chanyoungkim/ppo-qwen2.5-1.5b-alfworld-step70

PPO / Qwen2.5-1.5B-Instruct / ALFWorld — optimizer step 70

RL fine-tuning of Qwen/Qwen2.5-1.5B-Instruct on ALFWorld with PPO, using langfengQ/verl-agent.

This checkpoint: optimizer step 70.

Optimizer step	70
In-training validation success rate	36.7%
Backbone	Qwen/Qwen2.5-1.5B-Instruct (1.54B params, bf16)
Environment	ALFWorld alfworld/AlfredTWEnv
Hardware	2x NVIDIA A100 80GB

Standalone evaluation at this step

128 ALFWorld valid_seen tasks, 3 seeds, temperature 0.4, max 50 env steps:

	value
success rate	35.42% ± 1.61
base Qwen2.5-1.5B-Instruct	2.86% ± 0.37
mean episode length	39.3 (base: 49.1)
format rate	97.6% (base: 98.1%)

Training curve

In-training validation success rate (val/success_rate), measured every 5 optimizer steps on a 32-task validation batch (shown every 10 steps below). This is a smaller and noisier probe than the 128-task standalone evaluation.

optimizer step	success rate (%)
0	6.2
10	7.8
20	13.3
30	14.8
40	16.4
50	34.4
60	35.2
70	36.7
80	43.0
90	50.0
100	59.4
110	64.8
120	63.3
130	70.3
140	68.0
150	64.8

Run history

This run (ppo_qwen2.5_1.5b_v3) is the third PPO attempt. An earlier attempt collapsed — its step-130 checkpoint scored 9.90% with a 1.3% action format rate, i.e. the policy stopped emitting parseable actions. The run published here was restarted from checkpoints twice (at step 30 and step 80) for operational reasons, not because of divergence; the validation curve is continuous across those boundaries.

Hyperparameters

group	parameter	value
RL	adv_estimator	gae
RL	actor.use_kl_loss / kl_loss_coef	True / 0.01
RL	kl_loss_type	low_var_kl
RL	invalid action penalty	True, coef 0.1
Optim	actor learning rate	1e-6
Optim	critic learning rate	1e-5
Optim	ppo_mini_batch_size	256
Data	train_batch_size	128
Data	group size (env.rollout.n)	1
Data	episodes per step	128 x 1 = 128
Data	max_prompt_length / max_response_length	2048 / 512
Rollout	engine / TP / gpu_memory_utilization	vLLM / 2 / 0.6
Rollout	val_kwargs.temperature	0.4
Train	save_freq / test_freq	10 / 5

Files

path	contents
model.safetensors, config.json, tokenizer files	bf16 weights, merged from the FSDP shards with scripts/model_merger.py. lm_head is omitted because tie_word_embeddings=true (same layout as the base Qwen release).
training_state/actor/*.pt	FSDP-sharded actor weights, Adam optimizer state, RNG/scheduler state

training_state/ lets you resume RL training from this exact optimizer step. The shards are written for world_size=2; resuming on a different number of GPUs requires resharding.

Other checkpoints from this run

step 10 · step 20 · step 30 · step 60 · step 70 · step 80 · step 130 · step 140 · step 150

Not every step was retained: the run used trainer.max_actor_ckpt_to_keep, so some intermediate checkpoints were pruned during training.

Caveats

• Do not use is_correct / pass@1 from verl logs; they are hardcoded to 1.0. Use val/success_rate.
• Evaluated on ALFWorld valid_seen only; valid_unseen was not run.
• A StraTA reproduction is published alongside these models (chanyoungkim/strata-qwen2.5-1.5b-alfworld-step*). It uses a different agent scaffold (140 eval tasks, temperature 0.7, 7168-token prompts, strategy-conditioned prompting) and is therefore not directly comparable to the numbers above.

Usage

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

repo = "chanyoungkim/ppo-qwen2.5-1.5b-alfworld-step70"
model = AutoModelForCausalLM.from_pretrained(repo, dtype=torch.bfloat16, device_map="auto")
tok = AutoTokenizer.from_pretrained(repo)