Instructions to use Dassem/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-endangered_gregarious_wolf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Dassem/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-endangered_gregarious_wolf with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Dassem/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-endangered_gregarious_wolf")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Dassem/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-endangered_gregarious_wolf")
model = AutoModelForCausalLM.from_pretrained("Dassem/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-endangered_gregarious_wolf", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Dassem/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-endangered_gregarious_wolf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Dassem/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-endangered_gregarious_wolf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Dassem/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-endangered_gregarious_wolf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Dassem/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-endangered_gregarious_wolf

SGLang

How to use Dassem/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-endangered_gregarious_wolf with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Dassem/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-endangered_gregarious_wolf" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Dassem/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-endangered_gregarious_wolf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Dassem/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-endangered_gregarious_wolf" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Dassem/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-endangered_gregarious_wolf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Dassem/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-endangered_gregarious_wolf with Docker Model Runner:
```
docker model run hf.co/Dassem/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-endangered_gregarious_wolf
```

Dassem commited on Apr 29, 2025

Commit

087ffc3

verified ·

1 Parent(s): fa34645

End of training

Browse files

Files changed (4) hide show

all_results.json +5 -5
model.safetensors +1 -1
train_results.json +5 -5
trainer_state.json +115 -115

all_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 3.151223813802062e-06,
-    "train_runtime": 518.4281,
-    "train_samples": 84,
-    "train_samples_per_second": 0.617,
-    "train_steps_per_second": 0.039
 }

 {
     "total_flos": 0.0,
+    "train_loss": 9.376462548971176e-06,
+    "train_runtime": 213.5018,
+    "train_samples": 28,
+    "train_samples_per_second": 1.499,
+    "train_steps_per_second": 0.094
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9a701aeb54101ce4e42a9633ea798be4a0e3fe48627a8452bd09b42a9b7e3ae
 size 1976163472

 version https://git-lfs.github.com/spec/v1
+oid sha256:40f05f6a78dac6fcf250222e2db013b8bc0d538bb044567c88092de29c8014fe
 size 1976163472

train_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 3.151223813802062e-06,
-    "train_runtime": 518.4281,
-    "train_samples": 84,
-    "train_samples_per_second": 0.617,
-    "train_steps_per_second": 0.039
 }

 {
     "total_flos": 0.0,
+    "train_loss": 9.376462548971176e-06,
+    "train_runtime": 213.5018,
+    "train_samples": 28,
+    "train_samples_per_second": 1.499,
+    "train_steps_per_second": 0.094
 }

trainer_state.json CHANGED Viewed

@@ -2,7 +2,7 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.8571428571428572,
   "eval_steps": 500,
   "global_step": 20,
   "is_hyper_param_search": false,
@@ -10,209 +10,209 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "completion_length": 343.84375,
-      "epoch": 0.19047619047619047,
-      "grad_norm": 6.41450834274292,
       "kl": 0.0,
       "learning_rate": 5e-07,
       "loss": 0.0,
-      "reward": 1.3421010066522285,
-      "reward_std": 1.406665334085119,
-      "rewards/concensus_correctness_reward_func": 0.6851250007748604,
-      "rewards/consensus_reward_func": 0.0625,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.125,
-      "rewards/question_recreation_reward_func": 0.32650725438725203,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.015625,
-      "rewards/xmlcount_reward_func": 0.1273437519557774,
       "step": 2
     },
     {
-      "completion_length": 339.53125,
-      "epoch": 0.38095238095238093,
-      "grad_norm": 6.3102498054504395,
-      "kl": 0.0012349215921858558,
       "learning_rate": 4.864543104251586e-07,
       "loss": 0.0,
-      "reward": 0.3265813000034541,
-      "reward_std": 0.4629429771230207,
-      "rewards/concensus_correctness_reward_func": 0.0,
-      "rewards/consensus_reward_func": 0.0625,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.0625,
-      "rewards/question_recreation_reward_func": 0.13289380201604217,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.06868749670684338,
       "step": 4
     },
     {
-      "completion_length": 296.1875,
-      "epoch": 0.5714285714285714,
-      "grad_norm": 61.84025573730469,
-      "kl": 0.005961592213679978,
       "learning_rate": 4.472851273490984e-07,
       "loss": 0.0,
-      "reward": 0.5405496190069243,
-      "reward_std": 0.5028865041094832,
-      "rewards/concensus_correctness_reward_func": 0.059812501072883606,
-      "rewards/consensus_reward_func": 0.125,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.0,
-      "rewards/question_recreation_reward_func": 0.27689335064496845,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.07884375378489494,
       "step": 6
     },
     {
-      "completion_length": 249.1875,
-      "epoch": 0.7619047619047619,
-      "grad_norm": 56.74770736694336,
-      "kl": 0.002046526838967111,
       "learning_rate": 3.867370395306068e-07,
       "loss": 0.0,
-      "reward": 0.37825396441621706,
-      "reward_std": 0.37752981589437695,
-      "rewards/concensus_correctness_reward_func": 0.0,
-      "rewards/consensus_reward_func": 0.0625,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.0625,
-      "rewards/question_recreation_reward_func": 0.18716021499130875,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.06609375029802322,
       "step": 8
     },
     {
-      "completion_length": 285.75,
-      "epoch": 0.9523809523809523,
-      "grad_norm": 35.71620178222656,
-      "kl": 0.0014948487314541126,
       "learning_rate": 3.1137137178519977e-07,
       "loss": 0.0,
-      "reward": 0.6967899320879951,
-      "reward_std": 0.5912124498172489,
-      "rewards/concensus_correctness_reward_func": 0.06024999916553497,
-      "rewards/consensus_reward_func": 0.125,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.125,
-      "rewards/question_recreation_reward_func": 0.2623211840982549,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.12421874701976776,
       "step": 10
     },
     {
-      "completion_length": 347.2916666666667,
-      "epoch": 1.0952380952380953,
-      "grad_norm": 5.5424346923828125,
-      "kl": 0.001293833294766955,
       "learning_rate": 2.2935516363191693e-07,
       "loss": 0.0,
-      "reward": 0.1296683083055541,
-      "reward_std": 0.42109029918598634,
-      "rewards/concensus_correctness_reward_func": 0.0,
-      "rewards/consensus_reward_func": 0.08333333333333333,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0,
-      "rewards/question_recreation_reward_func": 0.13004330720286816,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": -0.08370832974712054,
       "step": 12
     },
     {
-      "completion_length": 373.09375,
-      "epoch": 1.2857142857142856,
-      "grad_norm": 17.043167114257812,
-      "kl": 0.0012364095746306702,
       "learning_rate": 1.4957614383675767e-07,
       "loss": 0.0,
-      "reward": 0.3166529495501891,
-      "reward_std": 0.406706450904494,
       "rewards/concensus_correctness_reward_func": 0.0,
       "rewards/consensus_reward_func": 0.0,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0625,
-      "rewards/question_recreation_reward_func": 0.16937170409073588,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.08478125440888107,
       "step": 14
     },
     {
-      "completion_length": 245.1875,
-      "epoch": 1.4761904761904763,
-      "grad_norm": 27.399072647094727,
-      "kl": 0.0028427706747606862,
       "learning_rate": 8.067960709356478e-08,
       "loss": 0.0,
-      "reward": 0.6848066907841712,
-      "reward_std": 0.6611888102197554,
-      "rewards/concensus_correctness_reward_func": 0.06012500077486038,
-      "rewards/consensus_reward_func": 0.125,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.125,
-      "rewards/question_recreation_reward_func": 0.25196293997578323,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.12271874817088246,
       "step": 16
     },
     {
-      "completion_length": 264.25,
-      "epoch": 1.6666666666666665,
-      "grad_norm": 42.305606842041016,
-      "kl": 0.0022985513096500654,
       "learning_rate": 3.013156219837776e-08,
-      "loss": 0.0,
-      "reward": 1.2035528365522623,
-      "reward_std": 1.0453436647367198,
-      "rewards/concensus_correctness_reward_func": 0.15699999779462814,
-      "rewards/consensus_reward_func": 0.25,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.1875,
-      "rewards/question_recreation_reward_func": 0.26874033408239484,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.015625,
-      "rewards/xmlcount_reward_func": 0.3246875018812716,
       "step": 18
     },
     {
-      "completion_length": 378.5625,
-      "epoch": 1.8571428571428572,
-      "grad_norm": 64.05872344970703,
-      "kl": 0.013361819263081998,
       "learning_rate": 3.4096741493194193e-09,
       "loss": 0.0,
-      "reward": 0.8212161803094205,
-      "reward_std": 1.0907838449347764,
-      "rewards/concensus_correctness_reward_func": 0.06012500077486038,
-      "rewards/consensus_reward_func": 0.25,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.1875,
-      "rewards/question_recreation_reward_func": 0.24912242317805067,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.07446875050663948,
       "step": 20
     },
     {
-      "epoch": 1.8571428571428572,
       "step": 20,
       "total_flos": 0.0,
-      "train_loss": 3.151223813802062e-06,
-      "train_runtime": 518.4281,
-      "train_samples_per_second": 0.617,
-      "train_steps_per_second": 0.039
     }
   ],
   "logging_steps": 2,
   "max_steps": 20,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 2,
   "save_steps": 25,
   "stateful_callbacks": {
     "TrainerControl": {

   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
+  "epoch": 5.0,
   "eval_steps": 500,
   "global_step": 20,
   "is_hyper_param_search": false,
   "is_world_process_zero": true,
   "log_history": [
     {
+      "completion_length": 409.15625,
+      "epoch": 0.5714285714285714,
+      "grad_norm": 9.875356674194336,
       "kl": 0.0,
       "learning_rate": 5e-07,
       "loss": 0.0,
+      "reward": 0.3602086678147316,
+      "reward_std": 0.4318295910725283,
+      "rewards/concensus_correctness_reward_func": 0.0,
+      "rewards/consensus_reward_func": 0.0,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.0625,
+      "rewards/question_recreation_reward_func": 0.21970867551863194,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.07800000044517219,
       "step": 2
     },
     {
+      "completion_length": 385.7916666666667,
+      "epoch": 1.0,
+      "grad_norm": 117.25511169433594,
+      "kl": 0.0056322487313688425,
       "learning_rate": 4.864543104251586e-07,
       "loss": 0.0,
+      "reward": 0.4368452951312065,
+      "reward_std": 0.7759081007291874,
+      "rewards/concensus_correctness_reward_func": 0.07024999956289928,
+      "rewards/consensus_reward_func": 0.0,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.08333333333333333,
+      "rewards/question_recreation_reward_func": 0.3702619541436434,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": -0.08699999873836835,
       "step": 4
     },
     {
+      "completion_length": 397.40625,
+      "epoch": 1.5714285714285714,
+      "grad_norm": 8.081494331359863,
+      "kl": 0.004398276567371795,
       "learning_rate": 4.472851273490984e-07,
       "loss": 0.0,
+      "reward": 0.6226073214202188,
+      "reward_std": 0.5249523999518715,
+      "rewards/concensus_correctness_reward_func": 0.0951249971985817,
+      "rewards/consensus_reward_func": 0.0,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.1875,
+      "rewards/question_recreation_reward_func": 0.22788858361309394,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.11209374759346247,
       "step": 6
     },
     {
+      "completion_length": 350.2083333333333,
+      "epoch": 2.0,
+      "grad_norm": 8.431388854980469,
+      "kl": 0.0031580582823759564,
       "learning_rate": 3.867370395306068e-07,
       "loss": 0.0,
+      "reward": 0.5635077450424433,
+      "reward_std": 0.581715359352529,
+      "rewards/concensus_correctness_reward_func": -0.007500000298023224,
+      "rewards/consensus_reward_func": 0.08333333333333333,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.0,
+      "rewards/question_recreation_reward_func": 0.3322160681709647,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.15545834538837275,
       "step": 8
     },
     {
+      "completion_length": 461.21875,
+      "epoch": 2.571428571428571,
+      "grad_norm": 4.464199066162109,
+      "kl": 0.005941408970102202,
       "learning_rate": 3.1137137178519977e-07,
       "loss": 0.0,
+      "reward": 0.17902526422403753,
+      "reward_std": 0.6957999468722846,
+      "rewards/concensus_correctness_reward_func": 0.0,
+      "rewards/consensus_reward_func": 0.0,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.0,
+      "rewards/question_recreation_reward_func": 0.25424400495830923,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": -0.07521873898804188,
       "step": 10
     },
     {
+      "completion_length": 420.7916666666667,
+      "epoch": 3.0,
+      "grad_norm": 13.741572380065918,
+      "kl": 0.009973627614575284,
       "learning_rate": 2.2935516363191693e-07,
       "loss": 0.0,
+      "reward": 1.2170113790780306,
+      "reward_std": 1.650551260759433,
+      "rewards/concensus_correctness_reward_func": 0.8333333333333334,
+      "rewards/consensus_reward_func": 0.0,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0,
+      "rewards/question_recreation_reward_func": 0.2790946864212553,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.10458333293596904,
       "step": 12
     },
     {
+      "completion_length": 365.0,
+      "epoch": 3.571428571428571,
+      "grad_norm": 11.39220905303955,
+      "kl": 0.003105924144620076,
       "learning_rate": 1.4957614383675767e-07,
       "loss": 0.0,
+      "reward": 0.3411784037016332,
+      "reward_std": 0.5926390361855738,
       "rewards/concensus_correctness_reward_func": 0.0,
       "rewards/consensus_reward_func": 0.0,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0625,
+      "rewards/question_recreation_reward_func": 0.29302217275835574,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": -0.014343749731779099,
       "step": 14
     },
     {
+      "completion_length": 402.75,
+      "epoch": 4.0,
+      "grad_norm": 5.019252300262451,
+      "kl": 0.0031478352757403627,
       "learning_rate": 8.067960709356478e-08,
       "loss": 0.0,
+      "reward": 0.48165157514934737,
+      "reward_std": 0.5276354240098348,
+      "rewards/concensus_correctness_reward_func": 0.12683332959810892,
+      "rewards/consensus_reward_func": 0.0,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.08333333333333333,
+      "rewards/question_recreation_reward_func": 0.3021932320358853,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": -0.03070833347737789,
       "step": 16
     },
     {
+      "completion_length": 391.84375,
+      "epoch": 4.571428571428571,
+      "grad_norm": 21.691829681396484,
+      "kl": 0.05942032911843853,
       "learning_rate": 3.013156219837776e-08,
+      "loss": 0.0001,
+      "reward": 0.8444168888963759,
+      "reward_std": 0.878114497900242,
+      "rewards/concensus_correctness_reward_func": 0.018124999478459358,
+      "rewards/consensus_reward_func": 0.0625,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.125,
+      "rewards/question_recreation_reward_func": 0.3953543780371547,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.24343750439584255,
       "step": 18
     },
     {
+      "completion_length": 413.7916666666667,
+      "epoch": 5.0,
+      "grad_norm": 5.071010112762451,
+      "kl": 0.005696416522065799,
       "learning_rate": 3.4096741493194193e-09,
       "loss": 0.0,
+      "reward": 1.6230570636689663,
+      "reward_std": 1.8531924900598824,
+      "rewards/concensus_correctness_reward_func": 0.8333333333333334,
+      "rewards/consensus_reward_func": 0.0,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.16666666666666666,
+      "rewards/question_recreation_reward_func": 0.42043201873699826,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.20262499153614044,
       "step": 20
     },
     {
+      "epoch": 5.0,
       "step": 20,
       "total_flos": 0.0,
+      "train_loss": 9.376462548971176e-06,
+      "train_runtime": 213.5018,
+      "train_samples_per_second": 1.499,
+      "train_steps_per_second": 0.094
     }
   ],
   "logging_steps": 2,
   "max_steps": 20,
   "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
   "save_steps": 25,
   "stateful_callbacks": {
     "TrainerControl": {