Tiredsheep commited on
Commit
d12eb6d
·
verified ·
1 Parent(s): 3eb6327

Upload folder using huggingface_hub

Browse files
Files changed (46) hide show
  1. metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/.hydra/config.yaml +85 -0
  2. metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/.hydra/hydra.yaml +154 -0
  3. metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/.hydra/overrides.yaml +1 -0
  4. metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/SAC_1/events.out.tfevents.1765879788.rll1011.355867.0 +3 -0
  5. metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/checkpoint/final.zip +3 -0
  6. metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/checkpoint/ft_policy_1000000_steps.zip +3 -0
  7. metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/checkpoint/ft_policy_1250000_steps.zip +3 -0
  8. metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/checkpoint/ft_policy_1500000_steps.zip +3 -0
  9. metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/checkpoint/ft_policy_1750000_steps.zip +3 -0
  10. metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/checkpoint/ft_policy_2000000_steps.zip +3 -0
  11. metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/checkpoint/ft_policy_2250000_steps.zip +3 -0
  12. metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/checkpoint/ft_policy_2500000_steps.zip +3 -0
  13. metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/checkpoint/ft_policy_250000_steps.zip +3 -0
  14. metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/checkpoint/ft_policy_2750000_steps.zip +3 -0
  15. metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/checkpoint/ft_policy_3000000_steps.zip +3 -0
  16. metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/checkpoint/ft_policy_3250000_steps.zip +3 -0
  17. metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/checkpoint/ft_policy_3500000_steps.zip +3 -0
  18. metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/checkpoint/ft_policy_3750000_steps.zip +3 -0
  19. metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/checkpoint/ft_policy_4000000_steps.zip +3 -0
  20. metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/checkpoint/ft_policy_4250000_steps.zip +3 -0
  21. metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/checkpoint/ft_policy_4500000_steps.zip +3 -0
  22. metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/checkpoint/ft_policy_4750000_steps.zip +3 -0
  23. metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/checkpoint/ft_policy_5000000_steps.zip +3 -0
  24. metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/checkpoint/ft_policy_500000_steps.zip +3 -0
  25. metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/checkpoint/ft_policy_750000_steps.zip +3 -0
  26. metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/checkpoint/ft_policy_replay_buffer_1000000_steps.pkl +3 -0
  27. metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/checkpoint/ft_policy_replay_buffer_1250000_steps.pkl +3 -0
  28. metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/checkpoint/ft_policy_replay_buffer_1500000_steps.pkl +3 -0
  29. metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/checkpoint/ft_policy_replay_buffer_1750000_steps.pkl +3 -0
  30. metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/checkpoint/ft_policy_replay_buffer_2000000_steps.pkl +3 -0
  31. metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/checkpoint/ft_policy_replay_buffer_2250000_steps.pkl +3 -0
  32. metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/checkpoint/ft_policy_replay_buffer_2500000_steps.pkl +3 -0
  33. metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/checkpoint/ft_policy_replay_buffer_250000_steps.pkl +3 -0
  34. metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/checkpoint/ft_policy_replay_buffer_2750000_steps.pkl +3 -0
  35. metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/checkpoint/ft_policy_replay_buffer_3000000_steps.pkl +3 -0
  36. metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/checkpoint/ft_policy_replay_buffer_3250000_steps.pkl +3 -0
  37. metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/checkpoint/ft_policy_replay_buffer_3500000_steps.pkl +3 -0
  38. metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/checkpoint/ft_policy_replay_buffer_3750000_steps.pkl +3 -0
  39. metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/checkpoint/ft_policy_replay_buffer_4000000_steps.pkl +3 -0
  40. metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/checkpoint/ft_policy_replay_buffer_4250000_steps.pkl +3 -0
  41. metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/checkpoint/ft_policy_replay_buffer_4500000_steps.pkl +3 -0
  42. metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/checkpoint/ft_policy_replay_buffer_4750000_steps.pkl +3 -0
  43. metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/checkpoint/ft_policy_replay_buffer_5000000_steps.pkl +3 -0
  44. metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/checkpoint/ft_policy_replay_buffer_500000_steps.pkl +3 -0
  45. metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/checkpoint/ft_policy_replay_buffer_750000_steps.pkl +3 -0
  46. metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/train_dsrl.log +3 -0
metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/.hydra/config.yaml ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ name: metaworld_${env_name}_dsrl_${now:%Y-%m-%d}_${now:%H-%M-%S}_${seed}
2
+ logdir: ${log_dir}/metaworld-dsrl/${now:%Y-%m-%d}/${name}
3
+ base_policy_path: ./dppo/log/metaworld-pretrain/dial-turn-v3_pre_diffusion_mlp_ta1_td30/2025-11-29_09-16-40_42/checkpoint/state_5000.pt
4
+ dppo_path: ./dppo
5
+ normalization_path: ./dppo/log/metaworld/${env_name}/normalization.npz
6
+ algorithm: dsrl_na
7
+ seed: 1
8
+ device: cuda:0
9
+ use_wandb: true
10
+ env_name: dial-turn-v3
11
+ log_dir: ./logs
12
+ obs_dim: 39
13
+ action_dim: 4
14
+ cond_steps: 1
15
+ act_steps: 1
16
+ load_offline_data: false
17
+ deterministic_eval: false
18
+ eval_interval: 12500
19
+ num_evals: 200
20
+ save_model_interval: 12500
21
+ save_replay_buffer: true
22
+ env:
23
+ n_envs: 20
24
+ n_eval_envs: 25
25
+ name: ${env_name}
26
+ max_episode_steps: 150
27
+ reset_at_iteration: false
28
+ save_video: false
29
+ use_success_info: true
30
+ sparse_reward: false
31
+ reward_offset: 1
32
+ wrappers:
33
+ metaworld_lowdim:
34
+ normalization_path: ${normalization_path}
35
+ multi_step:
36
+ n_obs_steps: ${cond_steps}
37
+ n_action_steps: ${act_steps}
38
+ max_episode_steps: ${env.max_episode_steps}
39
+ reset_within_step: true
40
+ wandb:
41
+ project: dsrl-metaworld-${env_name}
42
+ run: ${now:%H-%M-%S}_${name}
43
+ group: metaworld-dial-turn-v3
44
+ train:
45
+ total_timesteps: 5000000
46
+ tau: 0.005
47
+ actor_lr: 5.0e-05
48
+ batch_size: 256
49
+ train_freq: 1
50
+ utd: 20
51
+ noise_critic_grad_steps: 10
52
+ use_layer_norm: true
53
+ layer_size: 512
54
+ num_layers: 3
55
+ discount: 0.9
56
+ ent_coef: -1
57
+ target_ent: 0.0
58
+ init_rollout_steps: 1501
59
+ action_magnitude: 1.5
60
+ n_critics: 2
61
+ critic_backup_combine_type: min
62
+ model:
63
+ _target_: model.diffusion.diffusion_eval.DiffusionEval
64
+ ft_denoising_steps: 0
65
+ predict_epsilon: true
66
+ denoised_clip_value: 1.0
67
+ network_path: ${base_policy_path}
68
+ network:
69
+ _target_: model.diffusion.mlp_diffusion.DiffusionMLP
70
+ time_dim: 16
71
+ mlp_dims:
72
+ - 16
73
+ - 16
74
+ residual_style: false
75
+ cond_dim: ${eval:'${obs_dim} * ${cond_steps}'}
76
+ horizon_steps: ${act_steps}
77
+ action_dim: ${action_dim}
78
+ horizon_steps: ${act_steps}
79
+ obs_dim: ${obs_dim}
80
+ action_dim: ${action_dim}
81
+ denoising_steps: 30
82
+ device: ${device}
83
+ use_ddim: true
84
+ ddim_steps: 2
85
+ controllable_noise: true
metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/.hydra/hydra.yaml ADDED
@@ -0,0 +1,154 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ hydra:
2
+ run:
3
+ dir: ${logdir}
4
+ sweep:
5
+ dir: multirun/${now:%Y-%m-%d}/${now:%H-%M-%S}
6
+ subdir: ${hydra.job.num}
7
+ launcher:
8
+ _target_: hydra._internal.core_plugins.basic_launcher.BasicLauncher
9
+ sweeper:
10
+ _target_: hydra._internal.core_plugins.basic_sweeper.BasicSweeper
11
+ max_batch_size: null
12
+ params: null
13
+ help:
14
+ app_name: ${hydra.job.name}
15
+ header: '${hydra.help.app_name} is powered by Hydra.
16
+
17
+ '
18
+ footer: 'Powered by Hydra (https://hydra.cc)
19
+
20
+ Use --hydra-help to view Hydra specific help
21
+
22
+ '
23
+ template: '${hydra.help.header}
24
+
25
+ == Configuration groups ==
26
+
27
+ Compose your configuration from those groups (group=option)
28
+
29
+
30
+ $APP_CONFIG_GROUPS
31
+
32
+
33
+ == Config ==
34
+
35
+ Override anything in the config (foo.bar=value)
36
+
37
+
38
+ $CONFIG
39
+
40
+
41
+ ${hydra.help.footer}
42
+
43
+ '
44
+ hydra_help:
45
+ template: 'Hydra (${hydra.runtime.version})
46
+
47
+ See https://hydra.cc for more info.
48
+
49
+
50
+ == Flags ==
51
+
52
+ $FLAGS_HELP
53
+
54
+
55
+ == Configuration groups ==
56
+
57
+ Compose your configuration from those groups (For example, append hydra/job_logging=disabled
58
+ to command line)
59
+
60
+
61
+ $HYDRA_CONFIG_GROUPS
62
+
63
+
64
+ Use ''--cfg hydra'' to Show the Hydra config.
65
+
66
+ '
67
+ hydra_help: ???
68
+ hydra_logging:
69
+ version: 1
70
+ formatters:
71
+ simple:
72
+ format: '[%(asctime)s][HYDRA] %(message)s'
73
+ handlers:
74
+ console:
75
+ class: logging.StreamHandler
76
+ formatter: simple
77
+ stream: ext://sys.stdout
78
+ root:
79
+ level: INFO
80
+ handlers:
81
+ - console
82
+ loggers:
83
+ logging_example:
84
+ level: DEBUG
85
+ disable_existing_loggers: false
86
+ job_logging:
87
+ version: 1
88
+ formatters:
89
+ simple:
90
+ format: '[%(asctime)s][%(name)s][%(levelname)s] - %(message)s'
91
+ handlers:
92
+ console:
93
+ class: logging.StreamHandler
94
+ formatter: simple
95
+ stream: ext://sys.stdout
96
+ file:
97
+ class: logging.FileHandler
98
+ formatter: simple
99
+ filename: ${hydra.runtime.output_dir}/${hydra.job.name}.log
100
+ root:
101
+ level: INFO
102
+ handlers:
103
+ - console
104
+ - file
105
+ disable_existing_loggers: false
106
+ env: {}
107
+ mode: RUN
108
+ searchpath: []
109
+ callbacks: {}
110
+ output_subdir: .hydra
111
+ overrides:
112
+ hydra:
113
+ - hydra.mode=RUN
114
+ task: []
115
+ job:
116
+ name: train_dsrl
117
+ chdir: null
118
+ override_dirname: ''
119
+ id: ???
120
+ num: ???
121
+ config_name: dsrl_dial-turn-v3.yaml
122
+ env_set: {}
123
+ env_copy: []
124
+ config:
125
+ override_dirname:
126
+ kv_sep: '='
127
+ item_sep: ','
128
+ exclude_keys: []
129
+ runtime:
130
+ version: 1.3.2
131
+ version_base: '1.3'
132
+ cwd: /tmp2/tiredsheep/dsdp
133
+ config_sources:
134
+ - path: hydra.conf
135
+ schema: pkg
136
+ provider: hydra
137
+ - path: /tmp2/tiredsheep/dsdp/cfg/metaworld/dsrl
138
+ schema: file
139
+ provider: main
140
+ - path: ''
141
+ schema: structured
142
+ provider: schema
143
+ output_dir: /tmp2/tiredsheep/dsdp/logs/metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1
144
+ choices:
145
+ hydra/env: default
146
+ hydra/callbacks: null
147
+ hydra/job_logging: default
148
+ hydra/hydra_logging: default
149
+ hydra/hydra_help: default
150
+ hydra/help: default
151
+ hydra/sweeper: basic
152
+ hydra/launcher: basic
153
+ hydra/output: default
154
+ verbose: false
metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/.hydra/overrides.yaml ADDED
@@ -0,0 +1 @@
 
 
1
+ []
metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/SAC_1/events.out.tfevents.1765879788.rll1011.355867.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e834387ac6a3cafeaea03346c8e767a753eaaa8b7a1a4d1c9c50396b202d5ca4
3
+ size 1982838
metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/checkpoint/final.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2736a7d17de51d15d5c9743753e0f6db8aad3d6efb099fe030e6d04ce2886141
3
+ size 28832755
metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/checkpoint/ft_policy_1000000_steps.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86e111d783c2d95bc8b912950e9c56a8a165b4788dc92405f369ff084c0a864e
3
+ size 28832768
metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/checkpoint/ft_policy_1250000_steps.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b06311d03e2ec7989e20b386580c9d4bd6f4a90f763015c76a3e031e69e90bf
3
+ size 28832759
metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/checkpoint/ft_policy_1500000_steps.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1fb5d5b28721a1cd64a0d06362867b2179d14387bd068bee99239118060c829
3
+ size 28832769
metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/checkpoint/ft_policy_1750000_steps.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e841a66a7e82079de0bc3c277879f4e6bbf18082c991d4a410637a2750c44462
3
+ size 28832760
metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/checkpoint/ft_policy_2000000_steps.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ace2d19e2ca3483ccc13bbdd716af2eb33fe1de4ebaa99491aff1eda3ba60a7e
3
+ size 28832760
metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/checkpoint/ft_policy_2250000_steps.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1de84ac68a22b0a436cfd4cafb9aebee87f52b9e40a4c7e2c24b83c0fc296b4
3
+ size 28832770
metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/checkpoint/ft_policy_2500000_steps.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:692d070a32a95db1296478830d2af4e411ea927013db755697294182dd549907
3
+ size 28832760
metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/checkpoint/ft_policy_250000_steps.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb898f474df6a24354a19d3802315f01d5abe82e81598bfeb9e2ecd18a67f3db
3
+ size 28832728
metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/checkpoint/ft_policy_2750000_steps.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1eea876282e15b2a735fa28345cc5843db96f66ea829cab5f5b78bdb9a21e9c5
3
+ size 28832771
metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/checkpoint/ft_policy_3000000_steps.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b8cd0146b96e2610b7280654b1d85e7adac2767e4a0e0a48ae39be4985b6999
3
+ size 28832760
metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/checkpoint/ft_policy_3250000_steps.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:145ee4523704a34af12426737c2c0cb8d3f83d2f651c52cab9c561afad376abc
3
+ size 28832760
metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/checkpoint/ft_policy_3500000_steps.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d1c037610352a1d1c379b8230c3d9de663cb4a0a1a0027913bfe1682400a524
3
+ size 28832771
metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/checkpoint/ft_policy_3750000_steps.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c79f9e0cddb9c855a5ff96353da1029cee54785dccd30da3a6886b69c4e4b9cc
3
+ size 28832760
metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/checkpoint/ft_policy_4000000_steps.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5720ff835832e38a1d6280f7ea0f36c2cb61d60345c0cfbfc1c1d7934850f795
3
+ size 28832771
metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/checkpoint/ft_policy_4250000_steps.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e716f6070e3d26176a54726d0e3aa81aa6cc56dd5da0af119bd8b03eddbcd9f4
3
+ size 28832771
metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/checkpoint/ft_policy_4500000_steps.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c1f47f72f495bc251d98fa5b0550c0f4fde13f2890f66dcf05d570d5df07d9c
3
+ size 28832771
metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/checkpoint/ft_policy_4750000_steps.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9601b4b74e1fb1431b713a87a29625747941a916a0844d431cf28e033ed0f5f
3
+ size 28832771
metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/checkpoint/ft_policy_5000000_steps.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16cef92d80e8261b2f0410f8cda72285dd97f5837e8886c8e462bb6f2efacff1
3
+ size 28832770
metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/checkpoint/ft_policy_500000_steps.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e95f0b8d667434f97df793f4f71d01307be6afb26a1a0c1c08e5664e1261898e
3
+ size 28832757
metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/checkpoint/ft_policy_750000_steps.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:653628a811b57ac91e259af2b484a086a1936615a29a97a5792f647431da4f7a
3
+ size 28832757
metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/checkpoint/ft_policy_replay_buffer_1000000_steps.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85a73d495f90a70fdc18ded1a1122903db345461d5645a1ef637e37ef32d64ba
3
+ size 1780001904
metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/checkpoint/ft_policy_replay_buffer_1250000_steps.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5af218937c587504f6c71174ea06f80c5e8a768de02f0cfb1ec9406d923e561
3
+ size 1780001904
metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/checkpoint/ft_policy_replay_buffer_1500000_steps.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16a34640acd6bf7ecd5fbd477549151a7e2f1cc8514ae1f4cc3e762691b97334
3
+ size 1780001906
metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/checkpoint/ft_policy_replay_buffer_1750000_steps.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08cb45400611f0ec26b1e7c87e77111792b5bffb562d41b227dfda6c1b34b46b
3
+ size 1780001906
metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/checkpoint/ft_policy_replay_buffer_2000000_steps.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc19896db08b6321ecd36fa0c57344fb9888589f9f3d5cb0dae3413f2d001bf1
3
+ size 1780001906
metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/checkpoint/ft_policy_replay_buffer_2250000_steps.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d938dd3cb21c9f190abca689e8aceb58d817839f14026ca78e4ec6325c85006
3
+ size 1780001906
metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/checkpoint/ft_policy_replay_buffer_2500000_steps.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a70192562a926b314362b18d9bacc970ec912e58d819a03226a67362891db319
3
+ size 1780001906
metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/checkpoint/ft_policy_replay_buffer_250000_steps.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e96a25b440cce0d21a66793fca2e330555f17687825558a767244d0ccec886a
3
+ size 1780001904
metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/checkpoint/ft_policy_replay_buffer_2750000_steps.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:763b575d281174103f5d7b3b146bdaa52b05921662158f011f932016c651a7a2
3
+ size 1780001906
metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/checkpoint/ft_policy_replay_buffer_3000000_steps.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6ec8dc376ae523c8e76fe174cf688f36d8e8da3e3f6e1d1f64da67936857230
3
+ size 1780001906
metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/checkpoint/ft_policy_replay_buffer_3250000_steps.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0379a277b0119d3e4a6e880897463544a91b521dbb69fe5ac514f3b0543e1375
3
+ size 1780001906
metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/checkpoint/ft_policy_replay_buffer_3500000_steps.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64790661acf4a6149e236537e081d37e3955f3f56fc86b6c0e229f30df70f13f
3
+ size 1780001906
metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/checkpoint/ft_policy_replay_buffer_3750000_steps.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc009677e77704d225e912f41d96ea03bcba40631cd4e5178914c26b87c9a630
3
+ size 1780001906
metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/checkpoint/ft_policy_replay_buffer_4000000_steps.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da4f70229394e4f641d4d196e1fef25183824b22e9d55b43b220b189b7e90f2e
3
+ size 1780001906
metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/checkpoint/ft_policy_replay_buffer_4250000_steps.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cc26d49ff43b702102db32910580eea364e0edc33e5052126d691dcc43dcbff
3
+ size 1780001906
metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/checkpoint/ft_policy_replay_buffer_4500000_steps.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f40ee2f8e7d7c585cef927d3ac374fcc95c40352479f452441bdcd8bc0d831cf
3
+ size 1780001906
metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/checkpoint/ft_policy_replay_buffer_4750000_steps.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89f7aac46e98a4a1b9b42496076c51792c3997866502a931a75d2432bbe159e8
3
+ size 1780001906
metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/checkpoint/ft_policy_replay_buffer_5000000_steps.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77e982918f557b8dc583e280cdefa71870b38f09e04ba10ba8863319b412010e
3
+ size 1780001904
metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/checkpoint/ft_policy_replay_buffer_500000_steps.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:910241b18d023294d0e6ac246abd06fd7eaae881e90a3dca50a50bdc505b4128
3
+ size 1780001904
metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/checkpoint/ft_policy_replay_buffer_750000_steps.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e4458ab7c53042137ea62df28a6a516eec1235c9b470e5e7044e35f0896e1c9
3
+ size 1780001904
metaworld-dsrl/2025-12-16/metaworld_dial-turn-v3_dsrl_2025-12-16_18-08-52_1/train_dsrl.log ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ [2025-12-16 18:08:57,773][root][INFO] - Number of network parameters: 2372
2
+ [2025-12-16 18:08:57,882][root][INFO] - Actor weights not found. Using pre-trained weights!
3
+ [2025-12-16 18:08:57,882][root][INFO] - Loaded base policy weights from ./dppo/log/metaworld-pretrain/dial-turn-v3_pre_diffusion_mlp_ta1_td30/2025-11-29_09-16-40_42/checkpoint/state_5000.pt