Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- synthetic-rl-v1+sp/ckpts/policy_weights/policy_epoch_40.pt +3 -0
- synthetic-rl-v1+sp/ckpts/policy_weights/policy_epoch_41.pt +3 -0
- synthetic-rl-v1+sp/ckpts/policy_weights/policy_epoch_42.pt +3 -0
- synthetic-rl-v1+sp/ckpts/policy_weights/policy_epoch_43.pt +3 -0
- synthetic-rl-v1+sp/ckpts/policy_weights/policy_epoch_44.pt +3 -0
- synthetic-rl-v1+sp/ckpts/policy_weights/policy_epoch_45.pt +3 -0
- synthetic-rl-v1+sp/ckpts/policy_weights/policy_epoch_46.pt +3 -0
- synthetic-rl-v1+sp/ckpts/policy_weights/policy_epoch_47.pt +3 -0
- synthetic-rl-v1+sp/ckpts/policy_weights/policy_epoch_48.pt +3 -0
- synthetic-rl-v1+sp/ckpts/policy_weights/policy_epoch_49.pt +3 -0
- synthetic-rl-v1+sp/ckpts/policy_weights/policy_epoch_50.pt +3 -0
- synthetic-rl-v1+sp/config.txt +106 -0
- synthetic-rl-v1+sp/large_rl_dpg_binary_synthetic_v2/ckpts/policy_weights/policy_epoch_40.pt +3 -0
- synthetic-rl-v1+sp/large_rl_dpg_binary_synthetic_v2/ckpts/policy_weights/policy_epoch_41.pt +3 -0
- synthetic-rl-v1+sp/large_rl_dpg_binary_synthetic_v2/ckpts/policy_weights/policy_epoch_42.pt +3 -0
- synthetic-rl-v1+sp/large_rl_dpg_binary_synthetic_v2/ckpts/policy_weights/policy_epoch_43.pt +3 -0
- synthetic-rl-v1+sp/large_rl_dpg_binary_synthetic_v2/ckpts/policy_weights/policy_epoch_44.pt +3 -0
- synthetic-rl-v1+sp/large_rl_dpg_binary_synthetic_v2/ckpts/policy_weights/policy_epoch_45.pt +3 -0
- synthetic-rl-v1+sp/large_rl_dpg_binary_synthetic_v2/ckpts/policy_weights/policy_epoch_46.pt +3 -0
- synthetic-rl-v1+sp/large_rl_dpg_binary_synthetic_v2/ckpts/policy_weights/policy_epoch_47.pt +3 -0
- synthetic-rl-v1+sp/large_rl_dpg_binary_synthetic_v2/ckpts/policy_weights/policy_epoch_48.pt +3 -0
- synthetic-rl-v1+sp/large_rl_dpg_binary_synthetic_v2/ckpts/policy_weights/policy_epoch_49.pt +3 -0
- synthetic-rl-v1+sp/large_rl_dpg_binary_synthetic_v2/ckpts/policy_weights/policy_epoch_50.pt +3 -0
- synthetic-rl-v1+sp/large_rl_dpg_binary_synthetic_v2/ckpts/policy_weights/policy_epoch_51.pt +3 -0
- synthetic-rl-v1+sp/large_rl_dpg_binary_synthetic_v2/ckpts/training_states/large_rl_dpg_binary_synthetic_v2_epoch_40/custom_checkpoint_0.pkl +3 -0
- synthetic-rl-v1+sp/large_rl_dpg_binary_synthetic_v2/ckpts/training_states/large_rl_dpg_binary_synthetic_v2_epoch_40/custom_checkpoint_1.pkl +3 -0
- synthetic-rl-v1+sp/large_rl_dpg_binary_synthetic_v2/ckpts/training_states/large_rl_dpg_binary_synthetic_v2_epoch_40/model.safetensors +3 -0
- synthetic-rl-v1+sp/large_rl_dpg_binary_synthetic_v2/ckpts/training_states/large_rl_dpg_binary_synthetic_v2_epoch_40/optimizer.bin +3 -0
- synthetic-rl-v1+sp/large_rl_dpg_binary_synthetic_v2/ckpts/training_states/large_rl_dpg_binary_synthetic_v2_epoch_40/optimizer_1.bin +3 -0
- synthetic-rl-v1+sp/large_rl_dpg_binary_synthetic_v2/ckpts/training_states/large_rl_dpg_binary_synthetic_v2_epoch_40/random_states_0.pkl +3 -0
- synthetic-rl-v1+sp/large_rl_dpg_binary_synthetic_v2/ckpts/training_states/large_rl_dpg_binary_synthetic_v2_epoch_40/random_states_1.pkl +3 -0
- synthetic-rl-v1+sp/large_rl_dpg_binary_synthetic_v2/ckpts/training_states/large_rl_dpg_binary_synthetic_v2_epoch_40/random_states_2.pkl +3 -0
- synthetic-rl-v1+sp/large_rl_dpg_binary_synthetic_v2/ckpts/training_states/large_rl_dpg_binary_synthetic_v2_epoch_40/random_states_3.pkl +3 -0
- synthetic-rl-v1+sp/large_rl_dpg_binary_synthetic_v2/ckpts/training_states/large_rl_dpg_binary_synthetic_v2_epoch_40/random_states_4.pkl +3 -0
- synthetic-rl-v1+sp/large_rl_dpg_binary_synthetic_v2/ckpts/training_states/large_rl_dpg_binary_synthetic_v2_epoch_40/random_states_5.pkl +3 -0
- synthetic-rl-v1+sp/large_rl_dpg_binary_synthetic_v2/ckpts/training_states/large_rl_dpg_binary_synthetic_v2_epoch_40/random_states_6.pkl +3 -0
- synthetic-rl-v1+sp/large_rl_dpg_binary_synthetic_v2/ckpts/training_states/large_rl_dpg_binary_synthetic_v2_epoch_40/random_states_7.pkl +3 -0
- synthetic-rl-v1+sp/large_rl_dpg_binary_synthetic_v2/ckpts/training_states/large_rl_dpg_binary_synthetic_v2_epoch_40/scheduler.bin +3 -0
- synthetic-rl-v1+sp/large_rl_dpg_binary_synthetic_v2/ckpts/training_states/large_rl_dpg_binary_synthetic_v2_epoch_40/scheduler_1.bin +3 -0
- synthetic-rl-v1+sp/large_rl_dpg_binary_synthetic_v2/ckpts/training_states/large_rl_dpg_binary_synthetic_v2_epoch_41/custom_checkpoint_0.pkl +3 -0
- synthetic-rl-v1+sp/large_rl_dpg_binary_synthetic_v2/ckpts/training_states/large_rl_dpg_binary_synthetic_v2_epoch_41/custom_checkpoint_1.pkl +3 -0
- synthetic-rl-v1+sp/large_rl_dpg_binary_synthetic_v2/ckpts/training_states/large_rl_dpg_binary_synthetic_v2_epoch_41/model.safetensors +3 -0
- synthetic-rl-v1+sp/large_rl_dpg_binary_synthetic_v2/ckpts/training_states/large_rl_dpg_binary_synthetic_v2_epoch_41/optimizer.bin +3 -0
- synthetic-rl-v1+sp/large_rl_dpg_binary_synthetic_v2/ckpts/training_states/large_rl_dpg_binary_synthetic_v2_epoch_41/optimizer_1.bin +3 -0
- synthetic-rl-v1+sp/large_rl_dpg_binary_synthetic_v2/ckpts/training_states/large_rl_dpg_binary_synthetic_v2_epoch_41/random_states_0.pkl +3 -0
- synthetic-rl-v1+sp/large_rl_dpg_binary_synthetic_v2/ckpts/training_states/large_rl_dpg_binary_synthetic_v2_epoch_41/random_states_1.pkl +3 -0
- synthetic-rl-v1+sp/large_rl_dpg_binary_synthetic_v2/ckpts/training_states/large_rl_dpg_binary_synthetic_v2_epoch_41/random_states_2.pkl +3 -0
- synthetic-rl-v1+sp/large_rl_dpg_binary_synthetic_v2/ckpts/training_states/large_rl_dpg_binary_synthetic_v2_epoch_41/random_states_3.pkl +3 -0
- synthetic-rl-v1+sp/large_rl_dpg_binary_synthetic_v2/ckpts/training_states/large_rl_dpg_binary_synthetic_v2_epoch_41/random_states_4.pkl +3 -0
- synthetic-rl-v1+sp/large_rl_dpg_binary_synthetic_v2/ckpts/training_states/large_rl_dpg_binary_synthetic_v2_epoch_41/random_states_5.pkl +3 -0
synthetic-rl-v1+sp/ckpts/policy_weights/policy_epoch_40.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:79e799c121ff44cbd0443ae508c928a76bb43c427e32be74c8edf5d72a30ccee
|
3 |
+
size 802136514
|
synthetic-rl-v1+sp/ckpts/policy_weights/policy_epoch_41.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a67621d3364f269894f8355cd66085a43cd4c61ce5111ab8a56eede09101944d
|
3 |
+
size 802136514
|
synthetic-rl-v1+sp/ckpts/policy_weights/policy_epoch_42.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:feef032b178cc57ebb2a9d3fdc129addc467d15ae53d4898b56cb7906ea27f61
|
3 |
+
size 802136514
|
synthetic-rl-v1+sp/ckpts/policy_weights/policy_epoch_43.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eaeb278cc9098c5d4ab908b58f1cad467342416ab2075b912f268e75928f9711
|
3 |
+
size 802136514
|
synthetic-rl-v1+sp/ckpts/policy_weights/policy_epoch_44.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ce7b068f32225ccdda05a768bd837470f9e14ce3996a32cbc54cabb677ffc50e
|
3 |
+
size 802136514
|
synthetic-rl-v1+sp/ckpts/policy_weights/policy_epoch_45.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1acfa838574f5a9d5207b9b9255ec407a07cb0f3bbe55fd235dc8a6dcf83fdd7
|
3 |
+
size 802136514
|
synthetic-rl-v1+sp/ckpts/policy_weights/policy_epoch_46.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6f7d12f3712a846119addb7a4efeb32e6e9abe41d48aa225d18baef41573935f
|
3 |
+
size 802136514
|
synthetic-rl-v1+sp/ckpts/policy_weights/policy_epoch_47.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aa2a5cf41b0ea4ac01f8eda8b8e7091e510795202651eba04d4e4fa2d48892bd
|
3 |
+
size 802136514
|
synthetic-rl-v1+sp/ckpts/policy_weights/policy_epoch_48.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3c755feedf625a3f0bfea4ee7aab6c75b5d57b2b9cd2b7bb4f2be71f66a7b86c
|
3 |
+
size 802136514
|
synthetic-rl-v1+sp/ckpts/policy_weights/policy_epoch_49.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:575445f74d821294633ea632202c6e637c4329cc06999656612e195b889bb448
|
3 |
+
size 802136514
|
synthetic-rl-v1+sp/ckpts/policy_weights/policy_epoch_50.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7c137954b4a510be45f93866448a194dcdf9b87237a507d887141b05fdc9b71c
|
3 |
+
size 802136514
|
synthetic-rl-v1+sp/config.txt
ADDED
@@ -0,0 +1,106 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# Parameters for Actor:
|
2 |
+
# ==============================================================================
|
3 |
+
Actor.activation = 'leaky_relu'
|
4 |
+
Actor.cont_dist_kind = 'normal'
|
5 |
+
Actor.d_hidden = 512
|
6 |
+
Actor.dropout_p = 0.0
|
7 |
+
Actor.gmm_modes = 5
|
8 |
+
Actor.log_std_high = 2.0
|
9 |
+
Actor.log_std_low = -5.0
|
10 |
+
Actor.n_layers = 2
|
11 |
+
|
12 |
+
# Parameters for Agent:
|
13 |
+
# ==============================================================================
|
14 |
+
Agent.fake_filter = False
|
15 |
+
Agent.gamma = 0.999
|
16 |
+
Agent.num_critics = 6
|
17 |
+
Agent.num_critics_td = 2
|
18 |
+
Agent.offline_coeff = 1.0
|
19 |
+
Agent.online_coeff = 0.0
|
20 |
+
Agent.popart = True
|
21 |
+
Agent.reward_multiplier = 10.0
|
22 |
+
Agent.tau = 0.003
|
23 |
+
Agent.use_multigamma = True
|
24 |
+
Agent.use_target_actor = True
|
25 |
+
|
26 |
+
# Parameters for Experiment:
|
27 |
+
# ==============================================================================
|
28 |
+
Experiment.batches_per_update = 1
|
29 |
+
Experiment.critic_loss_weight = 10.0
|
30 |
+
Experiment.env_mode = 'async'
|
31 |
+
Experiment.force_reset_train_envs_every = None
|
32 |
+
Experiment.grad_clip = 1.0
|
33 |
+
Experiment.has_replay_buffer_rights = True
|
34 |
+
Experiment.l2_coeff = 0.001
|
35 |
+
Experiment.learning_rate = 0.0001
|
36 |
+
Experiment.local_time_optimizer = False
|
37 |
+
Experiment.lr_warmup_steps = 500
|
38 |
+
Experiment.mixed_precision = 'no'
|
39 |
+
Experiment.padded_sampling = 'none'
|
40 |
+
Experiment.save_trajs_as = 'npz'
|
41 |
+
Experiment.stagger_traj_file_lengths = True
|
42 |
+
Experiment.wandb_group_name = None
|
43 |
+
|
44 |
+
# Parameters for FlashAttention:
|
45 |
+
# ==============================================================================
|
46 |
+
FlashAttention.window_size = (-1, -1)
|
47 |
+
|
48 |
+
# Parameters for MetamonTstepEncoder:
|
49 |
+
# ==============================================================================
|
50 |
+
MetamonTstepEncoder.d_model = 160
|
51 |
+
MetamonTstepEncoder.extra_emb_dim = 18
|
52 |
+
MetamonTstepEncoder.n_heads = 8
|
53 |
+
MetamonTstepEncoder.n_layers = 5
|
54 |
+
MetamonTstepEncoder.scratch_tokens = 11
|
55 |
+
MetamonTstepEncoder.token_mask_aug = False
|
56 |
+
|
57 |
+
# Parameters for Multigammas:
|
58 |
+
# ==============================================================================
|
59 |
+
Multigammas.continuous = [0.1, 0.9, 0.95, 0.97, 0.99, 0.995]
|
60 |
+
Multigammas.discrete = [0.1, 0.9, 0.95, 0.97, 0.99, 0.995]
|
61 |
+
|
62 |
+
# Parameters for MultiModalEmbedding:
|
63 |
+
# ==============================================================================
|
64 |
+
MultiModalEmbedding.dropout = 0.05
|
65 |
+
MultiModalEmbedding.numerical_tokens = 6
|
66 |
+
|
67 |
+
# Parameters for NCritics:
|
68 |
+
# ==============================================================================
|
69 |
+
NCritics.activation = 'leaky_relu'
|
70 |
+
NCritics.d_hidden = 512
|
71 |
+
NCritics.dropout_p = 0.0
|
72 |
+
NCritics.n_layers = 2
|
73 |
+
|
74 |
+
# Parameters for PopArtLayer:
|
75 |
+
# ==============================================================================
|
76 |
+
PopArtLayer.beta = 0.0005
|
77 |
+
PopArtLayer.init_nu = 100.0
|
78 |
+
|
79 |
+
# Parameters for TformerTrajEncoder:
|
80 |
+
# ==============================================================================
|
81 |
+
TformerTrajEncoder.activation = 'leaky_relu'
|
82 |
+
TformerTrajEncoder.causal = True
|
83 |
+
TformerTrajEncoder.d_ff = 5120
|
84 |
+
TformerTrajEncoder.d_model = 1280
|
85 |
+
TformerTrajEncoder.dropout_attn = 0.0
|
86 |
+
TformerTrajEncoder.dropout_emb = 0.05
|
87 |
+
TformerTrajEncoder.dropout_ff = 0.05
|
88 |
+
TformerTrajEncoder.dropout_qkv = 0.0
|
89 |
+
TformerTrajEncoder.head_scaling = True
|
90 |
+
TformerTrajEncoder.n_heads = 20
|
91 |
+
TformerTrajEncoder.n_layers = 9
|
92 |
+
TformerTrajEncoder.norm = 'layer'
|
93 |
+
TformerTrajEncoder.normformer_norms = True
|
94 |
+
TformerTrajEncoder.sigma_reparam = True
|
95 |
+
|
96 |
+
# Parameters for TimestepTransformer:
|
97 |
+
# ==============================================================================
|
98 |
+
# None.
|
99 |
+
|
100 |
+
# Parameters for TokenEmbedding:
|
101 |
+
# ==============================================================================
|
102 |
+
# None.
|
103 |
+
|
104 |
+
# Parameters for TransformerTurnEmbedding:
|
105 |
+
# ==============================================================================
|
106 |
+
TransformerTurnEmbedding.dropout = 0.05
|
synthetic-rl-v1+sp/large_rl_dpg_binary_synthetic_v2/ckpts/policy_weights/policy_epoch_40.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:79e799c121ff44cbd0443ae508c928a76bb43c427e32be74c8edf5d72a30ccee
|
3 |
+
size 802136514
|
synthetic-rl-v1+sp/large_rl_dpg_binary_synthetic_v2/ckpts/policy_weights/policy_epoch_41.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a67621d3364f269894f8355cd66085a43cd4c61ce5111ab8a56eede09101944d
|
3 |
+
size 802136514
|
synthetic-rl-v1+sp/large_rl_dpg_binary_synthetic_v2/ckpts/policy_weights/policy_epoch_42.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:feef032b178cc57ebb2a9d3fdc129addc467d15ae53d4898b56cb7906ea27f61
|
3 |
+
size 802136514
|
synthetic-rl-v1+sp/large_rl_dpg_binary_synthetic_v2/ckpts/policy_weights/policy_epoch_43.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eaeb278cc9098c5d4ab908b58f1cad467342416ab2075b912f268e75928f9711
|
3 |
+
size 802136514
|
synthetic-rl-v1+sp/large_rl_dpg_binary_synthetic_v2/ckpts/policy_weights/policy_epoch_44.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ce7b068f32225ccdda05a768bd837470f9e14ce3996a32cbc54cabb677ffc50e
|
3 |
+
size 802136514
|
synthetic-rl-v1+sp/large_rl_dpg_binary_synthetic_v2/ckpts/policy_weights/policy_epoch_45.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1acfa838574f5a9d5207b9b9255ec407a07cb0f3bbe55fd235dc8a6dcf83fdd7
|
3 |
+
size 802136514
|
synthetic-rl-v1+sp/large_rl_dpg_binary_synthetic_v2/ckpts/policy_weights/policy_epoch_46.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6f7d12f3712a846119addb7a4efeb32e6e9abe41d48aa225d18baef41573935f
|
3 |
+
size 802136514
|
synthetic-rl-v1+sp/large_rl_dpg_binary_synthetic_v2/ckpts/policy_weights/policy_epoch_47.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aa2a5cf41b0ea4ac01f8eda8b8e7091e510795202651eba04d4e4fa2d48892bd
|
3 |
+
size 802136514
|
synthetic-rl-v1+sp/large_rl_dpg_binary_synthetic_v2/ckpts/policy_weights/policy_epoch_48.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3c755feedf625a3f0bfea4ee7aab6c75b5d57b2b9cd2b7bb4f2be71f66a7b86c
|
3 |
+
size 802136514
|
synthetic-rl-v1+sp/large_rl_dpg_binary_synthetic_v2/ckpts/policy_weights/policy_epoch_49.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:575445f74d821294633ea632202c6e637c4329cc06999656612e195b889bb448
|
3 |
+
size 802136514
|
synthetic-rl-v1+sp/large_rl_dpg_binary_synthetic_v2/ckpts/policy_weights/policy_epoch_50.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7c137954b4a510be45f93866448a194dcdf9b87237a507d887141b05fdc9b71c
|
3 |
+
size 802136514
|
synthetic-rl-v1+sp/large_rl_dpg_binary_synthetic_v2/ckpts/policy_weights/policy_epoch_51.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:59c8666e2daa7fe5018080a7aabaee5d9d24cb79a51c1b96a04d234d4054d53a
|
3 |
+
size 802136514
|
synthetic-rl-v1+sp/large_rl_dpg_binary_synthetic_v2/ckpts/training_states/large_rl_dpg_binary_synthetic_v2_epoch_40/custom_checkpoint_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c7c1a36e941afc5b17c5a645555bf80c1194f0bac8572e2ddd5cfa10a58edc74
|
3 |
+
size 1040
|
synthetic-rl-v1+sp/large_rl_dpg_binary_synthetic_v2/ckpts/training_states/large_rl_dpg_binary_synthetic_v2_epoch_40/custom_checkpoint_1.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3470a4f2909eaa65012762620c2760013fb6a80f01604b42c40bf6541ff11596
|
3 |
+
size 1104
|
synthetic-rl-v1+sp/large_rl_dpg_binary_synthetic_v2/ckpts/training_states/large_rl_dpg_binary_synthetic_v2_epoch_40/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bcb4b8c1c4e7c0b7df115ae92bdbb8600232b8c74f22bd9e99bb6e6b67d91a06
|
3 |
+
size 802037148
|
synthetic-rl-v1+sp/large_rl_dpg_binary_synthetic_v2/ckpts/training_states/large_rl_dpg_binary_synthetic_v2_epoch_40/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fbd693f84ba6eb7a7bcf3681e10cce89b5ce6db1dca235f5d364fc1d9f7317aa
|
3 |
+
size 1704
|
synthetic-rl-v1+sp/large_rl_dpg_binary_synthetic_v2/ckpts/training_states/large_rl_dpg_binary_synthetic_v2_epoch_40/optimizer_1.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:34c1d65da1a204f4848bbfbe870aabf5bcd8025dcbfe97986f98465b5ef80568
|
3 |
+
size 1503842936
|
synthetic-rl-v1+sp/large_rl_dpg_binary_synthetic_v2/ckpts/training_states/large_rl_dpg_binary_synthetic_v2_epoch_40/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d52922c55a82fcae12f65a268418329985b72a94180daab1c233e7507c80a121
|
3 |
+
size 16100
|
synthetic-rl-v1+sp/large_rl_dpg_binary_synthetic_v2/ckpts/training_states/large_rl_dpg_binary_synthetic_v2_epoch_40/random_states_1.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d5b57a46aa697cf6d8425c562e2b390030f362360432603bb10d89cf2b9c8798
|
3 |
+
size 16100
|
synthetic-rl-v1+sp/large_rl_dpg_binary_synthetic_v2/ckpts/training_states/large_rl_dpg_binary_synthetic_v2_epoch_40/random_states_2.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5ff7443987c474f6d7b1d58a0b09f956e9365aa04a5231804c2ed4a66fcf2074
|
3 |
+
size 16100
|
synthetic-rl-v1+sp/large_rl_dpg_binary_synthetic_v2/ckpts/training_states/large_rl_dpg_binary_synthetic_v2_epoch_40/random_states_3.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:21da5d3c01c2e6eda8bd3b5ba2c984580b18108190db153829e194874c38a2ed
|
3 |
+
size 16164
|
synthetic-rl-v1+sp/large_rl_dpg_binary_synthetic_v2/ckpts/training_states/large_rl_dpg_binary_synthetic_v2_epoch_40/random_states_4.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1ed2232e6769f3516b8ca9bff55bf9ee44d0ee66569e8bd166ea8defd52c1e67
|
3 |
+
size 16036
|
synthetic-rl-v1+sp/large_rl_dpg_binary_synthetic_v2/ckpts/training_states/large_rl_dpg_binary_synthetic_v2_epoch_40/random_states_5.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4e2a0c944f17016d778994a5d31921e7b01c68f9645dd9d5814b3bd665691482
|
3 |
+
size 16100
|
synthetic-rl-v1+sp/large_rl_dpg_binary_synthetic_v2/ckpts/training_states/large_rl_dpg_binary_synthetic_v2_epoch_40/random_states_6.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:089b1d5874a8ac534b6325e2914925b0c193861d7f76475522e07c2d64dcaac3
|
3 |
+
size 16036
|
synthetic-rl-v1+sp/large_rl_dpg_binary_synthetic_v2/ckpts/training_states/large_rl_dpg_binary_synthetic_v2_epoch_40/random_states_7.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:46d0459e050959b56bcb17155fda6eb4a505e74134fbdc52cc2e804bc5089b8d
|
3 |
+
size 16164
|
synthetic-rl-v1+sp/large_rl_dpg_binary_synthetic_v2/ckpts/training_states/large_rl_dpg_binary_synthetic_v2_epoch_40/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1a3f5898007c59ee48d752082b20f32a44a5f89b2f28423a3e2c0520d982de67
|
3 |
+
size 1000
|
synthetic-rl-v1+sp/large_rl_dpg_binary_synthetic_v2/ckpts/training_states/large_rl_dpg_binary_synthetic_v2_epoch_40/scheduler_1.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:939fd547dc297e7eb7a8088edb513fd3d150f0309a5a44dc77235f7646bb529d
|
3 |
+
size 1008
|
synthetic-rl-v1+sp/large_rl_dpg_binary_synthetic_v2/ckpts/training_states/large_rl_dpg_binary_synthetic_v2_epoch_41/custom_checkpoint_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c7c1a36e941afc5b17c5a645555bf80c1194f0bac8572e2ddd5cfa10a58edc74
|
3 |
+
size 1040
|
synthetic-rl-v1+sp/large_rl_dpg_binary_synthetic_v2/ckpts/training_states/large_rl_dpg_binary_synthetic_v2_epoch_41/custom_checkpoint_1.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d5a2c6a336f8cc72f3e58d064bf92b0ec657e936601e458b547c81a4bbd178b5
|
3 |
+
size 1104
|
synthetic-rl-v1+sp/large_rl_dpg_binary_synthetic_v2/ckpts/training_states/large_rl_dpg_binary_synthetic_v2_epoch_41/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8419b122ad001bfee904c34443e526f91c9e58574263cf03465923c896519afc
|
3 |
+
size 802037148
|
synthetic-rl-v1+sp/large_rl_dpg_binary_synthetic_v2/ckpts/training_states/large_rl_dpg_binary_synthetic_v2_epoch_41/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fbd693f84ba6eb7a7bcf3681e10cce89b5ce6db1dca235f5d364fc1d9f7317aa
|
3 |
+
size 1704
|
synthetic-rl-v1+sp/large_rl_dpg_binary_synthetic_v2/ckpts/training_states/large_rl_dpg_binary_synthetic_v2_epoch_41/optimizer_1.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:687f614be2a83f9d04d273bd2cd146165dd43e4687666f1e3acb190368a5ddf6
|
3 |
+
size 1503842936
|
synthetic-rl-v1+sp/large_rl_dpg_binary_synthetic_v2/ckpts/training_states/large_rl_dpg_binary_synthetic_v2_epoch_41/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9cbc67cd152e012b680b18872080a8a96c6ad27cf66349fedaa6828e8cf137f9
|
3 |
+
size 16100
|
synthetic-rl-v1+sp/large_rl_dpg_binary_synthetic_v2/ckpts/training_states/large_rl_dpg_binary_synthetic_v2_epoch_41/random_states_1.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ca038c3136e58b49424ed5d9dc61ed3194eca90f869e38e514dac19ff6cfece9
|
3 |
+
size 16100
|
synthetic-rl-v1+sp/large_rl_dpg_binary_synthetic_v2/ckpts/training_states/large_rl_dpg_binary_synthetic_v2_epoch_41/random_states_2.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:37322ecde945391ed270466b1e9b5d662a900b092e39c56b90a15c6c71b0381f
|
3 |
+
size 16100
|
synthetic-rl-v1+sp/large_rl_dpg_binary_synthetic_v2/ckpts/training_states/large_rl_dpg_binary_synthetic_v2_epoch_41/random_states_3.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:96f5dfc568481b598cabd5384bfbe7375fb808702308c2fea02f4ded137a5211
|
3 |
+
size 16164
|
synthetic-rl-v1+sp/large_rl_dpg_binary_synthetic_v2/ckpts/training_states/large_rl_dpg_binary_synthetic_v2_epoch_41/random_states_4.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:00784a3d6a565bc63a9466eb2d445a0af781ff06b53d122409cdc67e9c111bba
|
3 |
+
size 16036
|
synthetic-rl-v1+sp/large_rl_dpg_binary_synthetic_v2/ckpts/training_states/large_rl_dpg_binary_synthetic_v2_epoch_41/random_states_5.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:458646c46c7e0acfa9754a013d5a70f76b4b19d3046495b23a8125fb91384c78
|
3 |
+
size 16100
|