upload models trained on banana_disassembly_laptop

moto_gpt_finetuned_on_banana_disassembly_laptop/data_banana_disassembly_laptop-model_actPredTrueDiscrete_motionPredFalse_visionMaeLarge_seq2_chunk9_maskProb0.5-train_lr0.001_bs32_binaryGripperTrue-aug_shiftTrue_resizedCropFalse-resume_from_predLatentOnly_banana_disassembly_laptop_Epoch10/saved_epoch_10_step_1170/config.yaml

@@ -0,0 +1,34 @@
+_target_: moto_gpt.src.models.moto_gpt.MotoGPT
+model_lang:
+  _target_: transformers.T5EncoderModel.from_pretrained
+  pretrained_model_name_or_path: t5-base
+model_vision:
+  _target_: moto_gpt.src.models.mae_model.MaeEncoder
+  use_obs_feature: true
+  pretrained_model_name_or_path: facebook/vit-mae-large
+model_causal_transformer:
+  _target_: moto_gpt.src.models.trajectory_gpt2.GPT2Model
+  config:
+    _target_: moto_gpt.src.models.trajectory_gpt2.GPT2Config
+    vocab_size: 1
+    n_embd: 768
+    n_layer: 12
+    n_head: 12
+    activation_function: relu
+    dropout: 0.1
+    n_positions: 1024
+act_dim: 7
+hidden_size: 768
+sequence_length: 2
+chunk_size: 9
+per_latent_motion_len: 8
+latent_motion_codebook_size: 128
+latent_motion_pred: false
+act_pred: true
+img_feat_dim: 1024
+patch_feat_dim: 1024
+lang_feat_dim: 768
+mask_latent_motion_probability: 0.5
+freeze_lang: true
+freeze_vision: true
+pred_discrete_arm_action: true

moto_gpt_finetuned_on_banana_disassembly_laptop/data_banana_disassembly_laptop-model_actPredTrueDiscrete_motionPredFalse_visionMaeLarge_seq2_chunk9_maskProb0.5-train_lr0.001_bs32_binaryGripperTrue-aug_shiftTrue_resizedCropFalse-resume_from_predLatentOnly_banana_disassembly_laptop_Epoch10/saved_epoch_10_step_1170/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1121d13f0cc9c043c03c27c4187a9ca27c5b9e4cc17483ad34e73c66d2819de
+size 363796998

moto_gpt_finetuned_on_banana_disassembly_laptop/data_banana_disassembly_laptop-model_actPredTrueDiscrete_motionPredFalse_visionMaeLarge_seq2_chunk9_maskProb0.5-train_lr0.001_bs32_binaryGripperTrue-aug_shiftTrue_resizedCropFalse-resume_from_predLatentOnly_banana_disassembly_laptop_Epoch10/saved_epoch_15_step_1755/config.yaml

@@ -0,0 +1,34 @@
+_target_: moto_gpt.src.models.moto_gpt.MotoGPT
+model_lang:
+  _target_: transformers.T5EncoderModel.from_pretrained
+  pretrained_model_name_or_path: t5-base
+model_vision:
+  _target_: moto_gpt.src.models.mae_model.MaeEncoder
+  use_obs_feature: true
+  pretrained_model_name_or_path: facebook/vit-mae-large
+model_causal_transformer:
+  _target_: moto_gpt.src.models.trajectory_gpt2.GPT2Model
+  config:
+    _target_: moto_gpt.src.models.trajectory_gpt2.GPT2Config
+    vocab_size: 1
+    n_embd: 768
+    n_layer: 12
+    n_head: 12
+    activation_function: relu
+    dropout: 0.1
+    n_positions: 1024
+act_dim: 7
+hidden_size: 768
+sequence_length: 2
+chunk_size: 9
+per_latent_motion_len: 8
+latent_motion_codebook_size: 128
+latent_motion_pred: false
+act_pred: true
+img_feat_dim: 1024
+patch_feat_dim: 1024
+lang_feat_dim: 768
+mask_latent_motion_probability: 0.5
+freeze_lang: true
+freeze_vision: true
+pred_discrete_arm_action: true

moto_gpt_finetuned_on_banana_disassembly_laptop/data_banana_disassembly_laptop-model_actPredTrueDiscrete_motionPredFalse_visionMaeLarge_seq2_chunk9_maskProb0.5-train_lr0.001_bs32_binaryGripperTrue-aug_shiftTrue_resizedCropFalse-resume_from_predLatentOnly_banana_disassembly_laptop_Epoch10/saved_epoch_15_step_1755/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57cc7987af9e219b27d39a7d9cc7ffcbeaa5925211fb3ca93525f61791028932
+size 363796998

moto_gpt_finetuned_on_banana_disassembly_laptop/data_banana_disassembly_laptop-model_actPredTrueDiscrete_motionPredFalse_visionMaeLarge_seq2_chunk9_maskProb0.5-train_lr0.001_bs32_binaryGripperTrue-aug_shiftTrue_resizedCropFalse-resume_from_predLatentOnly_banana_disassembly_laptop_Epoch10/saved_epoch_20_step_2340/config.yaml

@@ -0,0 +1,34 @@
+_target_: moto_gpt.src.models.moto_gpt.MotoGPT
+model_lang:
+  _target_: transformers.T5EncoderModel.from_pretrained
+  pretrained_model_name_or_path: t5-base
+model_vision:
+  _target_: moto_gpt.src.models.mae_model.MaeEncoder
+  use_obs_feature: true
+  pretrained_model_name_or_path: facebook/vit-mae-large
+model_causal_transformer:
+  _target_: moto_gpt.src.models.trajectory_gpt2.GPT2Model
+  config:
+    _target_: moto_gpt.src.models.trajectory_gpt2.GPT2Config
+    vocab_size: 1
+    n_embd: 768
+    n_layer: 12
+    n_head: 12
+    activation_function: relu
+    dropout: 0.1
+    n_positions: 1024
+act_dim: 7
+hidden_size: 768
+sequence_length: 2
+chunk_size: 9
+per_latent_motion_len: 8
+latent_motion_codebook_size: 128
+latent_motion_pred: false
+act_pred: true
+img_feat_dim: 1024
+patch_feat_dim: 1024
+lang_feat_dim: 768
+mask_latent_motion_probability: 0.5
+freeze_lang: true
+freeze_vision: true
+pred_discrete_arm_action: true

moto_gpt_finetuned_on_banana_disassembly_laptop/data_banana_disassembly_laptop-model_actPredTrueDiscrete_motionPredFalse_visionMaeLarge_seq2_chunk9_maskProb0.5-train_lr0.001_bs32_binaryGripperTrue-aug_shiftTrue_resizedCropFalse-resume_from_predLatentOnly_banana_disassembly_laptop_Epoch10/saved_epoch_20_step_2340/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a24f0c04beb095675d0e863c230db07bf4b1d0fcb7a4eea99d80caf354702d28
+size 363796998

moto_gpt_finetuned_on_banana_disassembly_laptop/data_banana_disassembly_laptop-model_actPredTrueDiscrete_motionPredFalse_visionMaeLarge_seq2_chunk9_maskProb0.5-train_lr0.001_bs32_binaryGripperTrue-aug_shiftTrue_resizedCropFalse-resume_from_predLatentOnly_banana_disassembly_laptop_Epoch10/saved_epoch_3_step_351/config.yaml

@@ -0,0 +1,34 @@
+_target_: moto_gpt.src.models.moto_gpt.MotoGPT
+model_lang:
+  _target_: transformers.T5EncoderModel.from_pretrained
+  pretrained_model_name_or_path: t5-base
+model_vision:
+  _target_: moto_gpt.src.models.mae_model.MaeEncoder
+  use_obs_feature: true
+  pretrained_model_name_or_path: facebook/vit-mae-large
+model_causal_transformer:
+  _target_: moto_gpt.src.models.trajectory_gpt2.GPT2Model
+  config:
+    _target_: moto_gpt.src.models.trajectory_gpt2.GPT2Config
+    vocab_size: 1
+    n_embd: 768
+    n_layer: 12
+    n_head: 12
+    activation_function: relu
+    dropout: 0.1
+    n_positions: 1024
+act_dim: 7
+hidden_size: 768
+sequence_length: 2
+chunk_size: 9
+per_latent_motion_len: 8
+latent_motion_codebook_size: 128
+latent_motion_pred: false
+act_pred: true
+img_feat_dim: 1024
+patch_feat_dim: 1024
+lang_feat_dim: 768
+mask_latent_motion_probability: 0.5
+freeze_lang: true
+freeze_vision: true
+pred_discrete_arm_action: true

moto_gpt_finetuned_on_banana_disassembly_laptop/data_banana_disassembly_laptop-model_actPredTrueDiscrete_motionPredFalse_visionMaeLarge_seq2_chunk9_maskProb0.5-train_lr0.001_bs32_binaryGripperTrue-aug_shiftTrue_resizedCropFalse-resume_from_predLatentOnly_banana_disassembly_laptop_Epoch10/saved_epoch_3_step_351/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a78c11434970bb67c0a670f505e4122a6962646b2f34a364ef63d1abd0e9413
+size 363796998

moto_gpt_finetuned_on_banana_disassembly_laptop/data_banana_disassembly_laptop-model_actPredTrueDiscrete_motionPredFalse_visionMaeLarge_seq2_chunk9_maskProb0.5-train_lr0.001_bs32_binaryGripperTrue-aug_shiftTrue_resizedCropFalse-resume_from_predLatentOnly_banana_disassembly_laptop_Epoch10/saved_epoch_5_step_585/config.yaml

@@ -0,0 +1,34 @@
+_target_: moto_gpt.src.models.moto_gpt.MotoGPT
+model_lang:
+  _target_: transformers.T5EncoderModel.from_pretrained
+  pretrained_model_name_or_path: t5-base
+model_vision:
+  _target_: moto_gpt.src.models.mae_model.MaeEncoder
+  use_obs_feature: true
+  pretrained_model_name_or_path: facebook/vit-mae-large
+model_causal_transformer:
+  _target_: moto_gpt.src.models.trajectory_gpt2.GPT2Model
+  config:
+    _target_: moto_gpt.src.models.trajectory_gpt2.GPT2Config
+    vocab_size: 1
+    n_embd: 768
+    n_layer: 12
+    n_head: 12
+    activation_function: relu
+    dropout: 0.1
+    n_positions: 1024
+act_dim: 7
+hidden_size: 768
+sequence_length: 2
+chunk_size: 9
+per_latent_motion_len: 8
+latent_motion_codebook_size: 128
+latent_motion_pred: false
+act_pred: true
+img_feat_dim: 1024
+patch_feat_dim: 1024
+lang_feat_dim: 768
+mask_latent_motion_probability: 0.5
+freeze_lang: true
+freeze_vision: true
+pred_discrete_arm_action: true

moto_gpt_finetuned_on_banana_disassembly_laptop/data_banana_disassembly_laptop-model_actPredTrueDiscrete_motionPredFalse_visionMaeLarge_seq2_chunk9_maskProb0.5-train_lr0.001_bs32_binaryGripperTrue-aug_shiftTrue_resizedCropFalse-resume_from_predLatentOnly_banana_disassembly_laptop_Epoch10/saved_epoch_5_step_585/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c467727ae68dc70b25fa3614b282aef0f3abb682bb120eb6b3e877ace89310c7
+size 363796998

moto_gpt_finetuned_on_banana_disassembly_laptop/data_banana_disassembly_laptop-model_actPredTrueDiscrete_motionPredFalse_visionMaeLarge_seq2_chunk9_maskProb0.5-train_lr0.001_bs32_binaryGripperTrue-aug_shiftTrue_resizedCropFalse-resume_from_predLatentOnly_banana_disassembly_laptop_Epoch5/saved_epoch_10_step_1170/config.yaml

@@ -0,0 +1,34 @@
+_target_: moto_gpt.src.models.moto_gpt.MotoGPT
+model_lang:
+  _target_: transformers.T5EncoderModel.from_pretrained
+  pretrained_model_name_or_path: t5-base
+model_vision:
+  _target_: moto_gpt.src.models.mae_model.MaeEncoder
+  use_obs_feature: true
+  pretrained_model_name_or_path: facebook/vit-mae-large
+model_causal_transformer:
+  _target_: moto_gpt.src.models.trajectory_gpt2.GPT2Model
+  config:
+    _target_: moto_gpt.src.models.trajectory_gpt2.GPT2Config
+    vocab_size: 1
+    n_embd: 768
+    n_layer: 12
+    n_head: 12
+    activation_function: relu
+    dropout: 0.1
+    n_positions: 1024
+act_dim: 7
+hidden_size: 768
+sequence_length: 2
+chunk_size: 9
+per_latent_motion_len: 8
+latent_motion_codebook_size: 128
+latent_motion_pred: false
+act_pred: true
+img_feat_dim: 1024
+patch_feat_dim: 1024
+lang_feat_dim: 768
+mask_latent_motion_probability: 0.5
+freeze_lang: true
+freeze_vision: true
+pred_discrete_arm_action: true

moto_gpt_finetuned_on_banana_disassembly_laptop/data_banana_disassembly_laptop-model_actPredTrueDiscrete_motionPredFalse_visionMaeLarge_seq2_chunk9_maskProb0.5-train_lr0.001_bs32_binaryGripperTrue-aug_shiftTrue_resizedCropFalse-resume_from_predLatentOnly_banana_disassembly_laptop_Epoch5/saved_epoch_10_step_1170/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e476e98236de7e624fc2b50a3cbbdd7a32d202fac98ad0fb82381bb768d20c27
+size 363796998

moto_gpt_finetuned_on_banana_disassembly_laptop/data_banana_disassembly_laptop-model_actPredTrueDiscrete_motionPredFalse_visionMaeLarge_seq2_chunk9_maskProb0.5-train_lr0.001_bs32_binaryGripperTrue-aug_shiftTrue_resizedCropFalse-resume_from_predLatentOnly_banana_disassembly_laptop_Epoch5/saved_epoch_15_step_1755/config.yaml

@@ -0,0 +1,34 @@
+_target_: moto_gpt.src.models.moto_gpt.MotoGPT
+model_lang:
+  _target_: transformers.T5EncoderModel.from_pretrained
+  pretrained_model_name_or_path: t5-base
+model_vision:
+  _target_: moto_gpt.src.models.mae_model.MaeEncoder
+  use_obs_feature: true
+  pretrained_model_name_or_path: facebook/vit-mae-large
+model_causal_transformer:
+  _target_: moto_gpt.src.models.trajectory_gpt2.GPT2Model
+  config:
+    _target_: moto_gpt.src.models.trajectory_gpt2.GPT2Config
+    vocab_size: 1
+    n_embd: 768
+    n_layer: 12
+    n_head: 12
+    activation_function: relu
+    dropout: 0.1
+    n_positions: 1024
+act_dim: 7
+hidden_size: 768
+sequence_length: 2
+chunk_size: 9
+per_latent_motion_len: 8
+latent_motion_codebook_size: 128
+latent_motion_pred: false
+act_pred: true
+img_feat_dim: 1024
+patch_feat_dim: 1024
+lang_feat_dim: 768
+mask_latent_motion_probability: 0.5
+freeze_lang: true
+freeze_vision: true
+pred_discrete_arm_action: true

moto_gpt_finetuned_on_banana_disassembly_laptop/data_banana_disassembly_laptop-model_actPredTrueDiscrete_motionPredFalse_visionMaeLarge_seq2_chunk9_maskProb0.5-train_lr0.001_bs32_binaryGripperTrue-aug_shiftTrue_resizedCropFalse-resume_from_predLatentOnly_banana_disassembly_laptop_Epoch5/saved_epoch_15_step_1755/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2afe8f9f48ff47d2990a458f45d19d1565bf62bc0974436a9e7954042d2dffe9
+size 363796998

moto_gpt_finetuned_on_banana_disassembly_laptop/data_banana_disassembly_laptop-model_actPredTrueDiscrete_motionPredFalse_visionMaeLarge_seq2_chunk9_maskProb0.5-train_lr0.001_bs32_binaryGripperTrue-aug_shiftTrue_resizedCropFalse-resume_from_predLatentOnly_banana_disassembly_laptop_Epoch5/saved_epoch_20_step_2340/config.yaml

@@ -0,0 +1,34 @@
+_target_: moto_gpt.src.models.moto_gpt.MotoGPT
+model_lang:
+  _target_: transformers.T5EncoderModel.from_pretrained
+  pretrained_model_name_or_path: t5-base
+model_vision:
+  _target_: moto_gpt.src.models.mae_model.MaeEncoder
+  use_obs_feature: true
+  pretrained_model_name_or_path: facebook/vit-mae-large
+model_causal_transformer:
+  _target_: moto_gpt.src.models.trajectory_gpt2.GPT2Model
+  config:
+    _target_: moto_gpt.src.models.trajectory_gpt2.GPT2Config
+    vocab_size: 1
+    n_embd: 768
+    n_layer: 12
+    n_head: 12
+    activation_function: relu
+    dropout: 0.1
+    n_positions: 1024
+act_dim: 7
+hidden_size: 768
+sequence_length: 2
+chunk_size: 9
+per_latent_motion_len: 8
+latent_motion_codebook_size: 128
+latent_motion_pred: false
+act_pred: true
+img_feat_dim: 1024
+patch_feat_dim: 1024
+lang_feat_dim: 768
+mask_latent_motion_probability: 0.5
+freeze_lang: true
+freeze_vision: true
+pred_discrete_arm_action: true

moto_gpt_finetuned_on_banana_disassembly_laptop/data_banana_disassembly_laptop-model_actPredTrueDiscrete_motionPredFalse_visionMaeLarge_seq2_chunk9_maskProb0.5-train_lr0.001_bs32_binaryGripperTrue-aug_shiftTrue_resizedCropFalse-resume_from_predLatentOnly_banana_disassembly_laptop_Epoch5/saved_epoch_20_step_2340/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:198468d9fb283503ce624870c6675a9448fda6cf342c30e926a4c8186eecd1ba
+size 363796998

moto_gpt_finetuned_on_banana_disassembly_laptop/data_banana_disassembly_laptop-model_actPredTrueDiscrete_motionPredFalse_visionMaeLarge_seq2_chunk9_maskProb0.5-train_lr0.001_bs32_binaryGripperTrue-aug_shiftTrue_resizedCropFalse-resume_from_predLatentOnly_banana_disassembly_laptop_Epoch5/saved_epoch_3_step_351/config.yaml

@@ -0,0 +1,34 @@
+_target_: moto_gpt.src.models.moto_gpt.MotoGPT
+model_lang:
+  _target_: transformers.T5EncoderModel.from_pretrained
+  pretrained_model_name_or_path: t5-base
+model_vision:
+  _target_: moto_gpt.src.models.mae_model.MaeEncoder
+  use_obs_feature: true
+  pretrained_model_name_or_path: facebook/vit-mae-large
+model_causal_transformer:
+  _target_: moto_gpt.src.models.trajectory_gpt2.GPT2Model
+  config:
+    _target_: moto_gpt.src.models.trajectory_gpt2.GPT2Config
+    vocab_size: 1
+    n_embd: 768
+    n_layer: 12
+    n_head: 12
+    activation_function: relu
+    dropout: 0.1
+    n_positions: 1024
+act_dim: 7
+hidden_size: 768
+sequence_length: 2
+chunk_size: 9
+per_latent_motion_len: 8
+latent_motion_codebook_size: 128
+latent_motion_pred: false
+act_pred: true
+img_feat_dim: 1024
+patch_feat_dim: 1024
+lang_feat_dim: 768
+mask_latent_motion_probability: 0.5
+freeze_lang: true
+freeze_vision: true
+pred_discrete_arm_action: true

moto_gpt_finetuned_on_banana_disassembly_laptop/data_banana_disassembly_laptop-model_actPredTrueDiscrete_motionPredFalse_visionMaeLarge_seq2_chunk9_maskProb0.5-train_lr0.001_bs32_binaryGripperTrue-aug_shiftTrue_resizedCropFalse-resume_from_predLatentOnly_banana_disassembly_laptop_Epoch5/saved_epoch_3_step_351/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f2e09eb223124827f107e1e57b0a56525060048c324f746626cbed3564906a0
+size 363796998

moto_gpt_finetuned_on_banana_disassembly_laptop/data_banana_disassembly_laptop-model_actPredTrueDiscrete_motionPredFalse_visionMaeLarge_seq2_chunk9_maskProb0.5-train_lr0.001_bs32_binaryGripperTrue-aug_shiftTrue_resizedCropFalse-resume_from_predLatentOnly_banana_disassembly_laptop_Epoch5/saved_epoch_5_step_585/config.yaml

@@ -0,0 +1,34 @@
+_target_: moto_gpt.src.models.moto_gpt.MotoGPT
+model_lang:
+  _target_: transformers.T5EncoderModel.from_pretrained
+  pretrained_model_name_or_path: t5-base
+model_vision:
+  _target_: moto_gpt.src.models.mae_model.MaeEncoder
+  use_obs_feature: true
+  pretrained_model_name_or_path: facebook/vit-mae-large
+model_causal_transformer:
+  _target_: moto_gpt.src.models.trajectory_gpt2.GPT2Model
+  config:
+    _target_: moto_gpt.src.models.trajectory_gpt2.GPT2Config
+    vocab_size: 1
+    n_embd: 768
+    n_layer: 12
+    n_head: 12
+    activation_function: relu
+    dropout: 0.1
+    n_positions: 1024
+act_dim: 7
+hidden_size: 768
+sequence_length: 2
+chunk_size: 9
+per_latent_motion_len: 8
+latent_motion_codebook_size: 128
+latent_motion_pred: false
+act_pred: true
+img_feat_dim: 1024
+patch_feat_dim: 1024
+lang_feat_dim: 768
+mask_latent_motion_probability: 0.5
+freeze_lang: true
+freeze_vision: true
+pred_discrete_arm_action: true

moto_gpt_finetuned_on_banana_disassembly_laptop/data_banana_disassembly_laptop-model_actPredTrueDiscrete_motionPredFalse_visionMaeLarge_seq2_chunk9_maskProb0.5-train_lr0.001_bs32_binaryGripperTrue-aug_shiftTrue_resizedCropFalse-resume_from_predLatentOnly_banana_disassembly_laptop_Epoch5/saved_epoch_5_step_585/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38fa5557be24209a45dccf106c037ff3a74cd8e79701a6f45fdb65cb761101c9
+size 363796998

moto_gpt_finetuned_on_banana_disassembly_laptop/data_banana_disassembly_laptop-model_actPredTrueDiscrete_motionPredTrue_visionMaeLarge_seq2_chunk9_maskProb0.5-train_lr0.001_bs32_binaryGripperTrue-aug_shiftTrue_resizedCropFalse-resume_from_predLatentOnly_banana_disassembly_laptop_Epoch10/saved_epoch_10_step_1170/config.yaml

@@ -0,0 +1,34 @@
+_target_: moto_gpt.src.models.moto_gpt.MotoGPT
+model_lang:
+  _target_: transformers.T5EncoderModel.from_pretrained
+  pretrained_model_name_or_path: t5-base
+model_vision:
+  _target_: moto_gpt.src.models.mae_model.MaeEncoder
+  use_obs_feature: true
+  pretrained_model_name_or_path: facebook/vit-mae-large
+model_causal_transformer:
+  _target_: moto_gpt.src.models.trajectory_gpt2.GPT2Model
+  config:
+    _target_: moto_gpt.src.models.trajectory_gpt2.GPT2Config
+    vocab_size: 1
+    n_embd: 768
+    n_layer: 12
+    n_head: 12
+    activation_function: relu
+    dropout: 0.1
+    n_positions: 1024
+act_dim: 7
+hidden_size: 768
+sequence_length: 2
+chunk_size: 9
+per_latent_motion_len: 8
+latent_motion_codebook_size: 128
+latent_motion_pred: true
+act_pred: true
+img_feat_dim: 1024
+patch_feat_dim: 1024
+lang_feat_dim: 768
+mask_latent_motion_probability: 0.5
+freeze_lang: true
+freeze_vision: true
+pred_discrete_arm_action: true

moto_gpt_finetuned_on_banana_disassembly_laptop/data_banana_disassembly_laptop-model_actPredTrueDiscrete_motionPredTrue_visionMaeLarge_seq2_chunk9_maskProb0.5-train_lr0.001_bs32_binaryGripperTrue-aug_shiftTrue_resizedCropFalse-resume_from_predLatentOnly_banana_disassembly_laptop_Epoch10/saved_epoch_10_step_1170/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b54173b0bac6b97ee0bf80bcafb2b5555c0bb862c79833e9dfff94ba5ca5ff18
+size 364193934

moto_gpt_finetuned_on_banana_disassembly_laptop/data_banana_disassembly_laptop-model_actPredTrueDiscrete_motionPredTrue_visionMaeLarge_seq2_chunk9_maskProb0.5-train_lr0.001_bs32_binaryGripperTrue-aug_shiftTrue_resizedCropFalse-resume_from_predLatentOnly_banana_disassembly_laptop_Epoch10/saved_epoch_15_step_1755/config.yaml

@@ -0,0 +1,34 @@
+_target_: moto_gpt.src.models.moto_gpt.MotoGPT
+model_lang:
+  _target_: transformers.T5EncoderModel.from_pretrained
+  pretrained_model_name_or_path: t5-base
+model_vision:
+  _target_: moto_gpt.src.models.mae_model.MaeEncoder
+  use_obs_feature: true
+  pretrained_model_name_or_path: facebook/vit-mae-large
+model_causal_transformer:
+  _target_: moto_gpt.src.models.trajectory_gpt2.GPT2Model
+  config:
+    _target_: moto_gpt.src.models.trajectory_gpt2.GPT2Config
+    vocab_size: 1
+    n_embd: 768
+    n_layer: 12
+    n_head: 12
+    activation_function: relu
+    dropout: 0.1
+    n_positions: 1024
+act_dim: 7
+hidden_size: 768
+sequence_length: 2
+chunk_size: 9
+per_latent_motion_len: 8
+latent_motion_codebook_size: 128
+latent_motion_pred: true
+act_pred: true
+img_feat_dim: 1024
+patch_feat_dim: 1024
+lang_feat_dim: 768
+mask_latent_motion_probability: 0.5
+freeze_lang: true
+freeze_vision: true
+pred_discrete_arm_action: true

moto_gpt_finetuned_on_banana_disassembly_laptop/data_banana_disassembly_laptop-model_actPredTrueDiscrete_motionPredTrue_visionMaeLarge_seq2_chunk9_maskProb0.5-train_lr0.001_bs32_binaryGripperTrue-aug_shiftTrue_resizedCropFalse-resume_from_predLatentOnly_banana_disassembly_laptop_Epoch10/saved_epoch_15_step_1755/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86f83449754c5b2e50acf25c4c3c37532b5cfca791c4b38da3d98e86fd07f10e
+size 364193934

moto_gpt_finetuned_on_banana_disassembly_laptop/data_banana_disassembly_laptop-model_actPredTrueDiscrete_motionPredTrue_visionMaeLarge_seq2_chunk9_maskProb0.5-train_lr0.001_bs32_binaryGripperTrue-aug_shiftTrue_resizedCropFalse-resume_from_predLatentOnly_banana_disassembly_laptop_Epoch10/saved_epoch_20_step_2340/config.yaml

@@ -0,0 +1,34 @@
+_target_: moto_gpt.src.models.moto_gpt.MotoGPT
+model_lang:
+  _target_: transformers.T5EncoderModel.from_pretrained
+  pretrained_model_name_or_path: t5-base
+model_vision:
+  _target_: moto_gpt.src.models.mae_model.MaeEncoder
+  use_obs_feature: true
+  pretrained_model_name_or_path: facebook/vit-mae-large
+model_causal_transformer:
+  _target_: moto_gpt.src.models.trajectory_gpt2.GPT2Model
+  config:
+    _target_: moto_gpt.src.models.trajectory_gpt2.GPT2Config
+    vocab_size: 1
+    n_embd: 768
+    n_layer: 12
+    n_head: 12
+    activation_function: relu
+    dropout: 0.1
+    n_positions: 1024
+act_dim: 7
+hidden_size: 768
+sequence_length: 2
+chunk_size: 9
+per_latent_motion_len: 8
+latent_motion_codebook_size: 128
+latent_motion_pred: true
+act_pred: true
+img_feat_dim: 1024
+patch_feat_dim: 1024
+lang_feat_dim: 768
+mask_latent_motion_probability: 0.5
+freeze_lang: true
+freeze_vision: true
+pred_discrete_arm_action: true

moto_gpt_finetuned_on_banana_disassembly_laptop/data_banana_disassembly_laptop-model_actPredTrueDiscrete_motionPredTrue_visionMaeLarge_seq2_chunk9_maskProb0.5-train_lr0.001_bs32_binaryGripperTrue-aug_shiftTrue_resizedCropFalse-resume_from_predLatentOnly_banana_disassembly_laptop_Epoch10/saved_epoch_20_step_2340/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cc463761beb0044a9e04d77d89c3a01ff6b79b29af40e76d58c3c1d2b9d1b7a
+size 364193934

moto_gpt_finetuned_on_banana_disassembly_laptop/data_banana_disassembly_laptop-model_actPredTrueDiscrete_motionPredTrue_visionMaeLarge_seq2_chunk9_maskProb0.5-train_lr0.001_bs32_binaryGripperTrue-aug_shiftTrue_resizedCropFalse-resume_from_predLatentOnly_banana_disassembly_laptop_Epoch10/saved_epoch_3_step_351/config.yaml

@@ -0,0 +1,34 @@
+_target_: moto_gpt.src.models.moto_gpt.MotoGPT
+model_lang:
+  _target_: transformers.T5EncoderModel.from_pretrained
+  pretrained_model_name_or_path: t5-base
+model_vision:
+  _target_: moto_gpt.src.models.mae_model.MaeEncoder
+  use_obs_feature: true
+  pretrained_model_name_or_path: facebook/vit-mae-large
+model_causal_transformer:
+  _target_: moto_gpt.src.models.trajectory_gpt2.GPT2Model
+  config:
+    _target_: moto_gpt.src.models.trajectory_gpt2.GPT2Config
+    vocab_size: 1
+    n_embd: 768
+    n_layer: 12
+    n_head: 12
+    activation_function: relu
+    dropout: 0.1
+    n_positions: 1024
+act_dim: 7
+hidden_size: 768
+sequence_length: 2
+chunk_size: 9
+per_latent_motion_len: 8
+latent_motion_codebook_size: 128
+latent_motion_pred: true
+act_pred: true
+img_feat_dim: 1024
+patch_feat_dim: 1024
+lang_feat_dim: 768
+mask_latent_motion_probability: 0.5
+freeze_lang: true
+freeze_vision: true
+pred_discrete_arm_action: true

moto_gpt_finetuned_on_banana_disassembly_laptop/data_banana_disassembly_laptop-model_actPredTrueDiscrete_motionPredTrue_visionMaeLarge_seq2_chunk9_maskProb0.5-train_lr0.001_bs32_binaryGripperTrue-aug_shiftTrue_resizedCropFalse-resume_from_predLatentOnly_banana_disassembly_laptop_Epoch10/saved_epoch_3_step_351/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:415b2248377b887fd8e866f45b55b807fd7de1008f0b5e7cd07d0c8e4b680242
+size 364193934

moto_gpt_finetuned_on_banana_disassembly_laptop/data_banana_disassembly_laptop-model_actPredTrueDiscrete_motionPredTrue_visionMaeLarge_seq2_chunk9_maskProb0.5-train_lr0.001_bs32_binaryGripperTrue-aug_shiftTrue_resizedCropFalse-resume_from_predLatentOnly_banana_disassembly_laptop_Epoch10/saved_epoch_5_step_585/config.yaml

@@ -0,0 +1,34 @@
+_target_: moto_gpt.src.models.moto_gpt.MotoGPT
+model_lang:
+  _target_: transformers.T5EncoderModel.from_pretrained
+  pretrained_model_name_or_path: t5-base
+model_vision:
+  _target_: moto_gpt.src.models.mae_model.MaeEncoder
+  use_obs_feature: true
+  pretrained_model_name_or_path: facebook/vit-mae-large
+model_causal_transformer:
+  _target_: moto_gpt.src.models.trajectory_gpt2.GPT2Model
+  config:
+    _target_: moto_gpt.src.models.trajectory_gpt2.GPT2Config
+    vocab_size: 1
+    n_embd: 768
+    n_layer: 12
+    n_head: 12
+    activation_function: relu
+    dropout: 0.1
+    n_positions: 1024
+act_dim: 7
+hidden_size: 768
+sequence_length: 2
+chunk_size: 9
+per_latent_motion_len: 8
+latent_motion_codebook_size: 128
+latent_motion_pred: true
+act_pred: true
+img_feat_dim: 1024
+patch_feat_dim: 1024
+lang_feat_dim: 768
+mask_latent_motion_probability: 0.5
+freeze_lang: true
+freeze_vision: true
+pred_discrete_arm_action: true

moto_gpt_finetuned_on_banana_disassembly_laptop/data_banana_disassembly_laptop-model_actPredTrueDiscrete_motionPredTrue_visionMaeLarge_seq2_chunk9_maskProb0.5-train_lr0.001_bs32_binaryGripperTrue-aug_shiftTrue_resizedCropFalse-resume_from_predLatentOnly_banana_disassembly_laptop_Epoch10/saved_epoch_5_step_585/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d6a08f99081953711b70679b4041debdf7e8d43a4f0696d327276726cb748e1
+size 364193934

moto_gpt_finetuned_on_banana_disassembly_laptop/data_banana_disassembly_laptop-model_actPredTrueDiscrete_motionPredTrue_visionMaeLarge_seq2_chunk9_maskProb0.5-train_lr0.001_bs32_binaryGripperTrue-aug_shiftTrue_resizedCropFalse-resume_from_predLatentOnly_banana_disassembly_laptop_Epoch5/saved_epoch_10_step_1170/config.yaml

@@ -0,0 +1,34 @@
+_target_: moto_gpt.src.models.moto_gpt.MotoGPT
+model_lang:
+  _target_: transformers.T5EncoderModel.from_pretrained
+  pretrained_model_name_or_path: t5-base
+model_vision:
+  _target_: moto_gpt.src.models.mae_model.MaeEncoder
+  use_obs_feature: true
+  pretrained_model_name_or_path: facebook/vit-mae-large
+model_causal_transformer:
+  _target_: moto_gpt.src.models.trajectory_gpt2.GPT2Model
+  config:
+    _target_: moto_gpt.src.models.trajectory_gpt2.GPT2Config
+    vocab_size: 1
+    n_embd: 768
+    n_layer: 12
+    n_head: 12
+    activation_function: relu
+    dropout: 0.1
+    n_positions: 1024
+act_dim: 7
+hidden_size: 768
+sequence_length: 2
+chunk_size: 9
+per_latent_motion_len: 8
+latent_motion_codebook_size: 128
+latent_motion_pred: true
+act_pred: true
+img_feat_dim: 1024
+patch_feat_dim: 1024
+lang_feat_dim: 768
+mask_latent_motion_probability: 0.5
+freeze_lang: true
+freeze_vision: true
+pred_discrete_arm_action: true

moto_gpt_finetuned_on_banana_disassembly_laptop/data_banana_disassembly_laptop-model_actPredTrueDiscrete_motionPredTrue_visionMaeLarge_seq2_chunk9_maskProb0.5-train_lr0.001_bs32_binaryGripperTrue-aug_shiftTrue_resizedCropFalse-resume_from_predLatentOnly_banana_disassembly_laptop_Epoch5/saved_epoch_10_step_1170/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acd1a209470531626e08acc15c1545a483c0c2fbbebdc5335b71f48368bb8eb0
+size 364193934

moto_gpt_finetuned_on_banana_disassembly_laptop/data_banana_disassembly_laptop-model_actPredTrueDiscrete_motionPredTrue_visionMaeLarge_seq2_chunk9_maskProb0.5-train_lr0.001_bs32_binaryGripperTrue-aug_shiftTrue_resizedCropFalse-resume_from_predLatentOnly_banana_disassembly_laptop_Epoch5/saved_epoch_15_step_1755/config.yaml

@@ -0,0 +1,34 @@
+_target_: moto_gpt.src.models.moto_gpt.MotoGPT
+model_lang:
+  _target_: transformers.T5EncoderModel.from_pretrained
+  pretrained_model_name_or_path: t5-base
+model_vision:
+  _target_: moto_gpt.src.models.mae_model.MaeEncoder
+  use_obs_feature: true
+  pretrained_model_name_or_path: facebook/vit-mae-large
+model_causal_transformer:
+  _target_: moto_gpt.src.models.trajectory_gpt2.GPT2Model
+  config:
+    _target_: moto_gpt.src.models.trajectory_gpt2.GPT2Config
+    vocab_size: 1
+    n_embd: 768
+    n_layer: 12
+    n_head: 12
+    activation_function: relu
+    dropout: 0.1
+    n_positions: 1024
+act_dim: 7
+hidden_size: 768
+sequence_length: 2
+chunk_size: 9
+per_latent_motion_len: 8
+latent_motion_codebook_size: 128
+latent_motion_pred: true
+act_pred: true
+img_feat_dim: 1024
+patch_feat_dim: 1024
+lang_feat_dim: 768
+mask_latent_motion_probability: 0.5
+freeze_lang: true
+freeze_vision: true
+pred_discrete_arm_action: true

moto_gpt_finetuned_on_banana_disassembly_laptop/data_banana_disassembly_laptop-model_actPredTrueDiscrete_motionPredTrue_visionMaeLarge_seq2_chunk9_maskProb0.5-train_lr0.001_bs32_binaryGripperTrue-aug_shiftTrue_resizedCropFalse-resume_from_predLatentOnly_banana_disassembly_laptop_Epoch5/saved_epoch_15_step_1755/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89c44f1db518223280240cfb217800c39561a149adecf4f6bf8077abefc0ae9e
+size 364193934

moto_gpt_finetuned_on_banana_disassembly_laptop/data_banana_disassembly_laptop-model_actPredTrueDiscrete_motionPredTrue_visionMaeLarge_seq2_chunk9_maskProb0.5-train_lr0.001_bs32_binaryGripperTrue-aug_shiftTrue_resizedCropFalse-resume_from_predLatentOnly_banana_disassembly_laptop_Epoch5/saved_epoch_20_step_2340/config.yaml

@@ -0,0 +1,34 @@
+_target_: moto_gpt.src.models.moto_gpt.MotoGPT
+model_lang:
+  _target_: transformers.T5EncoderModel.from_pretrained
+  pretrained_model_name_or_path: t5-base
+model_vision:
+  _target_: moto_gpt.src.models.mae_model.MaeEncoder
+  use_obs_feature: true
+  pretrained_model_name_or_path: facebook/vit-mae-large
+model_causal_transformer:
+  _target_: moto_gpt.src.models.trajectory_gpt2.GPT2Model
+  config:
+    _target_: moto_gpt.src.models.trajectory_gpt2.GPT2Config
+    vocab_size: 1
+    n_embd: 768
+    n_layer: 12
+    n_head: 12
+    activation_function: relu
+    dropout: 0.1
+    n_positions: 1024
+act_dim: 7
+hidden_size: 768
+sequence_length: 2
+chunk_size: 9
+per_latent_motion_len: 8
+latent_motion_codebook_size: 128
+latent_motion_pred: true
+act_pred: true
+img_feat_dim: 1024
+patch_feat_dim: 1024
+lang_feat_dim: 768
+mask_latent_motion_probability: 0.5
+freeze_lang: true
+freeze_vision: true
+pred_discrete_arm_action: true

moto_gpt_finetuned_on_banana_disassembly_laptop/data_banana_disassembly_laptop-model_actPredTrueDiscrete_motionPredTrue_visionMaeLarge_seq2_chunk9_maskProb0.5-train_lr0.001_bs32_binaryGripperTrue-aug_shiftTrue_resizedCropFalse-resume_from_predLatentOnly_banana_disassembly_laptop_Epoch5/saved_epoch_20_step_2340/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f2d7c2cfd93499e1dcd8a75305b4dea7c7583043ca9b0d6265bf584980ab028
+size 364193934

moto_gpt_finetuned_on_banana_disassembly_laptop/data_banana_disassembly_laptop-model_actPredTrueDiscrete_motionPredTrue_visionMaeLarge_seq2_chunk9_maskProb0.5-train_lr0.001_bs32_binaryGripperTrue-aug_shiftTrue_resizedCropFalse-resume_from_predLatentOnly_banana_disassembly_laptop_Epoch5/saved_epoch_3_step_351/config.yaml

@@ -0,0 +1,34 @@
+_target_: moto_gpt.src.models.moto_gpt.MotoGPT
+model_lang:
+  _target_: transformers.T5EncoderModel.from_pretrained
+  pretrained_model_name_or_path: t5-base
+model_vision:
+  _target_: moto_gpt.src.models.mae_model.MaeEncoder
+  use_obs_feature: true
+  pretrained_model_name_or_path: facebook/vit-mae-large
+model_causal_transformer:
+  _target_: moto_gpt.src.models.trajectory_gpt2.GPT2Model
+  config:
+    _target_: moto_gpt.src.models.trajectory_gpt2.GPT2Config
+    vocab_size: 1
+    n_embd: 768
+    n_layer: 12
+    n_head: 12
+    activation_function: relu
+    dropout: 0.1
+    n_positions: 1024
+act_dim: 7
+hidden_size: 768
+sequence_length: 2
+chunk_size: 9
+per_latent_motion_len: 8
+latent_motion_codebook_size: 128
+latent_motion_pred: true
+act_pred: true
+img_feat_dim: 1024
+patch_feat_dim: 1024
+lang_feat_dim: 768
+mask_latent_motion_probability: 0.5
+freeze_lang: true
+freeze_vision: true
+pred_discrete_arm_action: true

moto_gpt_finetuned_on_banana_disassembly_laptop/data_banana_disassembly_laptop-model_actPredTrueDiscrete_motionPredTrue_visionMaeLarge_seq2_chunk9_maskProb0.5-train_lr0.001_bs32_binaryGripperTrue-aug_shiftTrue_resizedCropFalse-resume_from_predLatentOnly_banana_disassembly_laptop_Epoch5/saved_epoch_3_step_351/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdd4e3b666cf7883268314f2a5f0931c64a06ed6df1537c23e92896f6e95a044
+size 364193934

moto_gpt_finetuned_on_banana_disassembly_laptop/data_banana_disassembly_laptop-model_actPredTrueDiscrete_motionPredTrue_visionMaeLarge_seq2_chunk9_maskProb0.5-train_lr0.001_bs32_binaryGripperTrue-aug_shiftTrue_resizedCropFalse-resume_from_predLatentOnly_banana_disassembly_laptop_Epoch5/saved_epoch_5_step_585/config.yaml

@@ -0,0 +1,34 @@
+_target_: moto_gpt.src.models.moto_gpt.MotoGPT
+model_lang:
+  _target_: transformers.T5EncoderModel.from_pretrained
+  pretrained_model_name_or_path: t5-base
+model_vision:
+  _target_: moto_gpt.src.models.mae_model.MaeEncoder
+  use_obs_feature: true
+  pretrained_model_name_or_path: facebook/vit-mae-large
+model_causal_transformer:
+  _target_: moto_gpt.src.models.trajectory_gpt2.GPT2Model
+  config:
+    _target_: moto_gpt.src.models.trajectory_gpt2.GPT2Config
+    vocab_size: 1
+    n_embd: 768
+    n_layer: 12
+    n_head: 12
+    activation_function: relu
+    dropout: 0.1
+    n_positions: 1024
+act_dim: 7
+hidden_size: 768
+sequence_length: 2
+chunk_size: 9
+per_latent_motion_len: 8
+latent_motion_codebook_size: 128
+latent_motion_pred: true
+act_pred: true
+img_feat_dim: 1024
+patch_feat_dim: 1024
+lang_feat_dim: 768
+mask_latent_motion_probability: 0.5
+freeze_lang: true
+freeze_vision: true
+pred_discrete_arm_action: true

moto_gpt_finetuned_on_banana_disassembly_laptop/data_banana_disassembly_laptop-model_actPredTrueDiscrete_motionPredTrue_visionMaeLarge_seq2_chunk9_maskProb0.5-train_lr0.001_bs32_binaryGripperTrue-aug_shiftTrue_resizedCropFalse-resume_from_predLatentOnly_banana_disassembly_laptop_Epoch5/saved_epoch_5_step_585/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a2a89cd1e6b152204b9f41cd9178a136e92df1acc4ada93b12154ac192a105e
+size 364193934