Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+sf_log.txt filter=lfs diff=lfs merge=lfs -text

.summary/0/events.out.tfevents.1704305846.t0046

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bf8ffc9068426ad6151a4ef08259e40b2e6d781e5556eb493709f10f273ef53
+size 7891513

README.md

@@ -0,0 +1,56 @@
+---
+library_name: sample-factory
+tags:
+- deep-reinforcement-learning
+- reinforcement-learning
+- sample-factory
+model-index:
+- name: APPO
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: nethack_challenge
+      type: nethack_challenge
+    metrics:
+    - type: mean_reward
+      value: 2228.00 +/- 0.00
+      name: mean_reward
+      verified: false
+---
+
+A(n) **APPO** model trained on the **nethack_challenge** environment.
+
+This model was trained using Sample-Factory 2.0: https://github.com/alex-petrenko/sample-factory.
+Documentation for how to use Sample-Factory can be found at https://www.samplefactory.dev/
+
+
+## Downloading the model
+
+After installing Sample-Factory, download the model with:
+```
+python -m sample_factory.huggingface.load_from_hub -r LLParallax/sample_factory_human_monk
+```
+
+    
+## Using the model
+
+To run the model after download, use the `enjoy` script corresponding to this environment:
+```
+python -m <path.to.enjoy.module> --algo=APPO --env=nethack_challenge --train_dir=./train_dir --experiment=sample_factory_human_monk
+```
+
+
+You can also upload models to the Hugging Face Hub using the same script with the `--push_to_hub` flag.
+See https://www.samplefactory.dev/10-huggingface/huggingface/ for more details
+    
+## Training with this model
+
+To continue training with this model, use the `train` script corresponding to this environment:
+```
+python -m <path.to.train.module> --algo=APPO --env=nethack_challenge --train_dir=./train_dir --experiment=sample_factory_human_monk --restart_behavior=resume --train_for_env_steps=10000000000
+```
+
+Note, you may have to adjust `--train_for_env_steps` to a suitably high number as the experiment will resume at the number of steps it concluded at.
+    

checkpoint_p0/best_000470117_1925599232_reward_4324.130.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d7c1c2ad85ea1f1f0c673c99860cf1d4c8c64ef204173e9f69b73d39b8e4ff4
+size 74688762

checkpoint_p0/checkpoint_000488106_1999282176.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:681d8c968faea7809a19fa6db545e2dc124367bc6ca231cb580d5179ec6af772
+size 74689506

checkpoint_p0/checkpoint_000488283_2000007168.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f7ecfe1e842252f39b7e93b2b63257995271d748b2e5970f0ed24e745c4f1ae
+size 74689506

config.json

@@ -0,0 +1,162 @@
+{
+  "help": false,
+  "algo": "APPO",
+  "env": "nethack_challenge",
+  "experiment": "default_experiment",
+  "train_dir": "/net/tscratch/people/plgbartekcupial/mrunner_scratch/sample_factory_nethack/03_01-17_00-vigilant_hodgkin/2023-12-28-monk-appo_4m9d_2/train_dir",
+  "restart_behavior": "resume",
+  "device": "gpu",
+  "seed": 2,
+  "num_policies": 1,
+  "async_rl": true,
+  "serial_mode": false,
+  "batched_sampling": false,
+  "num_batches_to_accumulate": 2,
+  "worker_num_splits": 2,
+  "policy_workers_per_policy": 1,
+  "max_policy_lag": 1000,
+  "num_workers": 16,
+  "num_envs_per_worker": 32,
+  "batch_size": 4096,
+  "num_batches_per_epoch": 1,
+  "num_epochs": 1,
+  "rollout": 32,
+  "recurrence": 32,
+  "shuffle_minibatches": false,
+  "gamma": 0.999,
+  "reward_scale": 1.0,
+  "reward_clip": 10.0,
+  "value_bootstrap": false,
+  "normalize_returns": true,
+  "exploration_loss_coeff": 0.001,
+  "value_loss_coeff": 1.0,
+  "kl_loss_coeff": 0.0,
+  "exploration_loss": "entropy",
+  "gae_lambda": 1.0,
+  "ppo_clip_ratio": 0.1,
+  "ppo_clip_value": 1.0,
+  "with_vtrace": false,
+  "vtrace_rho": 1.0,
+  "vtrace_c": 1.0,
+  "optimizer": "adam",
+  "adam_eps": 1e-07,
+  "adam_beta1": 0.9,
+  "adam_beta2": 0.999,
+  "max_grad_norm": 4,
+  "learning_rate": 0.0001,
+  "lr_schedule": "constant",
+  "lr_schedule_kl_threshold": 0.008,
+  "lr_adaptive_min": 1e-06,
+  "lr_adaptive_max": 0.01,
+  "obs_subtract_mean": 0.0,
+  "obs_scale": 1.0,
+  "normalize_input": false,
+  "normalize_input_keys": null,
+  "decorrelate_experience_max_seconds": 0,
+  "decorrelate_envs_on_one_worker": true,
+  "actor_worker_gpus": [],
+  "set_workers_cpu_affinity": true,
+  "force_envs_single_thread": false,
+  "default_niceness": 0,
+  "log_to_file": true,
+  "experiment_summaries_interval": 50,
+  "flush_summaries_interval": 30,
+  "stats_avg": 100,
+  "summaries_use_frameskip": true,
+  "heartbeat_interval": 20,
+  "heartbeat_reporting_interval": 180,
+  "train_for_env_steps": 2000000000,
+  "train_for_seconds": 10000000000,
+  "save_every_sec": 120,
+  "keep_checkpoints": 2,
+  "load_checkpoint_kind": "latest",
+  "save_milestones_sec": -1,
+  "save_best_every_sec": 5,
+  "save_best_metric": "reward",
+  "save_best_after": 100000,
+  "benchmark": false,
+  "encoder_mlp_layers": [
+    512,
+    512
+  ],
+  "encoder_conv_architecture": "convnet_simple",
+  "encoder_conv_mlp_layers": [
+    512
+  ],
+  "use_rnn": true,
+  "rnn_size": 512,
+  "rnn_type": "lstm",
+  "rnn_num_layers": 1,
+  "decoder_mlp_layers": [],
+  "nonlinearity": "relu",
+  "policy_initialization": "orthogonal",
+  "policy_init_gain": 1.0,
+  "actor_critic_share_weights": true,
+  "adaptive_stddev": false,
+  "continuous_tanh_scale": 0.0,
+  "initial_stddev": 1.0,
+  "use_env_info_cache": false,
+  "env_gpu_actions": false,
+  "env_gpu_observations": true,
+  "env_frameskip": 1,
+  "env_framestack": 1,
+  "pixel_format": "CHW",
+  "use_record_episode_statistics": false,
+  "episode_counter": false,
+  "with_wandb": true,
+  "wandb_user": "bartekcupial",
+  "wandb_project": "sample_factory_nethack",
+  "wandb_group": "gmum",
+  "wandb_job_type": "SF",
+  "wandb_tags": [],
+  "with_pbt": false,
+  "pbt_mix_policies_in_one_env": true,
+  "pbt_period_env_steps": 5000000,
+  "pbt_start_mutation": 20000000,
+  "pbt_replace_fraction": 0.3,
+  "pbt_mutation_rate": 0.15,
+  "pbt_replace_reward_gap": 0.1,
+  "pbt_replace_reward_gap_absolute": 1e-06,
+  "pbt_optimize_gamma": false,
+  "pbt_target_objective": "true_objective",
+  "pbt_perturb_min": 1.1,
+  "pbt_perturb_max": 1.5,
+  "character": "mon-hum-neu-mal",
+  "max_episode_steps": 100000,
+  "penalty_step": 0.0,
+  "penalty_time": 0.0,
+  "fn_penalty_step": "constant",
+  "savedir": null,
+  "save_ttyrec_every": 0,
+  "add_image_observation": true,
+  "crop_dim": 18,
+  "pixel_size": 6,
+  "use_prev_action": true,
+  "use_tty_only": true,
+  "model": "ChaoticDwarvenGPT5",
+  "add_stats_to_info": true,
+  "command_line": "--env=nethack_challenge --train_for_env_steps=2000000000 --character=mon-hum-neu-mal --num_workers=16 --num_envs_per_worker=32 --worker_num_splits=2 --rollout=32 --batch_size=4096 --async_rl=True --serial_mode=False --wandb_user=bartekcupial --wandb_project=sample_factory_nethack --wandb_group=gmum --with_wandb=True --use_prev_action=True --model=ChaoticDwarvenGPT5 --rnn_size=512 --seed=2",
+  "cli_args": {
+    "env": "nethack_challenge",
+    "seed": 2,
+    "async_rl": true,
+    "serial_mode": false,
+    "worker_num_splits": 2,
+    "num_workers": 16,
+    "num_envs_per_worker": 32,
+    "batch_size": 4096,
+    "rollout": 32,
+    "train_for_env_steps": 2000000000,
+    "rnn_size": 512,
+    "with_wandb": true,
+    "wandb_user": "bartekcupial",
+    "wandb_project": "sample_factory_nethack",
+    "wandb_group": "gmum",
+    "character": "mon-hum-neu-mal",
+    "use_prev_action": true,
+    "model": "ChaoticDwarvenGPT5"
+  },
+  "git_hash": "unknown",
+  "git_repo_name": "not a git repository",
+  "wandb_unique_id": "default_experiment_20240103_191716_696528"
+}

sf_log.txt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cec37cde2f9538693efd7e24142cb3f23705c599fa1dd5ac9a03da46345f0105
+size 10529466