Training completed - 1000 steps

config.json

@@ -1,10 +1,10 @@
 {
-    "type": "act",
-    "n_obs_steps": 1,
+    "type": "diffusion",
+    "n_obs_steps": 2,
     "normalization_mapping": {
         "VISUAL": "MEAN_STD",
-        "STATE": "MEAN_STD",
-        "ACTION": "MEAN_STD"
+        "STATE": "MIN_MAX",
+        "ACTION": "MIN_MAX"
     },
     "input_features": {
         "observation.state": {
@@ -47,25 +47,45 @@
         "cubix"
     ],
     "license": null,
-    "chunk_size": 100,
-    "n_action_steps": 100,
+    "horizon": 16,
+    "n_action_steps": 8,
+    "drop_n_last_frames": 7,
     "vision_backbone": "resnet18",
-    "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
-    "replace_final_stride_with_dilation": false,
-    "pre_norm": false,
-    "dim_model": 512,
-    "n_heads": 8,
-    "dim_feedforward": 3200,
-    "feedforward_activation": "relu",
-    "n_encoder_layers": 4,
-    "n_decoder_layers": 1,
-    "use_vae": true,
-    "latent_dim": 32,
-    "n_vae_encoder_layers": 4,
-    "temporal_ensemble_coeff": null,
-    "dropout": 0.1,
-    "kl_weight": 10.0,
-    "optimizer_lr": 1e-05,
-    "optimizer_weight_decay": 0.0001,
-    "optimizer_lr_backbone": 1e-05
+    "crop_shape": [
+        84,
+        84
+    ],
+    "crop_is_random": true,
+    "pretrained_backbone_weights": null,
+    "use_group_norm": true,
+    "spatial_softmax_num_keypoints": 32,
+    "use_separate_rgb_encoder_per_camera": false,
+    "down_dims": [
+        512,
+        1024,
+        2048
+    ],
+    "kernel_size": 5,
+    "n_groups": 8,
+    "diffusion_step_embed_dim": 128,
+    "use_film_scale_modulation": true,
+    "noise_scheduler_type": "DDPM",
+    "num_train_timesteps": 100,
+    "beta_schedule": "squaredcos_cap_v2",
+    "beta_start": 0.0001,
+    "beta_end": 0.02,
+    "prediction_type": "epsilon",
+    "clip_sample": true,
+    "clip_sample_range": 1.0,
+    "num_inference_steps": null,
+    "do_mask_loss_for_padding": false,
+    "optimizer_lr": 0.0001,
+    "optimizer_betas": [
+        0.95,
+        0.999
+    ],
+    "optimizer_eps": 1e-08,
+    "optimizer_weight_decay": 1e-06,
+    "scheduler_name": "cosine",
+    "scheduler_warmup_steps": 500
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4284af35abfb3e40f562e2e1e24adc2313164beb4cbe436a39defe00a5a3b211
-size 206701072
+oid sha256:73c41676b51c29b2fa69dde6b137bef70ec2e446b050f4aa19dbc606d17f165b
+size 1066517736

train_config.json

@@ -66,12 +66,12 @@
     },
     "env": null,
     "policy": {
-        "type": "act",
-        "n_obs_steps": 1,
+        "type": "diffusion",
+        "n_obs_steps": 2,
         "normalization_mapping": {
             "VISUAL": "MEAN_STD",
-            "STATE": "MEAN_STD",
-            "ACTION": "MEAN_STD"
+            "STATE": "MIN_MAX",
+            "ACTION": "MIN_MAX"
         },
         "input_features": {
             "observation.state": {
@@ -114,29 +114,49 @@
             "cubix"
         ],
         "license": null,
-        "chunk_size": 100,
-        "n_action_steps": 100,
+        "horizon": 16,
+        "n_action_steps": 8,
+        "drop_n_last_frames": 7,
         "vision_backbone": "resnet18",
-        "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
-        "replace_final_stride_with_dilation": false,
-        "pre_norm": false,
-        "dim_model": 512,
-        "n_heads": 8,
-        "dim_feedforward": 3200,
-        "feedforward_activation": "relu",
-        "n_encoder_layers": 4,
-        "n_decoder_layers": 1,
-        "use_vae": true,
-        "latent_dim": 32,
-        "n_vae_encoder_layers": 4,
-        "temporal_ensemble_coeff": null,
-        "dropout": 0.1,
-        "kl_weight": 10.0,
-        "optimizer_lr": 1e-05,
-        "optimizer_weight_decay": 0.0001,
-        "optimizer_lr_backbone": 1e-05
+        "crop_shape": [
+            84,
+            84
+        ],
+        "crop_is_random": true,
+        "pretrained_backbone_weights": null,
+        "use_group_norm": true,
+        "spatial_softmax_num_keypoints": 32,
+        "use_separate_rgb_encoder_per_camera": false,
+        "down_dims": [
+            512,
+            1024,
+            2048
+        ],
+        "kernel_size": 5,
+        "n_groups": 8,
+        "diffusion_step_embed_dim": 128,
+        "use_film_scale_modulation": true,
+        "noise_scheduler_type": "DDPM",
+        "num_train_timesteps": 100,
+        "beta_schedule": "squaredcos_cap_v2",
+        "beta_start": 0.0001,
+        "beta_end": 0.02,
+        "prediction_type": "epsilon",
+        "clip_sample": true,
+        "clip_sample_range": 1.0,
+        "num_inference_steps": null,
+        "do_mask_loss_for_padding": false,
+        "optimizer_lr": 0.0001,
+        "optimizer_betas": [
+            0.95,
+            0.999
+        ],
+        "optimizer_eps": 1e-08,
+        "optimizer_weight_decay": 1e-06,
+        "scheduler_name": "cosine",
+        "scheduler_warmup_steps": 500
     },
-    "output_dir": "/tmp/lerobot_training_1752880447268_d0991f10",
+    "output_dir": "/tmp/lerobot_training_1752880695094_bed25fb3",
     "job_name": "testing trainging",
     "resume": false,
     "seed": 1000,
@@ -149,17 +169,21 @@
     "save_freq": 20000,
     "use_policy_training_preset": true,
     "optimizer": {
-        "type": "adamw",
-        "lr": 1e-05,
-        "weight_decay": 0.0001,
+        "type": "adam",
+        "lr": 0.0001,
+        "weight_decay": 1e-06,
         "grad_clip_norm": 10.0,
         "betas": [
-            0.9,
+            0.95,
             0.999
         ],
         "eps": 1e-08
     },
-    "scheduler": null,
+    "scheduler": {
+        "type": "diffuser",
+        "num_warmup_steps": 500,
+        "name": "cosine"
+    },
     "eval": {
         "n_episodes": 50,
         "batch_size": 50,