MattStammers
commited on
Commit
•
485e6c6
1
Parent(s):
ddc0793
Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- .gitattributes +1 -0
- .summary/0/events.out.tfevents.1703655592.rhmmedcatt-proliant-ml350-gen10 +3 -0
- .summary/1/events.out.tfevents.1703655592.rhmmedcatt-proliant-ml350-gen10 +3 -0
- README.md +189 -0
- checkpoint_p0/best_000001120_286720_reward_1000.000.pth +3 -0
- checkpoint_p0/checkpoint_001953536_500326400.pth +3 -0
- checkpoint_p0/checkpoint_001953744_500432896.pth +3 -0
- checkpoint_p0/milestones/checkpoint_000048240_12353536.pth +3 -0
- checkpoint_p0/milestones/checkpoint_000097032_24854528.pth +3 -0
- checkpoint_p0/milestones/checkpoint_000145640_37298176.pth +3 -0
- checkpoint_p0/milestones/checkpoint_000194248_49741824.pth +3 -0
- checkpoint_p0/milestones/checkpoint_000242888_62193664.pth +3 -0
- checkpoint_p0/milestones/checkpoint_000291584_74661888.pth +3 -0
- checkpoint_p0/milestones/checkpoint_000340224_87113728.pth +3 -0
- checkpoint_p0/milestones/checkpoint_000388928_99581952.pth +3 -0
- checkpoint_p0/milestones/checkpoint_000436896_111861760.pth +3 -0
- checkpoint_p0/milestones/checkpoint_000484896_124149760.pth +3 -0
- checkpoint_p0/milestones/checkpoint_000533568_136609792.pth +3 -0
- checkpoint_p0/milestones/checkpoint_000582176_149053440.pth +3 -0
- checkpoint_p0/milestones/checkpoint_000631040_161562624.pth +3 -0
- checkpoint_p0/milestones/checkpoint_000679696_174022656.pth +3 -0
- checkpoint_p0/milestones/checkpoint_000727912_186368000.pth +3 -0
- checkpoint_p0/milestones/checkpoint_000776064_198696960.pth +3 -0
- checkpoint_p0/milestones/checkpoint_000823360_210804736.pth +3 -0
- checkpoint_p0/milestones/checkpoint_000869360_222584832.pth +3 -0
- checkpoint_p0/milestones/checkpoint_000916608_234684416.pth +3 -0
- checkpoint_p0/milestones/checkpoint_000964472_246947840.pth +3 -0
- checkpoint_p0/milestones/checkpoint_001012296_259194880.pth +3 -0
- checkpoint_p0/milestones/checkpoint_001060552_271548416.pth +3 -0
- checkpoint_p0/milestones/checkpoint_001108736_283885568.pth +3 -0
- checkpoint_p0/milestones/checkpoint_001156944_296230912.pth +3 -0
- checkpoint_p0/milestones/checkpoint_001204912_308510720.pth +3 -0
- checkpoint_p0/milestones/checkpoint_001253184_320872448.pth +3 -0
- checkpoint_p0/milestones/checkpoint_001301216_333176832.pth +3 -0
- checkpoint_p0/milestones/checkpoint_001349432_345522176.pth +3 -0
- checkpoint_p0/milestones/checkpoint_001397544_357842944.pth +3 -0
- checkpoint_p0/milestones/checkpoint_001445800_370196480.pth +3 -0
- checkpoint_p0/milestones/checkpoint_001494040_382550016.pth +3 -0
- checkpoint_p0/milestones/checkpoint_001542256_394895360.pth +3 -0
- checkpoint_p0/milestones/checkpoint_001590448_407232512.pth +3 -0
- checkpoint_p0/milestones/checkpoint_001638608_419561472.pth +3 -0
- checkpoint_p0/milestones/checkpoint_001686824_431906816.pth +3 -0
- checkpoint_p0/milestones/checkpoint_001734824_444194816.pth +3 -0
- checkpoint_p0/milestones/checkpoint_001783072_456548352.pth +3 -0
- checkpoint_p0/milestones/checkpoint_001831096_468844544.pth +3 -0
- checkpoint_p0/milestones/checkpoint_001878968_481099776.pth +3 -0
- checkpoint_p0/milestones/checkpoint_001926936_493387776.pth +3 -0
- checkpoint_p1/best_000001120_286720_reward_1000.000.pth +3 -0
- checkpoint_p1/checkpoint_001952888_500006912.pth +3 -0
- checkpoint_p1/checkpoint_001952920_500015104.pth +3 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
sf_log.txt filter=lfs diff=lfs merge=lfs -text
|
.summary/0/events.out.tfevents.1703655592.rhmmedcatt-proliant-ml350-gen10
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2eef4031387c4c4d9097520b0d5260b32d54ddb518b26a62766350c482b5a05a
|
3 |
+
size 21428027
|
.summary/1/events.out.tfevents.1703655592.rhmmedcatt-proliant-ml350-gen10
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0ed58ba7a6205bc769c4388ec7c622226755cf13691f9fa799053d3c1f827885
|
3 |
+
size 10102521
|
README.md
ADDED
@@ -0,0 +1,189 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: sample-factory
|
3 |
+
tags:
|
4 |
+
- deep-reinforcement-learning
|
5 |
+
- reinforcement-learning
|
6 |
+
- sample-factory
|
7 |
+
model-index:
|
8 |
+
- name: APPO
|
9 |
+
results:
|
10 |
+
- task:
|
11 |
+
type: reinforcement-learning
|
12 |
+
name: reinforcement-learning
|
13 |
+
dataset:
|
14 |
+
name: mujoco_pendulum
|
15 |
+
type: mujoco_pendulum
|
16 |
+
metrics:
|
17 |
+
- type: mean_reward
|
18 |
+
value: 1000.00 +/- 0.00
|
19 |
+
name: mean_reward
|
20 |
+
verified: false
|
21 |
+
---
|
22 |
+
|
23 |
+
## About the Project
|
24 |
+
|
25 |
+
This project is an attempt to maximise performance of high sample throughput APPO RL models in Atari environments in as carbon efficient a manner as possible using a single, not particularly high performance single machine. It is about demonstrating the generalisability of on-policy algorithms to create good performance quickly (by sacrificing sample efficiency) while also proving that this route to RL production is accessible to even hobbyists like me (I am a gastroenterologist not a computer scientist).
|
26 |
+
|
27 |
+
In terms of throughput I am managing to reach throughputs of 2,500 - 3,000 across both policies using sample factory using two Quadro P2200's (not particularly powerful GPUs) each loaded up about 60% (3GB). Previously using the stable baselines 3 (sb3) implementation of PPO it would take about a week to train an atari agent to 100 million timesteps synchronously. By comparison the sample factory async implementation takes only just over 2 hours to achieve the same result. That is about 84 times faster with only typically a 21 watt burn per GPU. I am thus very grateful to Alex Petrenko and all the sample factory team for their work on this.
|
28 |
+
|
29 |
+
## Project Aims
|
30 |
+
|
31 |
+
This model as with all the others in the benchmarks was trained initially asynchronously un-seeded to 10 million steps for the purposes of setting a sample factory async baseline for this model on this environment but only 3/57 made it anywhere near sota performance.
|
32 |
+
|
33 |
+
I then re-trained the models with 100 million timesteps- at this point 2 environments maxed out at sota performance (Pong and Freeway) with four approaching sota performance - (atlantis, boxing, tennis and fishingderby.) =6/57 near sota.
|
34 |
+
|
35 |
+
The aim now is to try and reach state-of-the-art (SOTA) performance on a further block of atari environments using up to 1 billion training timesteps initially with appo. I will flag the models with SOTA when they reach at or near these levels.
|
36 |
+
|
37 |
+
After this I will switch on V-Trace to see if the Impala variations perform any better with the same seed (I have seeded '1234')
|
38 |
+
|
39 |
+
|
40 |
+
## About the Model
|
41 |
+
|
42 |
+
The hyperparameters used in the model are described in my shell script on my fork of sample-factory: https://github.com/MattStammers/sample-factory. Given that https://huggingface.co/edbeeching has kindly shared his parameters, I saved time and energy by using many of his tuned hyperparameters to reduce carbon inefficiency:
|
43 |
+
```
|
44 |
+
hyperparameters = {
|
45 |
+
"help": false,
|
46 |
+
"algo": "APPO",
|
47 |
+
"env": "atari_asteroid",
|
48 |
+
"experiment": "atari_asteroid_APPO",
|
49 |
+
"train_dir": "./train_atari",
|
50 |
+
"restart_behavior": "restart",
|
51 |
+
"device": "gpu",
|
52 |
+
"seed": 1234,
|
53 |
+
"num_policies": 2,
|
54 |
+
"async_rl": true,
|
55 |
+
"serial_mode": false,
|
56 |
+
"batched_sampling": true,
|
57 |
+
"num_batches_to_accumulate": 2,
|
58 |
+
"worker_num_splits": 1,
|
59 |
+
"policy_workers_per_policy": 1,
|
60 |
+
"max_policy_lag": 1000,
|
61 |
+
"num_workers": 16,
|
62 |
+
"num_envs_per_worker": 2,
|
63 |
+
"batch_size": 1024,
|
64 |
+
"num_batches_per_epoch": 8,
|
65 |
+
"num_epochs": 4,
|
66 |
+
"rollout": 128,
|
67 |
+
"recurrence": 1,
|
68 |
+
"shuffle_minibatches": false,
|
69 |
+
"gamma": 0.99,
|
70 |
+
"reward_scale": 1.0,
|
71 |
+
"reward_clip": 1000.0,
|
72 |
+
"value_bootstrap": false,
|
73 |
+
"normalize_returns": true,
|
74 |
+
"exploration_loss_coeff": 0.0004677351413,
|
75 |
+
"value_loss_coeff": 0.5,
|
76 |
+
"kl_loss_coeff": 0.0,
|
77 |
+
"exploration_loss": "entropy",
|
78 |
+
"gae_lambda": 0.95,
|
79 |
+
"ppo_clip_ratio": 0.1,
|
80 |
+
"ppo_clip_value": 1.0,
|
81 |
+
"with_vtrace": true,
|
82 |
+
"vtrace_rho": 1.0,
|
83 |
+
"vtrace_c": 1.0,
|
84 |
+
"optimizer": "adam",
|
85 |
+
"adam_eps": 1e-05,
|
86 |
+
"adam_beta1": 0.9,
|
87 |
+
"adam_beta2": 0.999,
|
88 |
+
"max_grad_norm": 0.0,
|
89 |
+
"learning_rate": 0.0003033891184,
|
90 |
+
"lr_schedule": "linear_decay",
|
91 |
+
"lr_schedule_kl_threshold": 0.008,
|
92 |
+
"lr_adaptive_min": 1e-06,
|
93 |
+
"lr_adaptive_max": 0.01,
|
94 |
+
"obs_subtract_mean": 0.0,
|
95 |
+
"obs_scale": 255.0,
|
96 |
+
"normalize_input": true,
|
97 |
+
"normalize_input_keys": [
|
98 |
+
"obs"
|
99 |
+
],
|
100 |
+
"decorrelate_experience_max_seconds": 0,
|
101 |
+
"decorrelate_envs_on_one_worker": true,
|
102 |
+
"actor_worker_gpus": [],
|
103 |
+
"set_workers_cpu_affinity": true,
|
104 |
+
"force_envs_single_thread": false,
|
105 |
+
"default_niceness": 0,
|
106 |
+
"log_to_file": true,
|
107 |
+
"experiment_summaries_interval": 3,
|
108 |
+
"flush_summaries_interval": 30,
|
109 |
+
"stats_avg": 100,
|
110 |
+
"summaries_use_frameskip": true,
|
111 |
+
"heartbeat_interval": 10,
|
112 |
+
"heartbeat_reporting_interval": 60,
|
113 |
+
"train_for_env_steps": 100000000,
|
114 |
+
"train_for_seconds": 10000000000,
|
115 |
+
"save_every_sec": 120,
|
116 |
+
"keep_checkpoints": 2,
|
117 |
+
"load_checkpoint_kind": "latest",
|
118 |
+
"save_milestones_sec": 1200,
|
119 |
+
"save_best_every_sec": 5,
|
120 |
+
"save_best_metric": "reward",
|
121 |
+
"save_best_after": 100000,
|
122 |
+
"benchmark": false,
|
123 |
+
"encoder_mlp_layers": [
|
124 |
+
512,
|
125 |
+
512
|
126 |
+
],
|
127 |
+
"encoder_conv_architecture": "convnet_atari",
|
128 |
+
"encoder_conv_mlp_layers": [
|
129 |
+
512
|
130 |
+
],
|
131 |
+
"use_rnn": false,
|
132 |
+
"rnn_size": 512,
|
133 |
+
"rnn_type": "gru",
|
134 |
+
"rnn_num_layers": 1,
|
135 |
+
"decoder_mlp_layers": [],
|
136 |
+
"nonlinearity": "relu",
|
137 |
+
"policy_initialization": "orthogonal",
|
138 |
+
"policy_init_gain": 1.0,
|
139 |
+
"actor_critic_share_weights": true,
|
140 |
+
"adaptive_stddev": false,
|
141 |
+
"continuous_tanh_scale": 0.0,
|
142 |
+
"initial_stddev": 1.0,
|
143 |
+
"use_env_info_cache": false,
|
144 |
+
"env_gpu_actions": false,
|
145 |
+
"env_gpu_observations": true,
|
146 |
+
"env_frameskip": 4,
|
147 |
+
"env_framestack": 4,
|
148 |
+
"pixel_format": "CHW"
|
149 |
+
}
|
150 |
+
|
151 |
+
```
|
152 |
+
|
153 |
+
|
154 |
+
|
155 |
+
A(n) **APPO** impala model trained on the **mujoco_pendulum** environment.
|
156 |
+
|
157 |
+
This model was trained using Sample-Factory 2.0: https://github.com/alex-petrenko/sample-factory. Sample factory is a
|
158 |
+
high throughput on-policy RL framework. I have been using
|
159 |
+
Documentation for how to use Sample-Factory can be found at https://www.samplefactory.dev/
|
160 |
+
|
161 |
+
|
162 |
+
## Downloading the model
|
163 |
+
|
164 |
+
After installing Sample-Factory, download the model with:
|
165 |
+
```
|
166 |
+
python -m sample_factory.huggingface.load_from_hub -r MattStammers/APPO-mujoco_pendulum
|
167 |
+
```
|
168 |
+
|
169 |
+
|
170 |
+
## Using the model
|
171 |
+
|
172 |
+
To run the model after download, use the `enjoy` script corresponding to this environment:
|
173 |
+
```
|
174 |
+
python -m sf_examples.mujoco.enjoy_mujoco --algo=APPO --env=mujoco_pendulum --train_dir=./train_dir --experiment=APPO-mujoco_pendulum
|
175 |
+
```
|
176 |
+
|
177 |
+
|
178 |
+
You can also upload models to the Hugging Face Hub using the same script with the `--push_to_hub` flag.
|
179 |
+
See https://www.samplefactory.dev/10-huggingface/huggingface/ for more details
|
180 |
+
|
181 |
+
## Training with this model
|
182 |
+
|
183 |
+
To continue training with this model, use the `train` script corresponding to this environment:
|
184 |
+
```
|
185 |
+
python -m sf_examples.mujoco.train_mujoco --algo=APPO --env=mujoco_pendulum --train_dir=./train_dir --experiment=APPO-mujoco_pendulum --restart_behavior=resume --train_for_env_steps=10000000000
|
186 |
+
```
|
187 |
+
|
188 |
+
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.
|
189 |
+
|
checkpoint_p0/best_000001120_286720_reward_1000.000.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:af696076f15d5bb430126e201d86fdda8681abd335f4c5559b07aff560599537
|
3 |
+
size 68991
|
checkpoint_p0/checkpoint_001953536_500326400.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e0720d15efbd251e468c72cb292e55fcc0e0202e4846df72bed8a0a483231330
|
3 |
+
size 69255
|
checkpoint_p0/checkpoint_001953744_500432896.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:20fe32aed05f5e9549196b4c355f10188b77de4d0188783aefcf8adf6fdc2dee
|
3 |
+
size 69255
|
checkpoint_p0/milestones/checkpoint_000048240_12353536.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ca329039e8043b136091daf829c3bcd07d1b61cec8ce6ecab6d25d5bf2b7bb91
|
3 |
+
size 69935
|
checkpoint_p0/milestones/checkpoint_000097032_24854528.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:92ef922ac9e7dc83fcfb61b253d579dc10595da8a3813685d32ee7e91a12deab
|
3 |
+
size 69935
|
checkpoint_p0/milestones/checkpoint_000145640_37298176.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5d0861111f0dbd130692c80ae13f56e5236fbdf5eec762809f892c530e610850
|
3 |
+
size 69935
|
checkpoint_p0/milestones/checkpoint_000194248_49741824.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a6fef64635c5c3d708b48f0b1f0a59286b7fe61c009ebd5842aa0f6319a8e7a6
|
3 |
+
size 69935
|
checkpoint_p0/milestones/checkpoint_000242888_62193664.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:130470a048f8d9d1a25b8d0329e65905ec3a38acafd941ef5c041a200bb5efa4
|
3 |
+
size 69935
|
checkpoint_p0/milestones/checkpoint_000291584_74661888.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5841cfa195d5b61a754f5826ef84e6bba117a9196a1ea342ddac465972874a2c
|
3 |
+
size 69935
|
checkpoint_p0/milestones/checkpoint_000340224_87113728.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fb16f95ee0c7c465665b119a66dfd6da73d22d0fe651957bb1b05ba3b56bdcdb
|
3 |
+
size 69935
|
checkpoint_p0/milestones/checkpoint_000388928_99581952.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:15a242c6e7a4d60751a5d503013f40482138f9a827930e4d90b79fa3e1237698
|
3 |
+
size 69935
|
checkpoint_p0/milestones/checkpoint_000436896_111861760.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d82aed58d0b615588948b0d3b2934dc10b87323a8f4cebd1a392f10a6cb1e071
|
3 |
+
size 69979
|
checkpoint_p0/milestones/checkpoint_000484896_124149760.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0f5ec15918b8f0f7a958c140cb3f145cac15ae8b03886abb02d70017835ca63f
|
3 |
+
size 69979
|
checkpoint_p0/milestones/checkpoint_000533568_136609792.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b9cee96717e4f1a400959179626572e21491a0205d2187bf2af04ba6bce50163
|
3 |
+
size 69979
|
checkpoint_p0/milestones/checkpoint_000582176_149053440.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ab59029819f2a3428387c91305311a4251b34bde1989c1064cd80006a958657a
|
3 |
+
size 69979
|
checkpoint_p0/milestones/checkpoint_000631040_161562624.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0f647f49f79a5e7fb653380ca02c9c1291bbaf84cbc2d0b83351e639b19cf76d
|
3 |
+
size 69979
|
checkpoint_p0/milestones/checkpoint_000679696_174022656.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e84428fe391a7e1387f16f94feef4e0b9fac1297f06625e830f94658264fe36b
|
3 |
+
size 69979
|
checkpoint_p0/milestones/checkpoint_000727912_186368000.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:df6af8c053ec52bfbd0d600d2ba2c72bf6a65e52036eaffc5a7da842f7b88f30
|
3 |
+
size 69979
|
checkpoint_p0/milestones/checkpoint_000776064_198696960.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:939e4c24cd6499881ccf4391947aa115c02d4180823f54a66da711a1eb40b8ad
|
3 |
+
size 69979
|
checkpoint_p0/milestones/checkpoint_000823360_210804736.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:91e04a55eb4e75e396a46ccfdf20d8953eca13c38651457f97270e7b7bc187f8
|
3 |
+
size 69979
|
checkpoint_p0/milestones/checkpoint_000869360_222584832.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:580234e0c3a3b92e0b63f420c6c1374fb1a0a31e3c97ee25a29cf251d68d608c
|
3 |
+
size 69979
|
checkpoint_p0/milestones/checkpoint_000916608_234684416.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dfe7b9eea918ddb494f3b71764a2f812e9983ee47e8d003b50a64fa301824bc8
|
3 |
+
size 69979
|
checkpoint_p0/milestones/checkpoint_000964472_246947840.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:28ef178889e0fa3d92786bca103aa7e29b60d68dd75adfd1fde17750a52e39bd
|
3 |
+
size 69979
|
checkpoint_p0/milestones/checkpoint_001012296_259194880.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4210e09fa8f3cadf7e3bc26e55310fc4125a783875fedfd4a0b939766fec16dd
|
3 |
+
size 69979
|
checkpoint_p0/milestones/checkpoint_001060552_271548416.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e1204369fcc621df28400a3c220d7b28607af3dc091aefd5414b10ff73c3f86f
|
3 |
+
size 69979
|
checkpoint_p0/milestones/checkpoint_001108736_283885568.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fbe61a972ea2c4b35d80365dd2c37c957e1f7497c62ca9360d6384de107bd745
|
3 |
+
size 69979
|
checkpoint_p0/milestones/checkpoint_001156944_296230912.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:23b7140e39568ef22813f581dc78945e922c0961c244fd0116e8b34e19aaa0bd
|
3 |
+
size 69979
|
checkpoint_p0/milestones/checkpoint_001204912_308510720.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:76e92911f6974a15bd521e5e7160b4264ba6c2b1f35573fa60b0f166cc170c5d
|
3 |
+
size 69979
|
checkpoint_p0/milestones/checkpoint_001253184_320872448.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:29cda0b4a07725c54ffdecdf154841611d1145177373013de5723f4931b220c4
|
3 |
+
size 69979
|
checkpoint_p0/milestones/checkpoint_001301216_333176832.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5c13588a2c6db8c2b8e86c89a8ad58b67bdae8f0b223ee207c426ae131bd4e5e
|
3 |
+
size 69979
|
checkpoint_p0/milestones/checkpoint_001349432_345522176.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9c14a7e36676686cb8696c3e59cb793e84646b9a612e3fb759c243ec27b60ef8
|
3 |
+
size 69979
|
checkpoint_p0/milestones/checkpoint_001397544_357842944.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:16b539f95fa7f819a1ee41571c1bfa9dd5b9123cab310309e53a663cf5da130a
|
3 |
+
size 69979
|
checkpoint_p0/milestones/checkpoint_001445800_370196480.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:81a5949e6cc6b665e025036a9446e5ff0c8e53699bcdb3a3eee9f9c961cd4469
|
3 |
+
size 69979
|
checkpoint_p0/milestones/checkpoint_001494040_382550016.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6e4b1cd93ed755ed20b147039a961a86774e0dbe96dcffdbfb7574180240b518
|
3 |
+
size 69979
|
checkpoint_p0/milestones/checkpoint_001542256_394895360.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:14e6c913c75b44f72870cdf087a2344687b8bfae7a311bf25e9a11fdf8fe2c42
|
3 |
+
size 69979
|
checkpoint_p0/milestones/checkpoint_001590448_407232512.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ca5aa7c839caba6714c45607ff562ea9b1e7831773329c1af354796ca467d703
|
3 |
+
size 69979
|
checkpoint_p0/milestones/checkpoint_001638608_419561472.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a6421b7fdff3c472ec47516b22e54670a425caf2385b46ee70529178cb4047bf
|
3 |
+
size 69979
|
checkpoint_p0/milestones/checkpoint_001686824_431906816.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6d3aefe36768d4257f9fd65804c24a4a2b6bbf3cd292f420b8e63d7ad51337e7
|
3 |
+
size 69979
|
checkpoint_p0/milestones/checkpoint_001734824_444194816.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5b4162fdf0b8e3e898152a7034c9151329c7ec0a754f7599c2fe1211ea7dfccb
|
3 |
+
size 69979
|
checkpoint_p0/milestones/checkpoint_001783072_456548352.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:732c35cb1bc178bcb30b7a7326e93c49b98536ce0787b00ec563a26818f0111c
|
3 |
+
size 69979
|
checkpoint_p0/milestones/checkpoint_001831096_468844544.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aa410ad0b88cae2834aef7e52bb961e16c6def0e096080331e9916ed874b5301
|
3 |
+
size 69979
|
checkpoint_p0/milestones/checkpoint_001878968_481099776.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:63b30a9f0e63f5f955d9f6aa53cf880d8802228335bbbdd4c73faf0f8aeb0696
|
3 |
+
size 69979
|
checkpoint_p0/milestones/checkpoint_001926936_493387776.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1c5b555792b7b6378d822159131e5abab450298c04f9b1d211b94d926ec0f1dc
|
3 |
+
size 69979
|
checkpoint_p1/best_000001120_286720_reward_1000.000.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7bba1da1a79b5a108f182912eff9754e25504e656987c02206531db1e8bf8aab
|
3 |
+
size 68991
|
checkpoint_p1/checkpoint_001952888_500006912.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bec961c01765572532db25878889492a15778ae154e9800e7a41ca560b220edb
|
3 |
+
size 69255
|
checkpoint_p1/checkpoint_001952920_500015104.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a24b90265f72eeda30dbc1e0240c00bd817bd3c73aaa95ed2a48e44974d7656a
|
3 |
+
size 69255
|