
|
| 204 |
+
0.9,
|
| 205 |
+
0.95
|
| 206 |
+
],
|
| 207 |
+
"eps": 1e-08
|
| 208 |
+
},
|
| 209 |
+
"scheduler": {
|
| 210 |
+
"type": "cosine_decay_with_warmup",
|
| 211 |
+
"num_warmup_steps": 1000,
|
| 212 |
+
"num_decay_steps": 30000,
|
| 213 |
+
"peak_lr": 0.0001,
|
| 214 |
+
"decay_lr": 2.5e-06
|
| 215 |
+
},
|
| 216 |
+
"eval": {
|
| 217 |
+
"n_episodes": 50,
|
| 218 |
+
"batch_size": 44,
|
| 219 |
+
"use_async_envs": true
|
| 220 |
+
},
|
| 221 |
+
"wandb": {
|
| 222 |
+
"enable": false,
|
| 223 |
+
"disable_artifact": false,
|
| 224 |
+
"project": "lerobot",
|
| 225 |
+
"entity": null,
|
| 226 |
+
"notes": null,
|
| 227 |
+
"run_id": null,
|
| 228 |
+
"mode": null,
|
| 229 |
+
"add_tags": true
|
| 230 |
+
},
|
| 231 |
+
"peft": null,
|
| 232 |
+
"use_rabc": false,
|
| 233 |
+
"rabc_progress_path": null,
|
| 234 |
+
"rabc_kappa": 0.01,
|
| 235 |
+
"rabc_epsilon": 1e-06,
|
| 236 |
+
"rabc_head_mode": "sparse",
|
| 237 |
+
"rename_map": {},
|
| 238 |
+
"checkpoint_path": null
|
| 239 |
+
}
|
checkpoints/020000/training_state/optimizer_param_groups.json
ADDED
|
@@ -0,0 +1,521 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[
|
| 2 |
+
{
|
| 3 |
+
"lr": 2.6875000000000013e-05,
|
| 4 |
+
"betas": [
|
| 5 |
+
0.9,
|
| 6 |
+
0.95
|
| 7 |
+
],
|
| 8 |
+
"eps": 1e-08,
|
| 9 |
+
"weight_decay": 1e-10,
|
| 10 |
+
"amsgrad": false,
|
| 11 |
+
"maximize": false,
|
| 12 |
+
"foreach": null,
|
| 13 |
+
"capturable": false,
|
| 14 |
+
"differentiable": false,
|
| 15 |
+
"fused": null,
|
| 16 |
+
"decoupled_weight_decay": true,
|
| 17 |
+
"initial_lr": 0.0001,
|
| 18 |
+
"params": [
|
| 19 |
+
0,
|
| 20 |
+
1,
|
| 21 |
+
2,
|
| 22 |
+
3,
|
| 23 |
+
4,
|
| 24 |
+
5,
|
| 25 |
+
6,
|
| 26 |
+
7,
|
| 27 |
+
8,
|
| 28 |
+
9,
|
| 29 |
+
10,
|
| 30 |
+
11,
|
| 31 |
+
12,
|
| 32 |
+
13,
|
| 33 |
+
14,
|
| 34 |
+
15,
|
| 35 |
+
16,
|
| 36 |
+
17,
|
| 37 |
+
18,
|
| 38 |
+
19,
|
| 39 |
+
20,
|
| 40 |
+
21,
|
| 41 |
+
22,
|
| 42 |
+
23,
|
| 43 |
+
24,
|
| 44 |
+
25,
|
| 45 |
+
26,
|
| 46 |
+
27,
|
| 47 |
+
28,
|
| 48 |
+
29,
|
| 49 |
+
30,
|
| 50 |
+
31,
|
| 51 |
+
32,
|
| 52 |
+
33,
|
| 53 |
+
34,
|
| 54 |
+
35,
|
| 55 |
+
36,
|
| 56 |
+
37,
|
| 57 |
+
38,
|
| 58 |
+
39,
|
| 59 |
+
40,
|
| 60 |
+
41,
|
| 61 |
+
42,
|
| 62 |
+
43,
|
| 63 |
+
44,
|
| 64 |
+
45,
|
| 65 |
+
46,
|
| 66 |
+
47,
|
| 67 |
+
48,
|
| 68 |
+
49,
|
| 69 |
+
50,
|
| 70 |
+
51,
|
| 71 |
+
52,
|
| 72 |
+
53,
|
| 73 |
+
54,
|
| 74 |
+
55,
|
| 75 |
+
56,
|
| 76 |
+
57,
|
| 77 |
+
58,
|
| 78 |
+
59,
|
| 79 |
+
60,
|
| 80 |
+
61,
|
| 81 |
+
62,
|
| 82 |
+
63,
|
| 83 |
+
64,
|
| 84 |
+
65,
|
| 85 |
+
66,
|
| 86 |
+
67,
|
| 87 |
+
68,
|
| 88 |
+
69,
|
| 89 |
+
70,
|
| 90 |
+
71,
|
| 91 |
+
72,
|
| 92 |
+
73,
|
| 93 |
+
74,
|
| 94 |
+
75,
|
| 95 |
+
76,
|
| 96 |
+
77,
|
| 97 |
+
78,
|
| 98 |
+
79,
|
| 99 |
+
80,
|
| 100 |
+
81,
|
| 101 |
+
82,
|
| 102 |
+
83,
|
| 103 |
+
84,
|
| 104 |
+
85,
|
| 105 |
+
86,
|
| 106 |
+
87,
|
| 107 |
+
88,
|
| 108 |
+
89,
|
| 109 |
+
90,
|
| 110 |
+
91,
|
| 111 |
+
92,
|
| 112 |
+
93,
|
| 113 |
+
94,
|
| 114 |
+
95,
|
| 115 |
+
96,
|
| 116 |
+
97,
|
| 117 |
+
98,
|
| 118 |
+
99,
|
| 119 |
+
100,
|
| 120 |
+
101,
|
| 121 |
+
102,
|
| 122 |
+
103,
|
| 123 |
+
104,
|
| 124 |
+
105,
|
| 125 |
+
106,
|
| 126 |
+
107,
|
| 127 |
+
108,
|
| 128 |
+
109,
|
| 129 |
+
110,
|
| 130 |
+
111,
|
| 131 |
+
112,
|
| 132 |
+
113,
|
| 133 |
+
114,
|
| 134 |
+
115,
|
| 135 |
+
116,
|
| 136 |
+
117,
|
| 137 |
+
118,
|
| 138 |
+
119,
|
| 139 |
+
120,
|
| 140 |
+
121,
|
| 141 |
+
122,
|
| 142 |
+
123,
|
| 143 |
+
124,
|
| 144 |
+
125,
|
| 145 |
+
126,
|
| 146 |
+
127,
|
| 147 |
+
128,
|
| 148 |
+
129,
|
| 149 |
+
130,
|
| 150 |
+
131,
|
| 151 |
+
132,
|
| 152 |
+
133,
|
| 153 |
+
134,
|
| 154 |
+
135,
|
| 155 |
+
136,
|
| 156 |
+
137,
|
| 157 |
+
138,
|
| 158 |
+
139,
|
| 159 |
+
140,
|
| 160 |
+
141,
|
| 161 |
+
142,
|
| 162 |
+
143,
|
| 163 |
+
144,
|
| 164 |
+
145,
|
| 165 |
+
146,
|
| 166 |
+
147,
|
| 167 |
+
148,
|
| 168 |
+
149,
|
| 169 |
+
150,
|
| 170 |
+
151,
|
| 171 |
+
152,
|
| 172 |
+
153,
|
| 173 |
+
154,
|
| 174 |
+
155,
|
| 175 |
+
156,
|
| 176 |
+
157,
|
| 177 |
+
158,
|
| 178 |
+
159,
|
| 179 |
+
160,
|
| 180 |
+
161,
|
| 181 |
+
162,
|
| 182 |
+
163,
|
| 183 |
+
164,
|
| 184 |
+
165,
|
| 185 |
+
166,
|
| 186 |
+
167,
|
| 187 |
+
168,
|
| 188 |
+
169,
|
| 189 |
+
170,
|
| 190 |
+
171,
|
| 191 |
+
172,
|
| 192 |
+
173,
|
| 193 |
+
174,
|
| 194 |
+
175,
|
| 195 |
+
176,
|
| 196 |
+
177,
|
| 197 |
+
178,
|
| 198 |
+
179,
|
| 199 |
+
180,
|
| 200 |
+
181,
|
| 201 |
+
182,
|
| 202 |
+
183,
|
| 203 |
+
184,
|
| 204 |
+
185,
|
| 205 |
+
186,
|
| 206 |
+
187,
|
| 207 |
+
188,
|
| 208 |
+
189,
|
| 209 |
+
190,
|
| 210 |
+
191,
|
| 211 |
+
192,
|
| 212 |
+
193,
|
| 213 |
+
194,
|
| 214 |
+
195,
|
| 215 |
+
196,
|
| 216 |
+
197,
|
| 217 |
+
198,
|
| 218 |
+
199,
|
| 219 |
+
200,
|
| 220 |
+
201,
|
| 221 |
+
202,
|
| 222 |
+
203,
|
| 223 |
+
204,
|
| 224 |
+
205,
|
| 225 |
+
206,
|
| 226 |
+
207,
|
| 227 |
+
208,
|
| 228 |
+
209,
|
| 229 |
+
210,
|
| 230 |
+
211,
|
| 231 |
+
212,
|
| 232 |
+
213,
|
| 233 |
+
214,
|
| 234 |
+
215,
|
| 235 |
+
216,
|
| 236 |
+
217,
|
| 237 |
+
218,
|
| 238 |
+
219,
|
| 239 |
+
220,
|
| 240 |
+
221,
|
| 241 |
+
222,
|
| 242 |
+
223,
|
| 243 |
+
224,
|
| 244 |
+
225,
|
| 245 |
+
226,
|
| 246 |
+
227,
|
| 247 |
+
228,
|
| 248 |
+
229,
|
| 249 |
+
230,
|
| 250 |
+
231,
|
| 251 |
+
232,
|
| 252 |
+
233,
|
| 253 |
+
234,
|
| 254 |
+
235,
|
| 255 |
+
236,
|
| 256 |
+
237,
|
| 257 |
+
238,
|
| 258 |
+
239,
|
| 259 |
+
240,
|
| 260 |
+
241,
|
| 261 |
+
242,
|
| 262 |
+
243,
|
| 263 |
+
244,
|
| 264 |
+
245,
|
| 265 |
+
246,
|
| 266 |
+
247,
|
| 267 |
+
248,
|
| 268 |
+
249,
|
| 269 |
+
250,
|
| 270 |
+
251,
|
| 271 |
+
252,
|
| 272 |
+
253,
|
| 273 |
+
254,
|
| 274 |
+
255,
|
| 275 |
+
256,
|
| 276 |
+
257,
|
| 277 |
+
258,
|
| 278 |
+
259,
|
| 279 |
+
260,
|
| 280 |
+
261,
|
| 281 |
+
262,
|
| 282 |
+
263,
|
| 283 |
+
264,
|
| 284 |
+
265,
|
| 285 |
+
266,
|
| 286 |
+
267,
|
| 287 |
+
268,
|
| 288 |
+
269,
|
| 289 |
+
270,
|
| 290 |
+
271,
|
| 291 |
+
272,
|
| 292 |
+
273,
|
| 293 |
+
274,
|
| 294 |
+
275,
|
| 295 |
+
276,
|
| 296 |
+
277,
|
| 297 |
+
278,
|
| 298 |
+
279,
|
| 299 |
+
280,
|
| 300 |
+
281,
|
| 301 |
+
282,
|
| 302 |
+
283,
|
| 303 |
+
284,
|
| 304 |
+
285,
|
| 305 |
+
286,
|
| 306 |
+
287,
|
| 307 |
+
288,
|
| 308 |
+
289,
|
| 309 |
+
290,
|
| 310 |
+
291,
|
| 311 |
+
292,
|
| 312 |
+
293,
|
| 313 |
+
294,
|
| 314 |
+
295,
|
| 315 |
+
296,
|
| 316 |
+
297,
|
| 317 |
+
298,
|
| 318 |
+
299,
|
| 319 |
+
300,
|
| 320 |
+
301,
|
| 321 |
+
302,
|
| 322 |
+
303,
|
| 323 |
+
304,
|
| 324 |
+
305,
|
| 325 |
+
306,
|
| 326 |
+
307,
|
| 327 |
+
308,
|
| 328 |
+
309,
|
| 329 |
+
310,
|
| 330 |
+
311,
|
| 331 |
+
312,
|
| 332 |
+
313,
|
| 333 |
+
314,
|
| 334 |
+
315,
|
| 335 |
+
316,
|
| 336 |
+
317,
|
| 337 |
+
318,
|
| 338 |
+
319,
|
| 339 |
+
320,
|
| 340 |
+
321,
|
| 341 |
+
322,
|
| 342 |
+
323,
|
| 343 |
+
324,
|
| 344 |
+
325,
|
| 345 |
+
326,
|
| 346 |
+
327,
|
| 347 |
+
328,
|
| 348 |
+
329,
|
| 349 |
+
330,
|
| 350 |
+
331,
|
| 351 |
+
332,
|
| 352 |
+
333,
|
| 353 |
+
334,
|
| 354 |
+
335,
|
| 355 |
+
336,
|
| 356 |
+
337,
|
| 357 |
+
338,
|
| 358 |
+
339,
|
| 359 |
+
340,
|
| 360 |
+
341,
|
| 361 |
+
342,
|
| 362 |
+
343,
|
| 363 |
+
344,
|
| 364 |
+
345,
|
| 365 |
+
346,
|
| 366 |
+
347,
|
| 367 |
+
348,
|
| 368 |
+
349,
|
| 369 |
+
350,
|
| 370 |
+
351,
|
| 371 |
+
352,
|
| 372 |
+
353,
|
| 373 |
+
354,
|
| 374 |
+
355,
|
| 375 |
+
356,
|
| 376 |
+
357,
|
| 377 |
+
358,
|
| 378 |
+
359,
|
| 379 |
+
360,
|
| 380 |
+
361,
|
| 381 |
+
362,
|
| 382 |
+
363,
|
| 383 |
+
364,
|
| 384 |
+
365,
|
| 385 |
+
366,
|
| 386 |
+
367,
|
| 387 |
+
368,
|
| 388 |
+
369,
|
| 389 |
+
370,
|
| 390 |
+
371,
|
| 391 |
+
372,
|
| 392 |
+
373,
|
| 393 |
+
374,
|
| 394 |
+
375,
|
| 395 |
+
376,
|
| 396 |
+
377,
|
| 397 |
+
378,
|
| 398 |
+
379,
|
| 399 |
+
380,
|
| 400 |
+
381,
|
| 401 |
+
382,
|
| 402 |
+
383,
|
| 403 |
+
384,
|
| 404 |
+
385,
|
| 405 |
+
386,
|
| 406 |
+
387,
|
| 407 |
+
388,
|
| 408 |
+
389,
|
| 409 |
+
390,
|
| 410 |
+
391,
|
| 411 |
+
392,
|
| 412 |
+
393,
|
| 413 |
+
394,
|
| 414 |
+
395,
|
| 415 |
+
396,
|
| 416 |
+
397,
|
| 417 |
+
398,
|
| 418 |
+
399,
|
| 419 |
+
400,
|
| 420 |
+
401,
|
| 421 |
+
402,
|
| 422 |
+
403,
|
| 423 |
+
404,
|
| 424 |
+
405,
|
| 425 |
+
406,
|
| 426 |
+
407,
|
| 427 |
+
408,
|
| 428 |
+
409,
|
| 429 |
+
410,
|
| 430 |
+
411,
|
| 431 |
+
412,
|
| 432 |
+
413,
|
| 433 |
+
414,
|
| 434 |
+
415,
|
| 435 |
+
416,
|
| 436 |
+
417,
|
| 437 |
+
418,
|
| 438 |
+
419,
|
| 439 |
+
420,
|
| 440 |
+
421,
|
| 441 |
+
422,
|
| 442 |
+
423,
|
| 443 |
+
424,
|
| 444 |
+
425,
|
| 445 |
+
426,
|
| 446 |
+
427,
|
| 447 |
+
428,
|
| 448 |
+
429,
|
| 449 |
+
430,
|
| 450 |
+
431,
|
| 451 |
+
432,
|
| 452 |
+
433,
|
| 453 |
+
434,
|
| 454 |
+
435,
|
| 455 |
+
436,
|
| 456 |
+
437,
|
| 457 |
+
438,
|
| 458 |
+
439,
|
| 459 |
+
440,
|
| 460 |
+
441,
|
| 461 |
+
442,
|
| 462 |
+
443,
|
| 463 |
+
444,
|
| 464 |
+
445,
|
| 465 |
+
446,
|
| 466 |
+
447,
|
| 467 |
+
448,
|
| 468 |
+
449,
|
| 469 |
+
450,
|
| 470 |
+
451,
|
| 471 |
+
452,
|
| 472 |
+
453,
|
| 473 |
+
454,
|
| 474 |
+
455,
|
| 475 |
+
456,
|
| 476 |
+
457,
|
| 477 |
+
458,
|
| 478 |
+
459,
|
| 479 |
+
460,
|
| 480 |
+
461,
|
| 481 |
+
462,
|
| 482 |
+
463,
|
| 483 |
+
464,
|
| 484 |
+
465,
|
| 485 |
+
466,
|
| 486 |
+
467,
|
| 487 |
+
468,
|
| 488 |
+
469,
|
| 489 |
+
470,
|
| 490 |
+
471,
|
| 491 |
+
472,
|
| 492 |
+
473,
|
| 493 |
+
474,
|
| 494 |
+
475,
|
| 495 |
+
476,
|
| 496 |
+
477,
|
| 497 |
+
478,
|
| 498 |
+
479,
|
| 499 |
+
480,
|
| 500 |
+
481,
|
| 501 |
+
482,
|
| 502 |
+
483,
|
| 503 |
+
484,
|
| 504 |
+
485,
|
| 505 |
+
486,
|
| 506 |
+
487,
|
| 507 |
+
488,
|
| 508 |
+
489,
|
| 509 |
+
490,
|
| 510 |
+
491,
|
| 511 |
+
492,
|
| 512 |
+
493,
|
| 513 |
+
494,
|
| 514 |
+
495,
|
| 515 |
+
496,
|
| 516 |
+
497,
|
| 517 |
+
498,
|
| 518 |
+
499
|
| 519 |
+
]
|
| 520 |
+
}
|
| 521 |
+
]
|
checkpoints/020000/training_state/optimizer_state.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:41e5c8a971ec034df4881f0a02260afaf1950846141082173a778520c464d034
|
| 3 |
+
size 412659164
|
checkpoints/020000/training_state/rng_state.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a7e98ee2fc579ccf456f9f5e097d94552901e7b07df1f51fe98e0bc1f2a4fef8
|
| 3 |
+
size 15708
|
checkpoints/020000/training_state/scheduler_state.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"base_lrs": [
|
| 3 |
+
0.0001
|
| 4 |
+
],
|
| 5 |
+
"last_epoch": 20000,
|
| 6 |
+
"_step_count": 20001,
|
| 7 |
+
"_is_initial": false,
|
| 8 |
+
"_get_lr_called_within_step": false,
|
| 9 |
+
"_last_lr": [
|
| 10 |
+
2.6875000000000013e-05
|
| 11 |
+
],
|
| 12 |
+
"lr_lambdas": [
|
| 13 |
+
null
|
| 14 |
+
]
|
| 15 |
+
}
|
checkpoints/020000/training_state/training_step.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"step": 20000
|
| 3 |
+
}
|
checkpoints/030000/pretrained_model/config.json
ADDED
|
@@ -0,0 +1,101 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"type": "smolvla",
|
| 3 |
+
"n_obs_steps": 1,
|
| 4 |
+
"input_features": {
|
| 5 |
+
"observation.state": {
|
| 6 |
+
"type": "STATE",
|
| 7 |
+
"shape": [
|
| 8 |
+
6
|
| 9 |
+
]
|
| 10 |
+
},
|
| 11 |
+
"observation.images.camera1": {
|
| 12 |
+
"type": "VISUAL",
|
| 13 |
+
"shape": [
|
| 14 |
+
3,
|
| 15 |
+
256,
|
| 16 |
+
256
|
| 17 |
+
]
|
| 18 |
+
},
|
| 19 |
+
"observation.images.camera2": {
|
| 20 |
+
"type": "VISUAL",
|
| 21 |
+
"shape": [
|
| 22 |
+
3,
|
| 23 |
+
256,
|
| 24 |
+
256
|
| 25 |
+
]
|
| 26 |
+
},
|
| 27 |
+
"observation.images.camera3": {
|
| 28 |
+
"type": "VISUAL",
|
| 29 |
+
"shape": [
|
| 30 |
+
3,
|
| 31 |
+
256,
|
| 32 |
+
256
|
| 33 |
+
]
|
| 34 |
+
}
|
| 35 |
+
},
|
| 36 |
+
"output_features": {
|
| 37 |
+
"action": {
|
| 38 |
+
"type": "ACTION",
|
| 39 |
+
"shape": [
|
| 40 |
+
6
|
| 41 |
+
]
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"device": "cuda",
|
| 45 |
+
"use_amp": false,
|
| 46 |
+
"use_peft": false,
|
| 47 |
+
"push_to_hub": true,
|
| 48 |
+
"repo_id": "BrandonAL/my_sim_smolvla_all_ft60k",
|
| 49 |
+
"private": null,
|
| 50 |
+
"tags": null,
|
| 51 |
+
"license": null,
|
| 52 |
+
"pretrained_path": "BrandonAL/my_sim_smolvla_all_step010000",
|
| 53 |
+
"chunk_size": 50,
|
| 54 |
+
"n_action_steps": 50,
|
| 55 |
+
"normalization_mapping": {
|
| 56 |
+
"VISUAL": "IDENTITY",
|
| 57 |
+
"STATE": "MEAN_STD",
|
| 58 |
+
"ACTION": "MEAN_STD"
|
| 59 |
+
},
|
| 60 |
+
"max_state_dim": 32,
|
| 61 |
+
"max_action_dim": 32,
|
| 62 |
+
"resize_imgs_with_padding": [
|
| 63 |
+
512,
|
| 64 |
+
512
|
| 65 |
+
],
|
| 66 |
+
"empty_cameras": 0,
|
| 67 |
+
"adapt_to_pi_aloha": false,
|
| 68 |
+
"use_delta_joint_actions_aloha": false,
|
| 69 |
+
"tokenizer_max_length": 48,
|
| 70 |
+
"num_steps": 10,
|
| 71 |
+
"use_cache": true,
|
| 72 |
+
"freeze_vision_encoder": true,
|
| 73 |
+
"train_expert_only": true,
|
| 74 |
+
"train_state_proj": true,
|
| 75 |
+
"optimizer_lr": 0.0001,
|
| 76 |
+
"optimizer_betas": [
|
| 77 |
+
0.9,
|
| 78 |
+
0.95
|
| 79 |
+
],
|
| 80 |
+
"optimizer_eps": 1e-08,
|
| 81 |
+
"optimizer_weight_decay": 1e-10,
|
| 82 |
+
"optimizer_grad_clip_norm": 10.0,
|
| 83 |
+
"scheduler_warmup_steps": 1000,
|
| 84 |
+
"scheduler_decay_steps": 30000,
|
| 85 |
+
"scheduler_decay_lr": 2.5e-06,
|
| 86 |
+
"vlm_model_name": "HuggingFaceTB/SmolVLM2-500M-Video-Instruct",
|
| 87 |
+
"load_vlm_weights": true,
|
| 88 |
+
"add_image_special_tokens": false,
|
| 89 |
+
"attention_mode": "cross_attn",
|
| 90 |
+
"prefix_length": 0,
|
| 91 |
+
"pad_language_to": "max_length",
|
| 92 |
+
"num_expert_layers": 0,
|
| 93 |
+
"num_vlm_layers": 16,
|
| 94 |
+
"self_attn_every_n_layers": 2,
|
| 95 |
+
"expert_width_multiplier": 0.75,
|
| 96 |
+
"min_period": 0.004,
|
| 97 |
+
"max_period": 4.0,
|
| 98 |
+
"rtc_config": null,
|
| 99 |
+
"compile_model": false,
|
| 100 |
+
"compile_mode": "max-autotune"
|
| 101 |
+
}
|
checkpoints/030000/pretrained_model/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:976a0d21ad684c35e7ea06ab107f06706298a8ffed19953b032f7b75597d901f
|
| 3 |
+
size 906712520
|
checkpoints/030000/pretrained_model/policy_postprocessor.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"name": "policy_postprocessor",
|
| 3 |
+
"steps": [
|
| 4 |
+
{
|
| 5 |
+
"registry_name": "unnormalizer_processor",
|
| 6 |
+
"config": {
|
| 7 |
+
"eps": 1e-08,
|
| 8 |
+
"features": {
|
| 9 |
+
"action": {
|
| 10 |
+
"type": "ACTION",
|
| 11 |
+
"shape": [
|
| 12 |
+
6
|
| 13 |
+
]
|
| 14 |
+
}
|
| 15 |
+
},
|
| 16 |
+
"norm_map": {
|
| 17 |
+
"VISUAL": "IDENTITY",
|
| 18 |
+
"STATE": "MEAN_STD",
|
| 19 |
+
"ACTION": "MEAN_STD"
|
| 20 |
+
}
|
| 21 |
+
},
|
| 22 |
+
"state_file": "policy_postprocessor_step_0_unnormalizer_processor.safetensors"
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"registry_name": "device_processor",
|
| 26 |
+
"config": {
|
| 27 |
+
"device": "cpu",
|
| 28 |
+
"float_dtype": null
|
| 29 |
+
}
|
| 30 |
+
}
|
| 31 |
+
]
|
| 32 |
+
}
|
checkpoints/030000/pretrained_model/policy_postprocessor_step_0_unnormalizer_processor.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7e560b7d5832bf20dfaa2db407540e3042344409d4fce910831109e0e74e7368
|
| 3 |
+
size 7592
|
checkpoints/030000/pretrained_model/policy_preprocessor.json
ADDED
|
@@ -0,0 +1,87 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"name": "policy_preprocessor",
|
| 3 |
+
"steps": [
|
| 4 |
+
{
|
| 5 |
+
"registry_name": "rename_observations_processor",
|
| 6 |
+
"config": {
|
| 7 |
+
"rename_map": {}
|
| 8 |
+
}
|
| 9 |
+
},
|
| 10 |
+
{
|
| 11 |
+
"registry_name": "to_batch_processor",
|
| 12 |
+
"config": {}
|
| 13 |
+
},
|
| 14 |
+
{
|
| 15 |
+
"registry_name": "smolvla_new_line_processor",
|
| 16 |
+
"config": {}
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"registry_name": "tokenizer_processor",
|
| 20 |
+
"config": {
|
| 21 |
+
"max_length": 48,
|
| 22 |
+
"task_key": "task",
|
| 23 |
+
"padding_side": "right",
|
| 24 |
+
"padding": "max_length",
|
| 25 |
+
"truncation": true,
|
| 26 |
+
"tokenizer_name": "HuggingFaceTB/SmolVLM2-500M-Video-Instruct"
|
| 27 |
+
}
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"registry_name": "device_processor",
|
| 31 |
+
"config": {
|
| 32 |
+
"device": "cuda",
|
| 33 |
+
"float_dtype": null
|
| 34 |
+
}
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"registry_name": "normalizer_processor",
|
| 38 |
+
"config": {
|
| 39 |
+
"eps": 1e-08,
|
| 40 |
+
"features": {
|
| 41 |
+
"observation.state": {
|
| 42 |
+
"type": "STATE",
|
| 43 |
+
"shape": [
|
| 44 |
+
6
|
| 45 |
+
]
|
| 46 |
+
},
|
| 47 |
+
"observation.images.camera1": {
|
| 48 |
+
"type": "VISUAL",
|
| 49 |
+
"shape": [
|
| 50 |
+
3,
|
| 51 |
+
256,
|
| 52 |
+
256
|
| 53 |
+
]
|
| 54 |
+
},
|
| 55 |
+
"observation.images.camera2": {
|
| 56 |
+
"type": "VISUAL",
|
| 57 |
+
"shape": [
|
| 58 |
+
3,
|
| 59 |
+
256,
|
| 60 |
+
256
|
| 61 |
+
]
|
| 62 |
+
},
|
| 63 |
+
"observation.images.camera3": {
|
| 64 |
+
"type": "VISUAL",
|
| 65 |
+
"shape": [
|
| 66 |
+
3,
|
| 67 |
+
256,
|
| 68 |
+
256
|
| 69 |
+
]
|
| 70 |
+
},
|
| 71 |
+
"action": {
|
| 72 |
+
"type": "ACTION",
|
| 73 |
+
"shape": [
|
| 74 |
+
6
|
| 75 |
+
]
|
| 76 |
+
}
|
| 77 |
+
},
|
| 78 |
+
"norm_map": {
|
| 79 |
+
"VISUAL": "IDENTITY",
|
| 80 |
+
"STATE": "MEAN_STD",
|
| 81 |
+
"ACTION": "MEAN_STD"
|
| 82 |
+
}
|
| 83 |
+
},
|
| 84 |
+
"state_file": "policy_preprocessor_step_5_normalizer_processor.safetensors"
|
| 85 |
+
}
|
| 86 |
+
]
|
| 87 |
+
}
|
checkpoints/030000/pretrained_model/policy_preprocessor_step_5_normalizer_processor.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7e560b7d5832bf20dfaa2db407540e3042344409d4fce910831109e0e74e7368
|
| 3 |
+
size 7592
|
checkpoints/030000/pretrained_model/train_config.json
ADDED
|
@@ -0,0 +1,239 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"dataset": {
|
| 3 |
+
"repo_id": "BrandonAL/my_sim_merged",
|
| 4 |
+
"root": null,
|
| 5 |
+
"episodes": null,
|
| 6 |
+
"image_transforms": {
|
| 7 |
+
"enable": true,
|
| 8 |
+
"max_num_transforms": 3,
|
| 9 |
+
"random_order": false,
|
| 10 |
+
"tfs": {
|
| 11 |
+
"brightness": {
|
| 12 |
+
"weight": 1.0,
|
| 13 |
+
"type": "ColorJitter",
|
| 14 |
+
"kwargs": {
|
| 15 |
+
"brightness": [
|
| 16 |
+
0.8,
|
| 17 |
+
1.2
|
| 18 |
+
]
|
| 19 |
+
}
|
| 20 |
+
},
|
| 21 |
+
"contrast": {
|
| 22 |
+
"weight": 1.0,
|
| 23 |
+
"type": "ColorJitter",
|
| 24 |
+
"kwargs": {
|
| 25 |
+
"contrast": [
|
| 26 |
+
0.8,
|
| 27 |
+
1.2
|
| 28 |
+
]
|
| 29 |
+
}
|
| 30 |
+
},
|
| 31 |
+
"saturation": {
|
| 32 |
+
"weight": 1.0,
|
| 33 |
+
"type": "ColorJitter",
|
| 34 |
+
"kwargs": {
|
| 35 |
+
"saturation": [
|
| 36 |
+
0.5,
|
| 37 |
+
1.5
|
| 38 |
+
]
|
| 39 |
+
}
|
| 40 |
+
},
|
| 41 |
+
"hue": {
|
| 42 |
+
"weight": 1.0,
|
| 43 |
+
"type": "ColorJitter",
|
| 44 |
+
"kwargs": {
|
| 45 |
+
"hue": [
|
| 46 |
+
-0.05,
|
| 47 |
+
0.05
|
| 48 |
+
]
|
| 49 |
+
}
|
| 50 |
+
},
|
| 51 |
+
"sharpness": {
|
| 52 |
+
"weight": 1.0,
|
| 53 |
+
"type": "SharpnessJitter",
|
| 54 |
+
"kwargs": {
|
| 55 |
+
"sharpness": [
|
| 56 |
+
0.5,
|
| 57 |
+
1.5
|
| 58 |
+
]
|
| 59 |
+
}
|
| 60 |
+
},
|
| 61 |
+
"affine": {
|
| 62 |
+
"weight": 1.0,
|
| 63 |
+
"type": "RandomAffine",
|
| 64 |
+
"kwargs": {
|
| 65 |
+
"degrees": [
|
| 66 |
+
-5.0,
|
| 67 |
+
5.0
|
| 68 |
+
],
|
| 69 |
+
"translate": [
|
| 70 |
+
0.05,
|
| 71 |
+
0.05
|
| 72 |
+
]
|
| 73 |
+
}
|
| 74 |
+
}
|
| 75 |
+
}
|
| 76 |
+
},
|
| 77 |
+
"revision": null,
|
| 78 |
+
"use_imagenet_stats": true,
|
| 79 |
+
"video_backend": "pyav",
|
| 80 |
+
"streaming": false
|
| 81 |
+
},
|
| 82 |
+
"env": null,
|
| 83 |
+
"policy": {
|
| 84 |
+
"type": "smolvla",
|
| 85 |
+
"n_obs_steps": 1,
|
| 86 |
+
"input_features": {
|
| 87 |
+
"observation.state": {
|
| 88 |
+
"type": "STATE",
|
| 89 |
+
"shape": [
|
| 90 |
+
6
|
| 91 |
+
]
|
| 92 |
+
},
|
| 93 |
+
"observation.images.camera1": {
|
| 94 |
+
"type": "VISUAL",
|
| 95 |
+
"shape": [
|
| 96 |
+
3,
|
| 97 |
+
256,
|
| 98 |
+
256
|
| 99 |
+
]
|
| 100 |
+
},
|
| 101 |
+
"observation.images.camera2": {
|
| 102 |
+
"type": "VISUAL",
|
| 103 |
+
"shape": [
|
| 104 |
+
3,
|
| 105 |
+
256,
|
| 106 |
+
256
|
| 107 |
+
]
|
| 108 |
+
},
|
| 109 |
+
"observation.images.camera3": {
|
| 110 |
+
"type": "VISUAL",
|
| 111 |
+
"shape": [
|
| 112 |
+
3,
|
| 113 |
+
256,
|
| 114 |
+
256
|
| 115 |
+
]
|
| 116 |
+
}
|
| 117 |
+
},
|
| 118 |
+
"output_features": {
|
| 119 |
+
"action": {
|
| 120 |
+
"type": "ACTION",
|
| 121 |
+
"shape": [
|
| 122 |
+
6
|
| 123 |
+
]
|
| 124 |
+
}
|
| 125 |
+
},
|
| 126 |
+
"device": "cuda",
|
| 127 |
+
"use_amp": false,
|
| 128 |
+
"use_peft": false,
|
| 129 |
+
"push_to_hub": true,
|
| 130 |
+
"repo_id": "BrandonAL/my_sim_smolvla_all_ft60k",
|
| 131 |
+
"private": null,
|
| 132 |
+
"tags": null,
|
| 133 |
+
"license": null,
|
| 134 |
+
"pretrained_path": "BrandonAL/my_sim_smolvla_all_step010000",
|
| 135 |
+
"chunk_size": 50,
|
| 136 |
+
"n_action_steps": 50,
|
| 137 |
+
"normalization_mapping": {
|
| 138 |
+
"VISUAL": "IDENTITY",
|
| 139 |
+
"STATE": "MEAN_STD",
|
| 140 |
+
"ACTION": "MEAN_STD"
|
| 141 |
+
},
|
| 142 |
+
"max_state_dim": 32,
|
| 143 |
+
"max_action_dim": 32,
|
| 144 |
+
"resize_imgs_with_padding": [
|
| 145 |
+
512,
|
| 146 |
+
512
|
| 147 |
+
],
|
| 148 |
+
"empty_cameras": 0,
|
| 149 |
+
"adapt_to_pi_aloha": false,
|
| 150 |
+
"use_delta_joint_actions_aloha": false,
|
| 151 |
+
"tokenizer_max_length": 48,
|
| 152 |
+
"num_steps": 10,
|
| 153 |
+
"use_cache": true,
|
| 154 |
+
"freeze_vision_encoder": true,
|
| 155 |
+
"train_expert_only": true,
|
| 156 |
+
"train_state_proj": true,
|
| 157 |
+
"optimizer_lr": 0.0001,
|
| 158 |
+
"optimizer_betas": [
|
| 159 |
+
0.9,
|
| 160 |
+
0.95
|
| 161 |
+
],
|
| 162 |
+
"optimizer_eps": 1e-08,
|
| 163 |
+
"optimizer_weight_decay": 1e-10,
|
| 164 |
+
"optimizer_grad_clip_norm": 10.0,
|
| 165 |
+
"scheduler_warmup_steps": 1000,
|
| 166 |
+
"scheduler_decay_steps": 30000,
|
| 167 |
+
"scheduler_decay_lr": 2.5e-06,
|
| 168 |
+
"vlm_model_name": "HuggingFaceTB/SmolVLM2-500M-Video-Instruct",
|
| 169 |
+
"load_vlm_weights": true,
|
| 170 |
+
"add_image_special_tokens": false,
|
| 171 |
+
"attention_mode": "cross_attn",
|
| 172 |
+
"prefix_length": 0,
|
| 173 |
+
"pad_language_to": "max_length",
|
| 174 |
+
"num_expert_layers": 0,
|
| 175 |
+
"num_vlm_layers": 16,
|
| 176 |
+
"self_attn_every_n_layers": 2,
|
| 177 |
+
"expert_width_multiplier": 0.75,
|
| 178 |
+
"min_period": 0.004,
|
| 179 |
+
"max_period": 4.0,
|
| 180 |
+
"rtc_config": null,
|
| 181 |
+
"compile_model": false,
|
| 182 |
+
"compile_mode": "max-autotune"
|
| 183 |
+
},
|
| 184 |
+
"output_dir": "outputs/train/my_sim_smolvla_all_ft60k",
|
| 185 |
+
"job_name": "my_smolvla_all_ft60k",
|
| 186 |
+
"resume": false,
|
| 187 |
+
"seed": 1000,
|
| 188 |
+
"cudnn_deterministic": false,
|
| 189 |
+
"num_workers": 4,
|
| 190 |
+
"batch_size": 64,
|
| 191 |
+
"steps": 50000,
|
| 192 |
+
"eval_freq": 20000,
|
| 193 |
+
"log_freq": 200,
|
| 194 |
+
"tolerance_s": 0.0001,
|
| 195 |
+
"save_checkpoint": true,
|
| 196 |
+
"save_freq": 10000,
|
| 197 |
+
"use_policy_training_preset": true,
|
| 198 |
+
"optimizer": {
|
| 199 |
+
"type": "adamw",
|
| 200 |
+
"lr": 0.0001,
|
| 201 |
+
"weight_decay": 1e-10,
|
| 202 |
+
"grad_clip_norm": 10.0,
|
| 203 |
+
"betas": [
|
| 204 |
+
0.9,
|
| 205 |
+
0.95
|
| 206 |
+
],
|
| 207 |
+
"eps": 1e-08
|
| 208 |
+
},
|
| 209 |
+
"scheduler": {
|
| 210 |
+
"type": "cosine_decay_with_warmup",
|
| 211 |
+
"num_warmup_steps": 1000,
|
| 212 |
+
"num_decay_steps": 30000,
|
| 213 |
+
"peak_lr": 0.0001,
|
| 214 |
+
"decay_lr": 2.5e-06
|
| 215 |
+
},
|
| 216 |
+
"eval": {
|
| 217 |
+
"n_episodes": 50,
|
| 218 |
+
"batch_size": 44,
|
| 219 |
+
"use_async_envs": true
|
| 220 |
+
},
|
| 221 |
+
"wandb": {
|
| 222 |
+
"enable": false,
|
| 223 |
+
"disable_artifact": false,
|
| 224 |
+
"project": "lerobot",
|
| 225 |
+
"entity": null,
|
| 226 |
+
"notes": null,
|
| 227 |
+
"run_id": null,
|
| 228 |
+
"mode": null,
|
| 229 |
+
"add_tags": true
|
| 230 |
+
},
|
| 231 |
+
"peft": null,
|
| 232 |
+
"use_rabc": false,
|
| 233 |
+
"rabc_progress_path": null,
|
| 234 |
+
"rabc_kappa": 0.01,
|
| 235 |
+
"rabc_epsilon": 1e-06,
|
| 236 |
+
"rabc_head_mode": "sparse",
|
| 237 |
+
"rename_map": {},
|
| 238 |
+
"checkpoint_path": null
|
| 239 |
+
}
|
checkpoints/030000/training_state/optimizer_param_groups.json
ADDED
|
@@ -0,0 +1,521 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[
|
| 2 |
+
{
|
| 3 |
+
"lr": 2.5e-06,
|
| 4 |
+
"betas": [
|
| 5 |
+
0.9,
|
| 6 |
+
0.95
|
| 7 |
+
],
|
| 8 |
+
"eps": 1e-08,
|
| 9 |
+
"weight_decay": 1e-10,
|
| 10 |
+
"amsgrad": false,
|
| 11 |
+
"maximize": false,
|
| 12 |
+
"foreach": null,
|
| 13 |
+
"capturable": false,
|
| 14 |
+
"differentiable": false,
|
| 15 |
+
"fused": null,
|
| 16 |
+
"decoupled_weight_decay": true,
|
| 17 |
+
"initial_lr": 0.0001,
|
| 18 |
+
"params": [
|
| 19 |
+
0,
|
| 20 |
+
1,
|
| 21 |
+
2,
|
| 22 |
+
3,
|
| 23 |
+
4,
|
| 24 |
+
5,
|
| 25 |
+
6,
|
| 26 |
+
7,
|
| 27 |
+
8,
|
| 28 |
+
9,
|
| 29 |
+
10,
|
| 30 |
+
11,
|
| 31 |
+
12,
|
| 32 |
+
13,
|
| 33 |
+
14,
|
| 34 |
+
15,
|
| 35 |
+
16,
|
| 36 |
+
17,
|
| 37 |
+
18,
|
| 38 |
+
19,
|
| 39 |
+
20,
|
| 40 |
+
21,
|
| 41 |
+
22,
|
| 42 |
+
23,
|
| 43 |
+
24,
|
| 44 |
+
25,
|
| 45 |
+
26,
|
| 46 |
+
27,
|
| 47 |
+
28,
|
| 48 |
+
29,
|
| 49 |
+
30,
|
| 50 |
+
31,
|
| 51 |
+
32,
|
| 52 |
+
33,
|
| 53 |
+
34,
|
| 54 |
+
35,
|
| 55 |
+
36,
|
| 56 |
+
37,
|
| 57 |
+
38,
|
| 58 |
+
39,
|
| 59 |
+
40,
|
| 60 |
+
41,
|
| 61 |
+
42,
|
| 62 |
+
43,
|
| 63 |
+
44,
|
| 64 |
+
45,
|
| 65 |
+
46,
|
| 66 |
+
47,
|
| 67 |
+
48,
|
| 68 |
+
49,
|
| 69 |
+
50,
|
| 70 |
+
51,
|
| 71 |
+
52,
|
| 72 |
+
53,
|
| 73 |
+
54,
|
| 74 |
+
55,
|
| 75 |
+
56,
|
| 76 |
+
57,
|
| 77 |
+
58,
|
| 78 |
+
59,
|
| 79 |
+
60,
|
| 80 |
+
61,
|
| 81 |
+
62,
|
| 82 |
+
63,
|
| 83 |
+
64,
|
| 84 |
+
65,
|
| 85 |
+
66,
|
| 86 |
+
67,
|
| 87 |
+
68,
|
| 88 |
+
69,
|
| 89 |
+
70,
|
| 90 |
+
71,
|
| 91 |
+
72,
|
| 92 |
+
73,
|
| 93 |
+
74,
|
| 94 |
+
75,
|
| 95 |
+
76,
|
| 96 |
+
77,
|
| 97 |
+
78,
|
| 98 |
+
79,
|
| 99 |
+
80,
|
| 100 |
+
81,
|
| 101 |
+
82,
|
| 102 |
+
83,
|
| 103 |
+
84,
|
| 104 |
+
85,
|
| 105 |
+
86,
|
| 106 |
+
87,
|
| 107 |
+
88,
|
| 108 |
+
89,
|
| 109 |
+
90,
|
| 110 |
+
91,
|
| 111 |
+
92,
|
| 112 |
+
93,
|
| 113 |
+
94,
|
| 114 |
+
95,
|
| 115 |
+
96,
|
| 116 |
+
97,
|
| 117 |
+
98,
|
| 118 |
+
99,
|
| 119 |
+
100,
|
| 120 |
+
101,
|
| 121 |
+
102,
|
| 122 |
+
103,
|
| 123 |
+
104,
|
| 124 |
+
105,
|
| 125 |
+
106,
|
| 126 |
+
107,
|
| 127 |
+
108,
|
| 128 |
+
109,
|
| 129 |
+
110,
|
| 130 |
+
111,
|
| 131 |
+
112,
|
| 132 |
+
113,
|
| 133 |
+
114,
|
| 134 |
+
115,
|
| 135 |
+
116,
|
| 136 |
+
117,
|
| 137 |
+
118,
|
| 138 |
+
119,
|
| 139 |
+
120,
|
| 140 |
+
121,
|
| 141 |
+
122,
|
| 142 |
+
123,
|
| 143 |
+
124,
|
| 144 |
+
125,
|
| 145 |
+
126,
|
| 146 |
+
127,
|
| 147 |
+
128,
|
| 148 |
+
129,
|
| 149 |
+
130,
|
| 150 |
+
131,
|
| 151 |
+
132,
|
| 152 |
+
133,
|
| 153 |
+
134,
|
| 154 |
+
135,
|
| 155 |
+
136,
|
| 156 |
+
137,
|
| 157 |
+
138,
|
| 158 |
+
139,
|
| 159 |
+
140,
|
| 160 |
+
141,
|
| 161 |
+
142,
|
| 162 |
+
143,
|
| 163 |
+
144,
|
| 164 |
+
145,
|
| 165 |
+
146,
|
| 166 |
+
147,
|
| 167 |
+
148,
|
| 168 |
+
149,
|
| 169 |
+
150,
|
| 170 |
+
151,
|
| 171 |
+
152,
|
| 172 |
+
153,
|
| 173 |
+
154,
|
| 174 |
+
155,
|
| 175 |
+
156,
|
| 176 |
+
157,
|
| 177 |
+
158,
|
| 178 |
+
159,
|
| 179 |
+
160,
|
| 180 |
+
161,
|
| 181 |
+
162,
|
| 182 |
+
163,
|
| 183 |
+
164,
|
| 184 |
+
165,
|
| 185 |
+
166,
|
| 186 |
+
167,
|
| 187 |
+
168,
|
| 188 |
+
169,
|
| 189 |
+
170,
|
| 190 |
+
171,
|
| 191 |
+
172,
|
| 192 |
+
173,
|
| 193 |
+
174,
|
| 194 |
+
175,
|
| 195 |
+
176,
|
| 196 |
+
177,
|
| 197 |
+
178,
|
| 198 |
+
179,
|
| 199 |
+
180,
|
| 200 |
+
181,
|
| 201 |
+
182,
|
| 202 |
+
183,
|
| 203 |
+
184,
|
| 204 |
+
185,
|
| 205 |
+
186,
|
| 206 |
+
187,
|
| 207 |
+
188,
|
| 208 |
+
189,
|
| 209 |
+
190,
|
| 210 |
+
191,
|
| 211 |
+
192,
|
| 212 |
+
193,
|
| 213 |
+
194,
|
| 214 |
+
195,
|
| 215 |
+
196,
|
| 216 |
+
197,
|
| 217 |
+
198,
|
| 218 |
+
199,
|
| 219 |
+
200,
|
| 220 |
+
201,
|
| 221 |
+
202,
|
| 222 |
+
203,
|
| 223 |
+
204,
|
| 224 |
+
205,
|
| 225 |
+
206,
|
| 226 |
+
207,
|
| 227 |
+
208,
|
| 228 |
+
209,
|
| 229 |
+
210,
|
| 230 |
+
211,
|
| 231 |
+
212,
|
| 232 |
+
213,
|
| 233 |
+
214,
|
| 234 |
+
215,
|
| 235 |
+
216,
|
| 236 |
+
217,
|
| 237 |
+
218,
|
| 238 |
+
219,
|
| 239 |
+
220,
|
| 240 |
+
221,
|
| 241 |
+
222,
|
| 242 |
+
223,
|
| 243 |
+
224,
|
| 244 |
+
225,
|
| 245 |
+
226,
|
| 246 |
+
227,
|
| 247 |
+
228,
|
| 248 |
+
229,
|
| 249 |
+
230,
|
| 250 |
+
231,
|
| 251 |
+
232,
|
| 252 |
+
233,
|
| 253 |
+
234,
|
| 254 |
+
235,
|
| 255 |
+
236,
|
| 256 |
+
237,
|
| 257 |
+
238,
|
| 258 |
+
239,
|
| 259 |
+
240,
|
| 260 |
+
241,
|
| 261 |
+
242,
|
| 262 |
+
243,
|
| 263 |
+
244,
|
| 264 |
+
245,
|
| 265 |
+
246,
|
| 266 |
+
247,
|
| 267 |
+
248,
|
| 268 |
+
249,
|
| 269 |
+
250,
|
| 270 |
+
251,
|
| 271 |
+
252,
|
| 272 |
+
253,
|
| 273 |
+
254,
|
| 274 |
+
255,
|
| 275 |
+
256,
|
| 276 |
+
257,
|
| 277 |
+
258,
|
| 278 |
+
259,
|
| 279 |
+
260,
|
| 280 |
+
261,
|
| 281 |
+
262,
|
| 282 |
+
263,
|
| 283 |
+
264,
|
| 284 |
+
265,
|
| 285 |
+
266,
|
| 286 |
+
267,
|
| 287 |
+
268,
|
| 288 |
+
269,
|
| 289 |
+
270,
|
| 290 |
+
271,
|
| 291 |
+
272,
|
| 292 |
+
273,
|
| 293 |
+
274,
|
| 294 |
+
275,
|
| 295 |
+
276,
|
| 296 |
+
277,
|
| 297 |
+
278,
|
| 298 |
+
279,
|
| 299 |
+
280,
|
| 300 |
+
281,
|
| 301 |
+
282,
|
| 302 |
+
283,
|
| 303 |
+
284,
|
| 304 |
+
285,
|
| 305 |
+
286,
|
| 306 |
+
287,
|
| 307 |
+
288,
|
| 308 |
+
289,
|
| 309 |
+
290,
|
| 310 |
+
291,
|
| 311 |
+
292,
|
| 312 |
+
293,
|
| 313 |
+
294,
|
| 314 |
+
295,
|
| 315 |
+
296,
|
| 316 |
+
297,
|
| 317 |
+
298,
|
| 318 |
+
299,
|
| 319 |
+
300,
|
| 320 |
+
301,
|
| 321 |
+
302,
|
| 322 |
+
303,
|
| 323 |
+
304,
|
| 324 |
+
305,
|
| 325 |
+
306,
|
| 326 |
+
307,
|
| 327 |
+
308,
|
| 328 |
+
309,
|
| 329 |
+
310,
|
| 330 |
+
311,
|
| 331 |
+
312,
|
| 332 |
+
313,
|
| 333 |
+
314,
|
| 334 |
+
315,
|
| 335 |
+
316,
|
| 336 |
+
317,
|
| 337 |
+
318,
|
| 338 |
+
319,
|
| 339 |
+
320,
|
| 340 |
+
321,
|
| 341 |
+
322,
|
| 342 |
+
323,
|
| 343 |
+
324,
|
| 344 |
+
325,
|
| 345 |
+
326,
|
| 346 |
+
327,
|
| 347 |
+
328,
|
| 348 |
+
329,
|
| 349 |
+
330,
|
| 350 |
+
331,
|
| 351 |
+
332,
|
| 352 |
+
333,
|
| 353 |
+
334,
|
| 354 |
+
335,
|
| 355 |
+
336,
|
| 356 |
+
337,
|
| 357 |
+
338,
|
| 358 |
+
339,
|
| 359 |
+
340,
|
| 360 |
+
341,
|
| 361 |
+
342,
|
| 362 |
+
343,
|
| 363 |
+
344,
|
| 364 |
+
345,
|
| 365 |
+
346,
|
| 366 |
+
347,
|
| 367 |
+
348,
|
| 368 |
+
349,
|
| 369 |
+
350,
|
| 370 |
+
351,
|
| 371 |
+
352,
|
| 372 |
+
353,
|
| 373 |
+
354,
|
| 374 |
+
355,
|
| 375 |
+
356,
|
| 376 |
+
357,
|
| 377 |
+
358,
|
| 378 |
+
359,
|
| 379 |
+
360,
|
| 380 |
+
361,
|
| 381 |
+
362,
|
| 382 |
+
363,
|
| 383 |
+
364,
|
| 384 |
+
365,
|
| 385 |
+
366,
|
| 386 |
+
367,
|
| 387 |
+
368,
|
| 388 |
+
369,
|
| 389 |
+
370,
|
| 390 |
+
371,
|
| 391 |
+
372,
|
| 392 |
+
373,
|
| 393 |
+
374,
|
| 394 |
+
375,
|
| 395 |
+
376,
|
| 396 |
+
377,
|
| 397 |
+
378,
|
| 398 |
+
379,
|
| 399 |
+
380,
|
| 400 |
+
381,
|
| 401 |
+
382,
|
| 402 |
+
383,
|
| 403 |
+
384,
|
| 404 |
+
385,
|
| 405 |
+
386,
|
| 406 |
+
387,
|
| 407 |
+
388,
|
| 408 |
+
389,
|
| 409 |
+
390,
|
| 410 |
+
391,
|
| 411 |
+
392,
|
| 412 |
+
393,
|
| 413 |
+
394,
|
| 414 |
+
395,
|
| 415 |
+
396,
|
| 416 |
+
397,
|
| 417 |
+
398,
|
| 418 |
+
399,
|
| 419 |
+
400,
|
| 420 |
+
401,
|
| 421 |
+
402,
|
| 422 |
+
403,
|
| 423 |
+
404,
|
| 424 |
+
405,
|
| 425 |
+
406,
|
| 426 |
+
407,
|
| 427 |
+
408,
|
| 428 |
+
409,
|
| 429 |
+
410,
|
| 430 |
+
411,
|
| 431 |
+
412,
|
| 432 |
+
413,
|
| 433 |
+
414,
|
| 434 |
+
415,
|
| 435 |
+
416,
|
| 436 |
+
417,
|
| 437 |
+
418,
|
| 438 |
+
419,
|
| 439 |
+
420,
|
| 440 |
+
421,
|
| 441 |
+
422,
|
| 442 |
+
423,
|
| 443 |
+
424,
|
| 444 |
+
425,
|
| 445 |
+
426,
|
| 446 |
+
427,
|
| 447 |
+
428,
|
| 448 |
+
429,
|
| 449 |
+
430,
|
| 450 |
+
431,
|
| 451 |
+
432,
|
| 452 |
+
433,
|
| 453 |
+
434,
|
| 454 |
+
435,
|
| 455 |
+
436,
|
| 456 |
+
437,
|
| 457 |
+
438,
|
| 458 |
+
439,
|
| 459 |
+
440,
|
| 460 |
+
441,
|
| 461 |
+
442,
|
| 462 |
+
443,
|
| 463 |
+
444,
|
| 464 |
+
445,
|
| 465 |
+
446,
|
| 466 |
+
447,
|
| 467 |
+
448,
|
| 468 |
+
449,
|
| 469 |
+
450,
|
| 470 |
+
451,
|
| 471 |
+
452,
|
| 472 |
+
453,
|
| 473 |
+
454,
|
| 474 |
+
455,
|
| 475 |
+
456,
|
| 476 |
+
457,
|
| 477 |
+
458,
|
| 478 |
+
459,
|
| 479 |
+
460,
|
| 480 |
+
461,
|
| 481 |
+
462,
|
| 482 |
+
463,
|
| 483 |
+
464,
|
| 484 |
+
465,
|
| 485 |
+
466,
|
| 486 |
+
467,
|
| 487 |
+
468,
|
| 488 |
+
469,
|
| 489 |
+
470,
|
| 490 |
+
471,
|
| 491 |
+
472,
|
| 492 |
+
473,
|
| 493 |
+
474,
|
| 494 |
+
475,
|
| 495 |
+
476,
|
| 496 |
+
477,
|
| 497 |
+
478,
|
| 498 |
+
479,
|
| 499 |
+
480,
|
| 500 |
+
481,
|
| 501 |
+
482,
|
| 502 |
+
483,
|
| 503 |
+
484,
|
| 504 |
+
485,
|
| 505 |
+
486,
|
| 506 |
+
487,
|
| 507 |
+
488,
|
| 508 |
+
489,
|
| 509 |
+
490,
|
| 510 |
+
491,
|
| 511 |
+
492,
|
| 512 |
+
493,
|
| 513 |
+
494,
|
| 514 |
+
495,
|
| 515 |
+
496,
|
| 516 |
+
497,
|
| 517 |
+
498,
|
| 518 |
+
499
|
| 519 |
+
]
|
| 520 |
+
}
|
| 521 |
+
]
|
checkpoints/030000/training_state/optimizer_state.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:611cebea1b9f41be0ff8b62010a09a322b0e4d275119c1070cd473188e75e9d6
|
| 3 |
+
size 412659164
|
checkpoints/030000/training_state/rng_state.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7c012492736ba4a290dcc25115e88e9c7a5760ee4c844d5cc23defd261392092
|
| 3 |
+
size 15708
|
checkpoints/030000/training_state/scheduler_state.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"base_lrs": [
|
| 3 |
+
0.0001
|
| 4 |
+
],
|
| 5 |
+
"last_epoch": 30000,
|
| 6 |
+
"_step_count": 30001,
|
| 7 |
+
"_is_initial": false,
|
| 8 |
+
"_get_lr_called_within_step": false,
|
| 9 |
+
"_last_lr": [
|
| 10 |
+
2.5e-06
|
| 11 |
+
],
|
| 12 |
+
"lr_lambdas": [
|
| 13 |
+
null
|
| 14 |
+
]
|
| 15 |
+
}
|
checkpoints/030000/training_state/training_step.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"step": 30000
|
| 3 |
+
}
|
checkpoints/040000/pretrained_model/config.json
ADDED
|
@@ -0,0 +1,101 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"type": "smolvla",
|
| 3 |
+
"n_obs_steps": 1,
|
| 4 |
+
"input_features": {
|
| 5 |
+
"observation.state": {
|
| 6 |
+
"type": "STATE",
|
| 7 |
+
"shape": [
|
| 8 |
+
6
|
| 9 |
+
]
|
| 10 |
+
},
|
| 11 |
+
"observation.images.camera1": {
|
| 12 |
+
"type": "VISUAL",
|
| 13 |
+
"shape": [
|
| 14 |
+
3,
|
| 15 |
+
256,
|
| 16 |
+
256
|
| 17 |
+
]
|
| 18 |
+
},
|
| 19 |
+
"observation.images.camera2": {
|
| 20 |
+
"type": "VISUAL",
|
| 21 |
+
"shape": [
|
| 22 |
+
3,
|
| 23 |
+
256,
|
| 24 |
+
256
|
| 25 |
+
]
|
| 26 |
+
},
|
| 27 |
+
"observation.images.camera3": {
|
| 28 |
+
"type": "VISUAL",
|
| 29 |
+
"shape": [
|
| 30 |
+
3,
|
| 31 |
+
256,
|
| 32 |
+
256
|
| 33 |
+
]
|
| 34 |
+
}
|
| 35 |
+
},
|
| 36 |
+
"output_features": {
|
| 37 |
+
"action": {
|
| 38 |
+
"type": "ACTION",
|
| 39 |
+
"shape": [
|
| 40 |
+
6
|
| 41 |
+
]
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"device": "cuda",
|
| 45 |
+
"use_amp": false,
|
| 46 |
+
"use_peft": false,
|
| 47 |
+
"push_to_hub": true,
|
| 48 |
+
"repo_id": "BrandonAL/my_sim_smolvla_all_ft60k",
|
| 49 |
+
"private": null,
|
| 50 |
+
"tags": null,
|
| 51 |
+
"license": null,
|
| 52 |
+
"pretrained_path": "BrandonAL/my_sim_smolvla_all_step010000",
|
| 53 |
+
"chunk_size": 50,
|
| 54 |
+
"n_action_steps": 50,
|
| 55 |
+
"normalization_mapping": {
|
| 56 |
+
"VISUAL": "IDENTITY",
|
| 57 |
+
"STATE": "MEAN_STD",
|
| 58 |
+
"ACTION": "MEAN_STD"
|
| 59 |
+
},
|
| 60 |
+
"max_state_dim": 32,
|
| 61 |
+
"max_action_dim": 32,
|
| 62 |
+
"resize_imgs_with_padding": [
|
| 63 |
+
512,
|
| 64 |
+
512
|
| 65 |
+
],
|
| 66 |
+
"empty_cameras": 0,
|
| 67 |
+
"adapt_to_pi_aloha": false,
|
| 68 |
+
"use_delta_joint_actions_aloha": false,
|
| 69 |
+
"tokenizer_max_length": 48,
|
| 70 |
+
"num_steps": 10,
|
| 71 |
+
"use_cache": true,
|
| 72 |
+
"freeze_vision_encoder": true,
|
| 73 |
+
"train_expert_only": true,
|
| 74 |
+
"train_state_proj": true,
|
| 75 |
+
"optimizer_lr": 0.0001,
|
| 76 |
+
"optimizer_betas": [
|
| 77 |
+
0.9,
|
| 78 |
+
0.95
|
| 79 |
+
],
|
| 80 |
+
"optimizer_eps": 1e-08,
|
| 81 |
+
"optimizer_weight_decay": 1e-10,
|
| 82 |
+
"optimizer_grad_clip_norm": 10.0,
|
| 83 |
+
"scheduler_warmup_steps": 1000,
|
| 84 |
+
"scheduler_decay_steps": 30000,
|
| 85 |
+
"scheduler_decay_lr": 2.5e-06,
|
| 86 |
+
"vlm_model_name": "HuggingFaceTB/SmolVLM2-500M-Video-Instruct",
|
| 87 |
+
"load_vlm_weights": true,
|
| 88 |
+
"add_image_special_tokens": false,
|
| 89 |
+
"attention_mode": "cross_attn",
|
| 90 |
+
"prefix_length": 0,
|
| 91 |
+
"pad_language_to": "max_length",
|
| 92 |
+
"num_expert_layers": 0,
|
| 93 |
+
"num_vlm_layers": 16,
|
| 94 |
+
"self_attn_every_n_layers": 2,
|
| 95 |
+
"expert_width_multiplier": 0.75,
|
| 96 |
+
"min_period": 0.004,
|
| 97 |
+
"max_period": 4.0,
|
| 98 |
+
"rtc_config": null,
|
| 99 |
+
"compile_model": false,
|
| 100 |
+
"compile_mode": "max-autotune"
|
| 101 |
+
}
|
checkpoints/040000/pretrained_model/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:460f16b9c8ded40a592d33e2d8687c97485806f91c90a9dde18d2294404132cb
|
| 3 |
+
size 906712520
|
checkpoints/040000/pretrained_model/policy_postprocessor.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"name": "policy_postprocessor",
|
| 3 |
+
"steps": [
|
| 4 |
+
{
|
| 5 |
+
"registry_name": "unnormalizer_processor",
|
| 6 |
+
"config": {
|
| 7 |
+
"eps": 1e-08,
|
| 8 |
+
"features": {
|
| 9 |
+
"action": {
|
| 10 |
+
"type": "ACTION",
|
| 11 |
+
"shape": [
|
| 12 |
+
6
|
| 13 |
+
]
|
| 14 |
+
}
|
| 15 |
+
},
|
| 16 |
+
"norm_map": {
|
| 17 |
+
"VISUAL": "IDENTITY",
|
| 18 |
+
"STATE": "MEAN_STD",
|
| 19 |
+
"ACTION": "MEAN_STD"
|
| 20 |
+
}
|
| 21 |
+
},
|
| 22 |
+
"state_file": "policy_postprocessor_step_0_unnormalizer_processor.safetensors"
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"registry_name": "device_processor",
|
| 26 |
+
"config": {
|
| 27 |
+
"device": "cpu",
|
| 28 |
+
"float_dtype": null
|
| 29 |
+
}
|
| 30 |
+
}
|
| 31 |
+
]
|
| 32 |
+
}
|
checkpoints/040000/pretrained_model/policy_postprocessor_step_0_unnormalizer_processor.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7e560b7d5832bf20dfaa2db407540e3042344409d4fce910831109e0e74e7368
|
| 3 |
+
size 7592
|
checkpoints/040000/pretrained_model/policy_preprocessor.json
ADDED
|
@@ -0,0 +1,87 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"name": "policy_preprocessor",
|
| 3 |
+
"steps": [
|
| 4 |
+
{
|
| 5 |
+
"registry_name": "rename_observations_processor",
|
| 6 |
+
"config": {
|
| 7 |
+
"rename_map": {}
|
| 8 |
+
}
|
| 9 |
+
},
|
| 10 |
+
{
|
| 11 |
+
"registry_name": "to_batch_processor",
|
| 12 |
+
"config": {}
|
| 13 |
+
},
|
| 14 |
+
{
|
| 15 |
+
"registry_name": "smolvla_new_line_processor",
|
| 16 |
+
"config": {}
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"registry_name": "tokenizer_processor",
|
| 20 |
+
"config": {
|
| 21 |
+
"max_length": 48,
|
| 22 |
+
"task_key": "task",
|
| 23 |
+
"padding_side": "right",
|
| 24 |
+
"padding": "max_length",
|
| 25 |
+
"truncation": true,
|
| 26 |
+
"tokenizer_name": "HuggingFaceTB/SmolVLM2-500M-Video-Instruct"
|
| 27 |
+
}
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"registry_name": "device_processor",
|
| 31 |
+
"config": {
|
| 32 |
+
"device": "cuda",
|
| 33 |
+
"float_dtype": null
|
| 34 |
+
}
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"registry_name": "normalizer_processor",
|
| 38 |
+
"config": {
|
| 39 |
+
"eps": 1e-08,
|
| 40 |
+
"features": {
|
| 41 |
+
"observation.state": {
|
| 42 |
+
"type": "STATE",
|
| 43 |
+
"shape": [
|
| 44 |
+
6
|
| 45 |
+
]
|
| 46 |
+
},
|
| 47 |
+
"observation.images.camera1": {
|
| 48 |
+
"type": "VISUAL",
|
| 49 |
+
"shape": [
|
| 50 |
+
3,
|
| 51 |
+
256,
|
| 52 |
+
256
|
| 53 |
+
]
|
| 54 |
+
},
|
| 55 |
+
"observation.images.camera2": {
|
| 56 |
+
"type": "VISUAL",
|
| 57 |
+
"shape": [
|
| 58 |
+
3,
|
| 59 |
+
256,
|
| 60 |
+
256
|
| 61 |
+
]
|
| 62 |
+
},
|
| 63 |
+
"observation.images.camera3": {
|
| 64 |
+
"type": "VISUAL",
|
| 65 |
+
"shape": [
|
| 66 |
+
3,
|
| 67 |
+
256,
|
| 68 |
+
256
|
| 69 |
+
]
|
| 70 |
+
},
|
| 71 |
+
"action": {
|
| 72 |
+
"type": "ACTION",
|
| 73 |
+
"shape": [
|
| 74 |
+
6
|
| 75 |
+
]
|
| 76 |
+
}
|
| 77 |
+
},
|
| 78 |
+
"norm_map": {
|
| 79 |
+
"VISUAL": "IDENTITY",
|
| 80 |
+
"STATE": "MEAN_STD",
|
| 81 |
+
"ACTION": "MEAN_STD"
|
| 82 |
+
}
|
| 83 |
+
},
|
| 84 |
+
"state_file": "policy_preprocessor_step_5_normalizer_processor.safetensors"
|
| 85 |
+
}
|
| 86 |
+
]
|
| 87 |
+
}
|
checkpoints/040000/pretrained_model/policy_preprocessor_step_5_normalizer_processor.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7e560b7d5832bf20dfaa2db407540e3042344409d4fce910831109e0e74e7368
|
| 3 |
+
size 7592
|
checkpoints/040000/pretrained_model/train_config.json
ADDED
|
@@ -0,0 +1,239 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"dataset": {
|
| 3 |
+
"repo_id": "BrandonAL/my_sim_merged",
|
| 4 |
+
"root": null,
|
| 5 |
+
"episodes": null,
|
| 6 |
+
"image_transforms": {
|
| 7 |
+
"enable": true,
|
| 8 |
+
"max_num_transforms": 3,
|
| 9 |
+
"random_order": false,
|
| 10 |
+
"tfs": {
|
| 11 |
+
"brightness": {
|
| 12 |
+
"weight": 1.0,
|
| 13 |
+
"type": "ColorJitter",
|
| 14 |
+
"kwargs": {
|
| 15 |
+
"brightness": [
|
| 16 |
+
0.8,
|
| 17 |
+
1.2
|
| 18 |
+
]
|
| 19 |
+
}
|
| 20 |
+
},
|
| 21 |
+
"contrast": {
|
| 22 |
+
"weight": 1.0,
|
| 23 |
+
"type": "ColorJitter",
|
| 24 |
+
"kwargs": {
|
| 25 |
+
"contrast": [
|
| 26 |
+
0.8,
|
| 27 |
+
1.2
|
| 28 |
+
]
|
| 29 |
+
}
|
| 30 |
+
},
|
| 31 |
+
"saturation": {
|
| 32 |
+
"weight": 1.0,
|
| 33 |
+
"type": "ColorJitter",
|
| 34 |
+
"kwargs": {
|
| 35 |
+
"saturation": [
|
| 36 |
+
0.5,
|
| 37 |
+
1.5
|
| 38 |
+
]
|
| 39 |
+
}
|
| 40 |
+
},
|
| 41 |
+
"hue": {
|
| 42 |
+
"weight": 1.0,
|
| 43 |
+
"type": "ColorJitter",
|
| 44 |
+
"kwargs": {
|
| 45 |
+
"hue": [
|
| 46 |
+
-0.05,
|
| 47 |
+
0.05
|
| 48 |
+
]
|
| 49 |
+
}
|
| 50 |
+
},
|
| 51 |
+
"sharpness": {
|
| 52 |
+
"weight": 1.0,
|
| 53 |
+
"type": "SharpnessJitter",
|
| 54 |
+
"kwargs": {
|
| 55 |
+
"sharpness": [
|
| 56 |
+
0.5,
|
| 57 |
+
1.5
|
| 58 |
+
]
|
| 59 |
+
}
|
| 60 |
+
},
|
| 61 |
+
"affine": {
|
| 62 |
+
"weight": 1.0,
|
| 63 |
+
"type": "RandomAffine",
|
| 64 |
+
"kwargs": {
|
| 65 |
+
"degrees": [
|
| 66 |
+
-5.0,
|
| 67 |
+
5.0
|
| 68 |
+
],
|
| 69 |
+
"translate": [
|
| 70 |
+
0.05,
|
| 71 |
+
0.05
|
| 72 |
+
]
|
| 73 |
+
}
|
| 74 |
+
}
|
| 75 |
+
}
|
| 76 |
+
},
|
| 77 |
+
"revision": null,
|
| 78 |
+
"use_imagenet_stats": true,
|
| 79 |
+
"video_backend": "pyav",
|
| 80 |
+
"streaming": false
|
| 81 |
+
},
|
| 82 |
+
"env": null,
|
| 83 |
+
"policy": {
|
| 84 |
+
"type": "smolvla",
|
| 85 |
+
"n_obs_steps": 1,
|
| 86 |
+
"input_features": {
|
| 87 |
+
"observation.state": {
|
| 88 |
+
"type": "STATE",
|
| 89 |
+
"shape": [
|
| 90 |
+
6
|
| 91 |
+
]
|
| 92 |
+
},
|
| 93 |
+
"observation.images.camera1": {
|
| 94 |
+
"type": "VISUAL",
|
| 95 |
+
"shape": [
|
| 96 |
+
3,
|
| 97 |
+
256,
|
| 98 |
+
256
|
| 99 |
+
]
|
| 100 |
+
},
|
| 101 |
+
"observation.images.camera2": {
|
| 102 |
+
"type": "VISUAL",
|
| 103 |
+
"shape": [
|
| 104 |
+
3,
|
| 105 |
+
256,
|
| 106 |
+
256
|
| 107 |
+
]
|
| 108 |
+
},
|
| 109 |
+
"observation.images.camera3": {
|
| 110 |
+
"type": "VISUAL",
|
| 111 |
+
"shape": [
|
| 112 |
+
3,
|
| 113 |
+
256,
|
| 114 |
+
256
|
| 115 |
+
]
|
| 116 |
+
}
|
| 117 |
+
},
|
| 118 |
+
"output_features": {
|
| 119 |
+
"action": {
|
| 120 |
+
"type": "ACTION",
|
| 121 |
+
"shape": [
|
| 122 |
+
6
|
| 123 |
+
]
|
| 124 |
+
}
|
| 125 |
+
},
|
| 126 |
+
"device": "cuda",
|
| 127 |
+
"use_amp": false,
|
| 128 |
+
"use_peft": false,
|
| 129 |
+
"push_to_hub": true,
|
| 130 |
+
"repo_id": "BrandonAL/my_sim_smolvla_all_ft60k",
|
| 131 |
+
"private": null,
|
| 132 |
+
"tags": null,
|
| 133 |
+
"license": null,
|
| 134 |
+
"pretrained_path": "BrandonAL/my_sim_smolvla_all_step010000",
|
| 135 |
+
"chunk_size": 50,
|
| 136 |
+
"n_action_steps": 50,
|
| 137 |
+
"normalization_mapping": {
|
| 138 |
+
"VISUAL": "IDENTITY",
|
| 139 |
+
"STATE": "MEAN_STD",
|
| 140 |
+
"ACTION": "MEAN_STD"
|
| 141 |
+
},
|
| 142 |
+
"max_state_dim": 32,
|
| 143 |
+
"max_action_dim": 32,
|
| 144 |
+
"resize_imgs_with_padding": [
|
| 145 |
+
512,
|
| 146 |
+
512
|
| 147 |
+
],
|
| 148 |
+
"empty_cameras": 0,
|
| 149 |
+
"adapt_to_pi_aloha": false,
|
| 150 |
+
"use_delta_joint_actions_aloha": false,
|
| 151 |
+
"tokenizer_max_length": 48,
|
| 152 |
+
"num_steps": 10,
|
| 153 |
+
"use_cache": true,
|
| 154 |
+
"freeze_vision_encoder": true,
|
| 155 |
+
"train_expert_only": true,
|
| 156 |
+
"train_state_proj": true,
|
| 157 |
+
"optimizer_lr": 0.0001,
|
| 158 |
+
"optimizer_betas": [
|
| 159 |
+
0.9,
|
| 160 |
+
0.95
|
| 161 |
+
],
|
| 162 |
+
"optimizer_eps": 1e-08,
|
| 163 |
+
"optimizer_weight_decay": 1e-10,
|
| 164 |
+
"optimizer_grad_clip_norm": 10.0,
|
| 165 |
+
"scheduler_warmup_steps": 1000,
|
| 166 |
+
"scheduler_decay_steps": 30000,
|
| 167 |
+
"scheduler_decay_lr": 2.5e-06,
|
| 168 |
+
"vlm_model_name": "HuggingFaceTB/SmolVLM2-500M-Video-Instruct",
|
| 169 |
+
"load_vlm_weights": true,
|
| 170 |
+
"add_image_special_tokens": false,
|
| 171 |
+
"attention_mode": "cross_attn",
|
| 172 |
+
"prefix_length": 0,
|
| 173 |
+
"pad_language_to": "max_length",
|
| 174 |
+
"num_expert_layers": 0,
|
| 175 |
+
"num_vlm_layers": 16,
|
| 176 |
+
"self_attn_every_n_layers": 2,
|
| 177 |
+
"expert_width_multiplier": 0.75,
|
| 178 |
+
"min_period": 0.004,
|
| 179 |
+
"max_period": 4.0,
|
| 180 |
+
"rtc_config": null,
|
| 181 |
+
"compile_model": false,
|
| 182 |
+
"compile_mode": "max-autotune"
|
| 183 |
+
},
|
| 184 |
+
"output_dir": "outputs/train/my_sim_smolvla_all_ft60k",
|
| 185 |
+
"job_name": "my_smolvla_all_ft60k",
|
| 186 |
+
"resume": false,
|
| 187 |
+
"seed": 1000,
|
| 188 |
+
"cudnn_deterministic": false,
|
| 189 |
+
"num_workers": 4,
|
| 190 |
+
"batch_size": 64,
|
| 191 |
+
"steps": 50000,
|
| 192 |
+
"eval_freq": 20000,
|
| 193 |
+
"log_freq": 200,
|
| 194 |
+
"tolerance_s": 0.0001,
|
| 195 |
+
"save_checkpoint": true,
|
| 196 |
+
"save_freq": 10000,
|
| 197 |
+
"use_policy_training_preset": true,
|
| 198 |
+
"optimizer": {
|
| 199 |
+
"type": "adamw",
|
| 200 |
+
"lr": 0.0001,
|
| 201 |
+
"weight_decay": 1e-10,
|
| 202 |
+
"grad_clip_norm": 10.0,
|
| 203 |
+
"betas": [
|
| 204 |
+
0.9,
|
| 205 |
+
0.95
|
| 206 |
+
],
|
| 207 |
+
"eps": 1e-08
|
| 208 |
+
},
|
| 209 |
+
"scheduler": {
|
| 210 |
+
"type": "cosine_decay_with_warmup",
|
| 211 |
+
"num_warmup_steps": 1000,
|
| 212 |
+
"num_decay_steps": 30000,
|
| 213 |
+
"peak_lr": 0.0001,
|
| 214 |
+
"decay_lr": 2.5e-06
|
| 215 |
+
},
|
| 216 |
+
"eval": {
|
| 217 |
+
"n_episodes": 50,
|
| 218 |
+
"batch_size": 44,
|
| 219 |
+
"use_async_envs": true
|
| 220 |
+
},
|
| 221 |
+
"wandb": {
|
| 222 |
+
"enable": false,
|
| 223 |
+
"disable_artifact": false,
|
| 224 |
+
"project": "lerobot",
|
| 225 |
+
"entity": null,
|
| 226 |
+
"notes": null,
|
| 227 |
+
"run_id": null,
|
| 228 |
+
"mode": null,
|
| 229 |
+
"add_tags": true
|
| 230 |
+
},
|
| 231 |
+
"peft": null,
|
| 232 |
+
"use_rabc": false,
|
| 233 |
+
"rabc_progress_path": null,
|
| 234 |
+
"rabc_kappa": 0.01,
|
| 235 |
+
"rabc_epsilon": 1e-06,
|
| 236 |
+
"rabc_head_mode": "sparse",
|
| 237 |
+
"rename_map": {},
|
| 238 |
+
"checkpoint_path": null
|
| 239 |
+
}
|
checkpoints/040000/training_state/optimizer_param_groups.json
ADDED
|
@@ -0,0 +1,521 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[
|
| 2 |
+
{
|
| 3 |
+
"lr": 2.5e-06,
|
| 4 |
+
"betas": [
|
| 5 |
+
0.9,
|
| 6 |
+
0.95
|
| 7 |
+
],
|
| 8 |
+
"eps": 1e-08,
|
| 9 |
+
"weight_decay": 1e-10,
|
| 10 |
+
"amsgrad": false,
|
| 11 |
+
"maximize": false,
|
| 12 |
+
"foreach": null,
|
| 13 |
+
"capturable": false,
|
| 14 |
+
"differentiable": false,
|
| 15 |
+
"fused": null,
|
| 16 |
+
"decoupled_weight_decay": true,
|
| 17 |
+
"initial_lr": 0.0001,
|
| 18 |
+
"params": [
|
| 19 |
+
0,
|
| 20 |
+
1,
|
| 21 |
+
2,
|
| 22 |
+
3,
|
| 23 |
+
4,
|
| 24 |
+
5,
|
| 25 |
+
6,
|
| 26 |
+
7,
|
| 27 |
+
8,
|
| 28 |
+
9,
|
| 29 |
+
10,
|
| 30 |
+
11,
|
| 31 |
+
12,
|
| 32 |
+
13,
|
| 33 |
+
14,
|
| 34 |
+
15,
|
| 35 |
+
16,
|
| 36 |
+
17,
|
| 37 |
+
18,
|
| 38 |
+
19,
|
| 39 |
+
20,
|
| 40 |
+
21,
|
| 41 |
+
22,
|
| 42 |
+
23,
|
| 43 |
+
24,
|
| 44 |
+
25,
|
| 45 |
+
26,
|
| 46 |
+
27,
|
| 47 |
+
28,
|
| 48 |
+
29,
|
| 49 |
+
30,
|
| 50 |
+
31,
|
| 51 |
+
32,
|
| 52 |
+
33,
|
| 53 |
+
34,
|
| 54 |
+
35,
|
| 55 |
+
36,
|
| 56 |
+
37,
|
| 57 |
+
38,
|
| 58 |
+
39,
|
| 59 |
+
40,
|
| 60 |
+
41,
|
| 61 |
+
42,
|
| 62 |
+
43,
|
| 63 |
+
44,
|
| 64 |
+
45,
|
| 65 |
+
46,
|
| 66 |
+
47,
|
| 67 |
+
48,
|
| 68 |
+
49,
|
| 69 |
+
50,
|
| 70 |
+
51,
|
| 71 |
+
52,
|
| 72 |
+
53,
|
| 73 |
+
54,
|
| 74 |
+
55,
|
| 75 |
+
56,
|
| 76 |
+
57,
|
| 77 |
+
58,
|
| 78 |
+
59,
|
| 79 |
+
60,
|
| 80 |
+
61,
|
| 81 |
+
62,
|
| 82 |
+
63,
|
| 83 |
+
64,
|
| 84 |
+
65,
|
| 85 |
+
66,
|
| 86 |
+
67,
|
| 87 |
+
68,
|
| 88 |
+
69,
|
| 89 |
+
70,
|
| 90 |
+
71,
|
| 91 |
+
72,
|
| 92 |
+
73,
|
| 93 |
+
74,
|
| 94 |
+
75,
|
| 95 |
+
76,
|
| 96 |
+
77,
|
| 97 |
+
78,
|
| 98 |
+
79,
|
| 99 |
+
80,
|
| 100 |
+
81,
|
| 101 |
+
82,
|
| 102 |
+
83,
|
| 103 |
+
84,
|
| 104 |
+
85,
|
| 105 |
+
86,
|
| 106 |
+
87,
|
| 107 |
+
88,
|
| 108 |
+
89,
|
| 109 |
+
90,
|
| 110 |
+
91,
|
| 111 |
+
92,
|
| 112 |
+
93,
|
| 113 |
+
94,
|
| 114 |
+
95,
|
| 115 |
+
96,
|
| 116 |
+
97,
|
| 117 |
+
98,
|
| 118 |
+
99,
|
| 119 |
+
100,
|
| 120 |
+
101,
|
| 121 |
+
102,
|
| 122 |
+
103,
|
| 123 |
+
104,
|
| 124 |
+
105,
|
| 125 |
+
106,
|
| 126 |
+
107,
|
| 127 |
+
108,
|
| 128 |
+
109,
|
| 129 |
+
110,
|
| 130 |
+
111,
|
| 131 |
+
112,
|
| 132 |
+
113,
|
| 133 |
+
114,
|
| 134 |
+
115,
|
| 135 |
+
116,
|
| 136 |
+
117,
|
| 137 |
+
118,
|
| 138 |
+
119,
|
| 139 |
+
120,
|
| 140 |
+
121,
|
| 141 |
+
122,
|
| 142 |
+
123,
|
| 143 |
+
124,
|
| 144 |
+
125,
|
| 145 |
+
126,
|
| 146 |
+
127,
|
| 147 |
+
128,
|
| 148 |
+
129,
|
| 149 |
+
130,
|
| 150 |
+
131,
|
| 151 |
+
132,
|
| 152 |
+
133,
|
| 153 |
+
134,
|
| 154 |
+
135,
|
| 155 |
+
136,
|
| 156 |
+
137,
|
| 157 |
+
138,
|
| 158 |
+
139,
|
| 159 |
+
140,
|
| 160 |
+
141,
|
| 161 |
+
142,
|
| 162 |
+
143,
|
| 163 |
+
144,
|
| 164 |
+
145,
|
| 165 |
+
146,
|
| 166 |
+
147,
|
| 167 |
+
148,
|
| 168 |
+
149,
|
| 169 |
+
150,
|
| 170 |
+
151,
|
| 171 |
+
152,
|
| 172 |
+
153,
|
| 173 |
+
154,
|
| 174 |
+
155,
|
| 175 |
+
156,
|
| 176 |
+
157,
|
| 177 |
+
158,
|
| 178 |
+
159,
|
| 179 |
+
160,
|
| 180 |
+
161,
|
| 181 |
+
162,
|
| 182 |
+
163,
|
| 183 |
+
164,
|
| 184 |
+
165,
|
| 185 |
+
166,
|
| 186 |
+
167,
|
| 187 |
+
168,
|
| 188 |
+
169,
|
| 189 |
+
170,
|
| 190 |
+
171,
|
| 191 |
+
172,
|
| 192 |
+
173,
|
| 193 |
+
174,
|
| 194 |
+
175,
|
| 195 |
+
176,
|
| 196 |
+
177,
|
| 197 |
+
178,
|
| 198 |
+
179,
|
| 199 |
+
180,
|
| 200 |
+
181,
|
| 201 |
+
182,
|
| 202 |
+
183,
|
| 203 |
+
184,
|
| 204 |
+
185,
|
| 205 |
+
186,
|
| 206 |
+
187,
|
| 207 |
+
188,
|
| 208 |
+
189,
|
| 209 |
+
190,
|
| 210 |
+
191,
|
| 211 |
+
192,
|
| 212 |
+
193,
|
| 213 |
+
194,
|
| 214 |
+
195,
|
| 215 |
+
196,
|
| 216 |
+
197,
|
| 217 |
+
198,
|
| 218 |
+
199,
|
| 219 |
+
200,
|
| 220 |
+
201,
|
| 221 |
+
202,
|
| 222 |
+
203,
|
| 223 |
+
204,
|
| 224 |
+
205,
|
| 225 |
+
206,
|
| 226 |
+
207,
|
| 227 |
+
208,
|
| 228 |
+
209,
|
| 229 |
+
210,
|
| 230 |
+
211,
|
| 231 |
+
212,
|
| 232 |
+
213,
|
| 233 |
+
214,
|
| 234 |
+
215,
|
| 235 |
+
216,
|
| 236 |
+
217,
|
| 237 |
+
218,
|
| 238 |
+
219,
|
| 239 |
+
220,
|
| 240 |
+
221,
|
| 241 |
+
222,
|
| 242 |
+
223,
|
| 243 |
+
224,
|
| 244 |
+
225,
|
| 245 |
+
226,
|
| 246 |
+
227,
|
| 247 |
+
228,
|
| 248 |
+
229,
|
| 249 |
+
230,
|
| 250 |
+
231,
|
| 251 |
+
232,
|
| 252 |
+
233,
|
| 253 |
+
234,
|
| 254 |
+
235,
|
| 255 |
+
236,
|
| 256 |
+
237,
|
| 257 |
+
238,
|
| 258 |
+
239,
|
| 259 |
+
240,
|
| 260 |
+
241,
|
| 261 |
+
242,
|
| 262 |
+
243,
|
| 263 |
+
244,
|
| 264 |
+
245,
|
| 265 |
+
246,
|
| 266 |
+
247,
|
| 267 |
+
248,
|
| 268 |
+
249,
|
| 269 |
+
250,
|
| 270 |
+
251,
|
| 271 |
+
252,
|
| 272 |
+
253,
|
| 273 |
+
254,
|
| 274 |
+
255,
|
| 275 |
+
256,
|
| 276 |
+
257,
|
| 277 |
+
258,
|
| 278 |
+
259,
|
| 279 |
+
260,
|
| 280 |
+
261,
|
| 281 |
+
262,
|
| 282 |
+
263,
|
| 283 |
+
264,
|
| 284 |
+
265,
|
| 285 |
+
266,
|
| 286 |
+
267,
|
| 287 |
+
268,
|
| 288 |
+
269,
|
| 289 |
+
270,
|
| 290 |
+
271,
|
| 291 |
+
272,
|
| 292 |
+
273,
|
| 293 |
+
274,
|
| 294 |
+
275,
|
| 295 |
+
276,
|
| 296 |
+
277,
|
| 297 |
+
278,
|
| 298 |
+
279,
|
| 299 |
+
280,
|
| 300 |
+
281,
|
| 301 |
+
282,
|
| 302 |
+
283,
|
| 303 |
+
284,
|
| 304 |
+
285,
|
| 305 |
+
286,
|
| 306 |
+
287,
|
| 307 |
+
288,
|
| 308 |
+
289,
|
| 309 |
+
290,
|
| 310 |
+
291,
|
| 311 |
+
292,
|
| 312 |
+
293,
|
| 313 |
+
294,
|
| 314 |
+
295,
|
| 315 |
+
296,
|
| 316 |
+
297,
|
| 317 |
+
298,
|
| 318 |
+
299,
|
| 319 |
+
300,
|
| 320 |
+
301,
|
| 321 |
+
302,
|
| 322 |
+
303,
|
| 323 |
+
304,
|
| 324 |
+
305,
|
| 325 |
+
306,
|
| 326 |
+
307,
|
| 327 |
+
308,
|
| 328 |
+
309,
|
| 329 |
+
310,
|
| 330 |
+
311,
|
| 331 |
+
312,
|
| 332 |
+
313,
|
| 333 |
+
314,
|
| 334 |
+
315,
|
| 335 |
+
316,
|
| 336 |
+
317,
|
| 337 |
+
318,
|
| 338 |
+
319,
|
| 339 |
+
320,
|
| 340 |
+
321,
|
| 341 |
+
322,
|
| 342 |
+
323,
|
| 343 |
+
324,
|
| 344 |
+
325,
|
| 345 |
+
326,
|
| 346 |
+
327,
|
| 347 |
+
328,
|
| 348 |
+
329,
|
| 349 |
+
330,
|
| 350 |
+
331,
|
| 351 |
+
332,
|
| 352 |
+
333,
|
| 353 |
+
334,
|
| 354 |
+
335,
|
| 355 |
+
336,
|
| 356 |
+
337,
|
| 357 |
+
338,
|
| 358 |
+
339,
|
| 359 |
+
340,
|
| 360 |
+
341,
|
| 361 |
+
342,
|
| 362 |
+
343,
|
| 363 |
+
344,
|
| 364 |
+
345,
|
| 365 |
+
346,
|
| 366 |
+
347,
|
| 367 |
+
348,
|
| 368 |
+
349,
|
| 369 |
+
350,
|
| 370 |
+
351,
|
| 371 |
+
352,
|
| 372 |
+
353,
|
| 373 |
+
354,
|
| 374 |
+
355,
|
| 375 |
+
356,
|
| 376 |
+
357,
|
| 377 |
+
358,
|
| 378 |
+
359,
|
| 379 |
+
360,
|
| 380 |
+
361,
|
| 381 |
+
362,
|
| 382 |
+
363,
|
| 383 |
+
364,
|
| 384 |
+
365,
|
| 385 |
+
366,
|
| 386 |
+
367,
|
| 387 |
+
368,
|
| 388 |
+
369,
|
| 389 |
+
370,
|
| 390 |
+
371,
|
| 391 |
+
372,
|
| 392 |
+
373,
|
| 393 |
+
374,
|
| 394 |
+
375,
|
| 395 |
+
376,
|
| 396 |
+
377,
|
| 397 |
+
378,
|
| 398 |
+
379,
|
| 399 |
+
380,
|
| 400 |
+
381,
|
| 401 |
+
382,
|
| 402 |
+
383,
|
| 403 |
+
384,
|
| 404 |
+
385,
|
| 405 |
+
386,
|
| 406 |
+
387,
|
| 407 |
+
388,
|
| 408 |
+
389,
|
| 409 |
+
390,
|
| 410 |
+
391,
|
| 411 |
+
392,
|
| 412 |
+
393,
|
| 413 |
+
394,
|
| 414 |
+
395,
|
| 415 |
+
396,
|
| 416 |
+
397,
|
| 417 |
+
398,
|
| 418 |
+
399,
|
| 419 |
+
400,
|
| 420 |
+
401,
|
| 421 |
+
402,
|
| 422 |
+
403,
|
| 423 |
+
404,
|
| 424 |
+
405,
|
| 425 |
+
406,
|
| 426 |
+
407,
|
| 427 |
+
408,
|
| 428 |
+
409,
|
| 429 |
+
410,
|
| 430 |
+
411,
|
| 431 |
+
412,
|
| 432 |
+
413,
|
| 433 |
+
414,
|
| 434 |
+
415,
|
| 435 |
+
416,
|
| 436 |
+
417,
|
| 437 |
+
418,
|
| 438 |
+
419,
|
| 439 |
+
420,
|
| 440 |
+
421,
|
| 441 |
+
422,
|
| 442 |
+
423,
|
| 443 |
+
424,
|
| 444 |
+
425,
|
| 445 |
+
426,
|
| 446 |
+
427,
|
| 447 |
+
428,
|
| 448 |
+
429,
|
| 449 |
+
430,
|
| 450 |
+
431,
|
| 451 |
+
432,
|
| 452 |
+
433,
|
| 453 |
+
434,
|
| 454 |
+
435,
|
| 455 |
+
436,
|
| 456 |
+
437,
|
| 457 |
+
438,
|
| 458 |
+
439,
|
| 459 |
+
440,
|
| 460 |
+
441,
|
| 461 |
+
442,
|
| 462 |
+
443,
|
| 463 |
+
444,
|
| 464 |
+
445,
|
| 465 |
+
446,
|
| 466 |
+
447,
|
| 467 |
+
448,
|
| 468 |
+
449,
|
| 469 |
+
450,
|
| 470 |
+
451,
|
| 471 |
+
452,
|
| 472 |
+
453,
|
| 473 |
+
454,
|
| 474 |
+
455,
|
| 475 |
+
456,
|
| 476 |
+
457,
|
| 477 |
+
458,
|
| 478 |
+
459,
|
| 479 |
+
460,
|
| 480 |
+
461,
|
| 481 |
+
462,
|
| 482 |
+
463,
|
| 483 |
+
464,
|
| 484 |
+
465,
|
| 485 |
+
466,
|
| 486 |
+
467,
|
| 487 |
+
468,
|
| 488 |
+
469,
|
| 489 |
+
470,
|
| 490 |
+
471,
|
| 491 |
+
472,
|
| 492 |
+
473,
|
| 493 |
+
474,
|
| 494 |
+
475,
|
| 495 |
+
476,
|
| 496 |
+
477,
|
| 497 |
+
478,
|
| 498 |
+
479,
|
| 499 |
+
480,
|
| 500 |
+
481,
|
| 501 |
+
482,
|
| 502 |
+
483,
|
| 503 |
+
484,
|
| 504 |
+
485,
|
| 505 |
+
486,
|
| 506 |
+
487,
|
| 507 |
+
488,
|
| 508 |
+
489,
|
| 509 |
+
490,
|
| 510 |
+
491,
|
| 511 |
+
492,
|
| 512 |
+
493,
|
| 513 |
+
494,
|
| 514 |
+
495,
|
| 515 |
+
496,
|
| 516 |
+
497,
|
| 517 |
+
498,
|
| 518 |
+
499
|
| 519 |
+
]
|
| 520 |
+
}
|
| 521 |
+
]
|
checkpoints/040000/training_state/optimizer_state.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fad1201c6b3ad625b74440af6e8792275736fcbb689bddfb0e44b756996bbb2a
|
| 3 |
+
size 412659164
|
checkpoints/040000/training_state/rng_state.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cbf555763296d344f271d59f65274bdcd1e2ea372b6492390d7a6e75bf5e5081
|
| 3 |
+
size 15708
|
checkpoints/040000/training_state/scheduler_state.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"base_lrs": [
|
| 3 |
+
0.0001
|
| 4 |
+
],
|
| 5 |
+
"last_epoch": 40000,
|
| 6 |
+
"_step_count": 40001,
|
| 7 |
+
"_is_initial": false,
|
| 8 |
+
"_get_lr_called_within_step": false,
|
| 9 |
+
"_last_lr": [
|
| 10 |
+
2.5e-06
|
| 11 |
+
],
|
| 12 |
+
"lr_lambdas": [
|
| 13 |
+
null
|
| 14 |
+
]
|
| 15 |
+
}
|
checkpoints/040000/training_state/training_step.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"step": 40000
|
| 3 |
+
}
|
checkpoints/050000/pretrained_model/config.json
ADDED
|
@@ -0,0 +1,101 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"type": "smolvla",
|
| 3 |
+
"n_obs_steps": 1,
|
| 4 |
+
"input_features": {
|
| 5 |
+
"observation.state": {
|
| 6 |
+
"type": "STATE",
|
| 7 |
+
"shape": [
|
| 8 |
+
6
|
| 9 |
+
]
|
| 10 |
+
},
|
| 11 |
+
"observation.images.camera1": {
|
| 12 |
+
"type": "VISUAL",
|
| 13 |
+
"shape": [
|
| 14 |
+
3,
|
| 15 |
+
256,
|
| 16 |
+
256
|
| 17 |
+
]
|
| 18 |
+
},
|
| 19 |
+
"observation.images.camera2": {
|
| 20 |
+
"type": "VISUAL",
|
| 21 |
+
"shape": [
|
| 22 |
+
3,
|
| 23 |
+
256,
|
| 24 |
+
256
|
| 25 |
+
]
|
| 26 |
+
},
|
| 27 |
+
"observation.images.camera3": {
|
| 28 |
+
"type": "VISUAL",
|
| 29 |
+
"shape": [
|
| 30 |
+
3,
|
| 31 |
+
256,
|
| 32 |
+
256
|
| 33 |
+
]
|
| 34 |
+
}
|
| 35 |
+
},
|
| 36 |
+
"output_features": {
|
| 37 |
+
"action": {
|
| 38 |
+
"type": "ACTION",
|
| 39 |
+
"shape": [
|
| 40 |
+
6
|
| 41 |
+
]
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"device": "cuda",
|
| 45 |
+
"use_amp": false,
|
| 46 |
+
"use_peft": false,
|
| 47 |
+
"push_to_hub": true,
|
| 48 |
+
"repo_id": "BrandonAL/my_sim_smolvla_all_ft60k",
|
| 49 |
+
"private": null,
|
| 50 |
+
"tags": null,
|
| 51 |
+
"license": null,
|
| 52 |
+
"pretrained_path": "BrandonAL/my_sim_smolvla_all_step010000",
|
| 53 |
+
"chunk_size": 50,
|
| 54 |
+
"n_action_steps": 50,
|
| 55 |
+
"normalization_mapping": {
|
| 56 |
+
"VISUAL": "IDENTITY",
|
| 57 |
+
"STATE": "MEAN_STD",
|
| 58 |
+
"ACTION": "MEAN_STD"
|
| 59 |
+
},
|
| 60 |
+
"max_state_dim": 32,
|
| 61 |
+
"max_action_dim": 32,
|
| 62 |
+
"resize_imgs_with_padding": [
|
| 63 |
+
512,
|
| 64 |
+
512
|
| 65 |
+
],
|
| 66 |
+
"empty_cameras": 0,
|
| 67 |
+
"adapt_to_pi_aloha": false,
|
| 68 |
+
"use_delta_joint_actions_aloha": false,
|
| 69 |
+
"tokenizer_max_length": 48,
|
| 70 |
+
"num_steps": 10,
|
| 71 |
+
"use_cache": true,
|
| 72 |
+
"freeze_vision_encoder": true,
|
| 73 |
+
"train_expert_only": true,
|
| 74 |
+
"train_state_proj": true,
|
| 75 |
+
"optimizer_lr": 0.0001,
|
| 76 |
+
"optimizer_betas": [
|
| 77 |
+
0.9,
|
| 78 |
+
0.95
|
| 79 |
+
],
|
| 80 |
+
"optimizer_eps": 1e-08,
|
| 81 |
+
"optimizer_weight_decay": 1e-10,
|
| 82 |
+
"optimizer_grad_clip_norm": 10.0,
|
| 83 |
+
"scheduler_warmup_steps": 1000,
|
| 84 |
+
"scheduler_decay_steps": 30000,
|
| 85 |
+
"scheduler_decay_lr": 2.5e-06,
|
| 86 |
+
"vlm_model_name": "HuggingFaceTB/SmolVLM2-500M-Video-Instruct",
|
| 87 |
+
"load_vlm_weights": true,
|
| 88 |
+
"add_image_special_tokens": false,
|
| 89 |
+
"attention_mode": "cross_attn",
|
| 90 |
+
"prefix_length": 0,
|
| 91 |
+
"pad_language_to": "max_length",
|
| 92 |
+
"num_expert_layers": 0,
|
| 93 |
+
"num_vlm_layers": 16,
|
| 94 |
+
"self_attn_every_n_layers": 2,
|
| 95 |
+
"expert_width_multiplier": 0.75,
|
| 96 |
+
"min_period": 0.004,
|
| 97 |
+
"max_period": 4.0,
|
| 98 |
+
"rtc_config": null,
|
| 99 |
+
"compile_model": false,
|
| 100 |
+
"compile_mode": "max-autotune"
|
| 101 |
+
}
|
checkpoints/050000/pretrained_model/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:10c9642b8228924f7370f54e4e3781a620e5778ceb43bb6c536acfb1f5e1a654
|
| 3 |
+
size 906712520
|