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_fanuc_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_fanuc_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 sha256:99a63e3a962fef8ceafebcf034a15606638417a0db683060195d13844ce25cff
+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_fanuc_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_fanuc_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 sha256:60e54c018c3dd2f84deac45e72e567d2f53fef2e18b70b29de448ab9cf8450ed
+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_fanuc_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_fanuc_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:f0a5fe0b78095cb7c01b9792f10578f77968195b08ff65d85241e2a7764ca7fa
+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_fanuc_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_fanuc_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 sha256:2c70a74ffde99b7eefdb3f7bd268dfe75f05daa901cb96b0d3c86590e22ebfb8
+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_fanuc_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_fanuc_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:c75e5f368e06ec58838c65065cf7c0abc51e76572f58f5d7b832d2eac351e106
+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_fanuc_banana_disassembly_laptop_weighted_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_fanuc_banana_disassembly_laptop_weighted_Epoch5/saved_epoch_10_step_1170/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd41ecc0e93062164b0ca25ca1d8a800a5112dc709e9d065ce20a6912ebecdcb
+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_fanuc_banana_disassembly_laptop_weighted_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_fanuc_banana_disassembly_laptop_weighted_Epoch5/saved_epoch_15_step_1755/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed9c8ca835aee01ec58fa698d40a3a80d3a4c125fcf3f0e88ad92829803deb1f
+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_fanuc_banana_disassembly_laptop_weighted_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_fanuc_banana_disassembly_laptop_weighted_Epoch5/saved_epoch_20_step_2340/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c417a77c0a094f6235940026b4cadf80abcf4ab5f538d74a889dea127f401db3
+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_fanuc_banana_disassembly_laptop_weighted_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_fanuc_banana_disassembly_laptop_weighted_Epoch5/saved_epoch_3_step_351/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7aa5657b768007972df90ebb73ee05ab624e0dda8600f011202f2ac48152ec0
+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_fanuc_banana_disassembly_laptop_weighted_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_fanuc_banana_disassembly_laptop_weighted_Epoch5/saved_epoch_5_step_585/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:843ad5719fcc260ccd7d09bcfbf9706bff23aebd2f6fd768572fa9cc7175f318
+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_fanuc_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_fanuc_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 sha256:0090108b818e5bd743ba2660150dd40ae8929f8d21e3560391844e1349d40a9a
+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_fanuc_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_fanuc_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:d2541b34c83d85862ffa2adb804518ca85b9e9c587330ce9b676e8260dc4686a
+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_fanuc_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_fanuc_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:a45fa42c7d2ebe6433ee4056c4d2b1ef41af52fde3ffb54c3092ab44916ad7a9
+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_fanuc_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_fanuc_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:f9781cdbc6a07a999064c24d1f6e4d662a5144c59ce77e890c5a876b9b26f6bc
+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_fanuc_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_fanuc_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 sha256:028dc49791d4a184d9c1d10213b6733dba0bd36991cdd42ca21e4e23665fb0b6
+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_fanuc_banana_disassembly_laptop_weighted_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_fanuc_banana_disassembly_laptop_weighted_Epoch5/saved_epoch_10_step_1170/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1114719b77888209cd0cbc00388f4ab0cbf93f3f1a72bda871ff6bef69981864
+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_fanuc_banana_disassembly_laptop_weighted_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_fanuc_banana_disassembly_laptop_weighted_Epoch5/saved_epoch_15_step_1755/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d14e245c2effae44b76801e806651d265b68e9b420b19603b8e238c77e3519fb
+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_fanuc_banana_disassembly_laptop_weighted_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_fanuc_banana_disassembly_laptop_weighted_Epoch5/saved_epoch_20_step_2340/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdaf18e43e026625e250b73d67571b45b18cfa9749c8107956e3c12137adf781
+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_fanuc_banana_disassembly_laptop_weighted_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_fanuc_banana_disassembly_laptop_weighted_Epoch5/saved_epoch_3_step_351/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c2a3b9bb225c7d65e199624d746e90b5f4d6a0b061a5b863700f60fce705450
+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_fanuc_banana_disassembly_laptop_weighted_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_fanuc_banana_disassembly_laptop_weighted_Epoch5/saved_epoch_5_step_585/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46a237050fc726488e462e0419e7357fcf8af10002576fa783a0a56e3d8db121
+size 364193934